x

.devcontainer/docker-compose.yaml

@@ -5,10 +5,10 @@ services:
       dockerfile: libs/langchain/dev.Dockerfile
       context: ..
     volumes:
-      # Update this to wherever you want VS Code to mount the folder of your project
+   # Update this to wherever you want VS Code to mount the folder of your project
       - ..:/workspaces/langchain:cached
     networks:
-      - langchain-network
+      - langchain-network 
   #   environment:
   #     MONGO_ROOT_USERNAME: root
   #     MONGO_ROOT_PASSWORD: example123
@@ -28,3 +28,5 @@ services:
 networks:
   langchain-network:
     driver: bridge
+    
+    

.github/ISSUE_TEMPLATE/config.yml

@@ -4,6 +4,9 @@ contact_links:
   - name: 🤔 Question or Problem
     about: Ask a question or ask about a problem in GitHub Discussions.
     url: https://www.github.com/langchain-ai/langchain/discussions/categories/q-a
+  - name: Discord
+    url: https://discord.gg/6adMQxSpJS
+    about: General community discussions
   - name: Feature Request
     url: https://www.github.com/langchain-ai/langchain/discussions/categories/ideas
     about: Suggest a feature or an idea

.github/actions/people/app/main.py

@@ -350,7 +350,11 @@ def get_graphql_pr_edges(*, settings: Settings, after: Union[str, None] = None):
         print("Querying PRs...")
     else:
         print(f"Querying PRs with cursor {after}...")
-    data = get_graphql_response(settings=settings, query=prs_query, after=after)
+    data = get_graphql_response(
+        settings=settings,
+        query=prs_query,
+        after=after
+    )
     graphql_response = PRsResponse.model_validate(data)
     return graphql_response.data.repository.pullRequests.edges
 
@@ -480,16 +484,10 @@ def get_contributors(settings: Settings):
             lines_changed = pr.additions + pr.deletions
             score = _logistic(files_changed, 20) + _logistic(lines_changed, 100)
             contributor_scores[pr.author.login] += score
-            three_months_ago = datetime.now(timezone.utc) - timedelta(days=3 * 30)
+            three_months_ago = (datetime.now(timezone.utc) - timedelta(days=3*30))
             if pr.createdAt > three_months_ago:
                 recent_contributor_scores[pr.author.login] += score
-    return (
-        contributors,
-        contributor_scores,
-        recent_contributor_scores,
-        reviewers,
-        authors,
-    )
+    return contributors, contributor_scores, recent_contributor_scores, reviewers, authors
 
 
 def get_top_users(
@@ -526,13 +524,9 @@ if __name__ == "__main__":
     # question_commentors, question_last_month_commentors, question_authors = get_experts(
     #     settings=settings
     # )
-    (
-        contributors,
-        contributor_scores,
-        recent_contributor_scores,
-        reviewers,
-        pr_authors,
-    ) = get_contributors(settings=settings)
+    contributors, contributor_scores, recent_contributor_scores, reviewers, pr_authors = get_contributors(
+        settings=settings
+    )
     # authors = {**question_authors, **pr_authors}
     authors = {**pr_authors}
     maintainers_logins = {
@@ -565,7 +559,7 @@ if __name__ == "__main__":
         maintainers.append(
             {
                 "login": login,
-                "count": contributors[login],  # + question_commentors[login],
+                "count": contributors[login], #+ question_commentors[login],
                 "avatarUrl": user.avatarUrl,
                 "twitterUsername": user.twitterUsername,
                 "url": user.url,
@@ -621,7 +615,9 @@ if __name__ == "__main__":
     new_people_content = yaml.dump(
         people, sort_keys=False, width=200, allow_unicode=True
     )
-    if people_old_content == new_people_content:
+    if (
+        people_old_content == new_people_content
+    ):
         logging.info("The LangChain People data hasn't changed, finishing.")
         sys.exit(0)
     people_path.write_text(new_people_content, encoding="utf-8")
@@ -634,7 +630,9 @@ if __name__ == "__main__":
     logging.info(f"Creating a new branch {branch_name}")
     subprocess.run(["git", "checkout", "-B", branch_name], check=True)
     logging.info("Adding updated file")
-    subprocess.run(["git", "add", str(people_path)], check=True)
+    subprocess.run(
+        ["git", "add", str(people_path)], check=True
+    )
     logging.info("Committing updated file")
     message = "👥 Update LangChain people data"
     result = subprocess.run(["git", "commit", "-m", message], check=True)
@@ -643,4 +641,4 @@ if __name__ == "__main__":
     logging.info("Creating PR")
     pr = repo.create_pull(title=message, body=message, base="master", head=branch_name)
     logging.info(f"Created PR: {pr.number}")
-    logging.info("Finished")
+    logging.info("Finished")

.github/scripts/check_diff.py

@@ -1,13 +1,11 @@
-import glob
 import json
-import os
-import re
 import sys
+import os
+from typing import Dict, List, Set
+
 import tomllib
 from collections import defaultdict
-from typing import Dict, List, Set
-from pathlib import Path
-
+import glob
 
 LANGCHAIN_DIRS = [
     "libs/core",
@@ -17,58 +15,22 @@ LANGCHAIN_DIRS = [
     "libs/experimental",
 ]
 
-
 def all_package_dirs() -> Set[str]:
-    return {
-        "/".join(path.split("/")[:-1]).lstrip("./")
-        for path in glob.glob("./libs/**/pyproject.toml", recursive=True)
-        if "libs/cli" not in path and "libs/standard-tests" not in path
-    }
+    return {"/".join(path.split("/")[:-1]) for path in glob.glob("./libs/**/pyproject.toml", recursive=True)}
 
 
 def dependents_graph() -> dict:
-    """
-    Construct a mapping of package -> dependents, such that we can
-    run tests on all dependents of a package when a change is made.
-    """
     dependents = defaultdict(set)
 
     for path in glob.glob("./libs/**/pyproject.toml", recursive=True):
         if "template" in path:
             continue
-
-        # load regular and test deps from pyproject.toml
         with open(path, "rb") as f:
-            pyproject = tomllib.load(f)["tool"]["poetry"]
-
+            pyproject = tomllib.load(f)['tool']['poetry']
         pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
-        for dep in [
-            *pyproject["dependencies"].keys(),
-            *pyproject["group"]["test"]["dependencies"].keys(),
-        ]:
+        for dep in pyproject['dependencies']:
             if "langchain" in dep:
                 dependents[dep].add(pkg_dir)
-                continue
-
-        # load extended deps from extended_testing_deps.txt
-        package_path = Path(path).parent
-        extended_requirement_path = package_path / "extended_testing_deps.txt"
-        if extended_requirement_path.exists():
-            with open(extended_requirement_path, "r") as f:
-                extended_deps = f.read().splitlines()
-                for depline in extended_deps:
-                    if depline.startswith("-e "):
-                        # editable dependency
-                        assert depline.startswith(
-                            "-e ../partners/"
-                        ), "Extended test deps should only editable install partner packages"
-                        partner = depline.split("partners/")[1]
-                        dep = f"langchain-{partner}"
-                    else:
-                        dep = depline.split("==")[0]
-
-                    if "langchain" in dep:
-                        dependents[dep].add(pkg_dir)
     return dependents
 
 
@@ -85,53 +47,6 @@ def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
     return list(updated)
 
 
-def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
-    min_python = "3.8"
-    max_python = "3.12"
-
-    # custom logic for specific directories
-    if dir_ == "libs/partners/milvus":
-        # milvus poetry doesn't allow 3.12 because they
-        # declare deps in funny way
-        max_python = "3.11"
-
-    if dir_ in ["libs/community", "libs/langchain"] and job == "extended-tests":
-        # community extended test resolution in 3.12 is slow
-        # even in uv
-        max_python = "3.11"
-
-    if dir_ == "libs/community" and job == "compile-integration-tests":
-        # community integration deps are slow in 3.12
-        max_python = "3.11"
-
-    return [
-        {"working-directory": dir_, "python-version": min_python},
-        {"working-directory": dir_, "python-version": max_python},
-    ]
-
-
-def _get_configs_for_multi_dirs(
-    job: str, dirs_to_run: List[str], dependents: dict
-) -> List[Dict[str, str]]:
-    if job == "lint":
-        dirs = add_dependents(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
-            dependents,
-        )
-    elif job in ["test", "compile-integration-tests", "dependencies"]:
-        dirs = add_dependents(
-            dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
-        )
-    elif job == "extended-tests":
-        dirs = list(dirs_to_run["extended-test"])
-    else:
-        raise ValueError(f"Unknown job: {job}")
-
-    return [
-        config for dir_ in dirs for config in _get_configs_for_single_dir(job, dir_)
-    ]
-
-
 if __name__ == "__main__":
     files = sys.argv[1:]
 
@@ -205,23 +120,14 @@ if __name__ == "__main__":
 
     dependents = dependents_graph()
 
-    # we now have dirs_by_job
-    # todo: clean this up
-
-    map_job_to_configs = {
-        job: _get_configs_for_multi_dirs(job, dirs_to_run, dependents)
-        for job in [
-            "lint",
-            "test",
-            "extended-tests",
-            "compile-integration-tests",
-            "dependencies",
-        ]
+    outputs = {
+        "dirs-to-lint": add_dependents(
+            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
+        ),
+        "dirs-to-test": add_dependents(dirs_to_run["test"] | dirs_to_run["extended-test"], dependents),
+        "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
+        "docs-edited": "true" if docs_edited else "",
     }
-    map_job_to_configs["test-doc-imports"] = (
-        [{"python-version": "3.12"}] if docs_edited else []
-    )
-
-    for key, value in map_job_to_configs.items():
+    for key, value in outputs.items():
         json_output = json.dumps(value)
         print(f"{key}={json_output}")

.github/scripts/check_prerelease_dependencies.py

@@ -1,35 +0,0 @@
-import sys
-import tomllib
-
-if __name__ == "__main__":
-    # Get the TOML file path from the command line argument
-    toml_file = sys.argv[1]
-
-    # read toml file
-    with open(toml_file, "rb") as file:
-        toml_data = tomllib.load(file)
-
-    # see if we're releasing an rc
-    version = toml_data["tool"]["poetry"]["version"]
-    releasing_rc = "rc" in version
-
-    # if not, iterate through dependencies and make sure none allow prereleases
-    if not releasing_rc:
-        dependencies = toml_data["tool"]["poetry"]["dependencies"]
-        for lib in dependencies:
-            dep_version = dependencies[lib]
-            dep_version_string = (
-                dep_version["version"] if isinstance(dep_version, dict) else dep_version
-            )
-
-            if "rc" in dep_version_string:
-                raise ValueError(
-                    f"Dependency {lib} has a prerelease version. Please remove this."
-                )
-
-            if isinstance(dep_version, dict) and dep_version.get(
-                "allow-prereleases", False
-            ):
-                raise ValueError(
-                    f"Dependency {lib} has allow-prereleases set to true. Please remove this."
-                )

.github/scripts/get_min_versions.py

@@ -1,11 +1,6 @@
 import sys
 
-if sys.version_info >= (3, 11):
-    import tomllib
-else:
-    # for python 3.10 and below, which doesnt have stdlib tomllib
-    import tomli as tomllib
-
+import tomllib
 from packaging.version import parse as parse_version
 import re
 
@@ -14,11 +9,8 @@ MIN_VERSION_LIBS = [
     "langchain-community",
     "langchain",
     "langchain-text-splitters",
-    "SQLAlchemy",
 ]
 
-SKIP_IF_PULL_REQUEST = ["langchain-core"]
-
 
 def get_min_version(version: str) -> str:
     # base regex for x.x.x with cases for rc/post/etc
@@ -45,7 +37,7 @@ def get_min_version(version: str) -> str:
     raise ValueError(f"Unrecognized version format: {version}")
 
 
-def get_min_version_from_toml(toml_path: str, versions_for: str):
+def get_min_version_from_toml(toml_path: str):
     # Parse the TOML file
     with open(toml_path, "rb") as file:
         toml_data = tomllib.load(file)
@@ -58,10 +50,6 @@ def get_min_version_from_toml(toml_path: str, versions_for: str):
 
     # Iterate over the libs in MIN_VERSION_LIBS
     for lib in MIN_VERSION_LIBS:
-        if versions_for == "pull_request" and lib in SKIP_IF_PULL_REQUEST:
-            # some libs only get checked on release because of simultaneous
-            # changes
-            continue
         # Check if the lib is present in the dependencies
         if lib in dependencies:
             # Get the version string
@@ -82,10 +70,10 @@ def get_min_version_from_toml(toml_path: str, versions_for: str):
 if __name__ == "__main__":
     # Get the TOML file path from the command line argument
     toml_file = sys.argv[1]
-    versions_for = sys.argv[2]
-    assert versions_for in ["release", "pull_request"]
 
     # Call the function to get the minimum versions
-    min_versions = get_min_version_from_toml(toml_file, versions_for)
+    min_versions = get_min_version_from_toml(toml_file)
 
-    print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))
+    print(
+        " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
+    )

.github/workflows/_compile_integration_test.yml

@@ -7,10 +7,6 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -21,14 +17,22 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: "poetry run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+          - "3.12"
+    name: "poetry run pytest -m compile tests/integration_tests #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: compile-integration

.github/workflows/_dependencies.yml

@@ -11,10 +11,6 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -25,14 +21,22 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: dependency checks ${{ inputs.python-version }}
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+          - "3.12"
+    name: dependency checks ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: pydantic-cross-compat

.github/workflows/_integration_test.yml

@@ -6,10 +6,6 @@ on:
       working-directory:
         required: true
         type: string
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -20,14 +16,19 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: Python ${{ inputs.python-version }}
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core

.github/workflows/_lint.yml

@@ -11,10 +11,6 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -25,15 +21,27 @@ env:
 
 jobs:
   build:
-    name: "make lint #${{ inputs.python-version }}"
+    name: "make lint #${{ matrix.python-version }}"
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        # Only lint on the min and max supported Python versions.
+        # It's extremely unlikely that there's a lint issue on any version in between
+        # that doesn't show up on the min or max versions.
+        #
+        # GitHub rate-limits how many jobs can be running at any one time.
+        # Starting new jobs is also relatively slow,
+        # so linting on fewer versions makes CI faster.
+        python-version:
+          - "3.8"
+          - "3.12"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: lint-with-extras
@@ -78,7 +86,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache
-          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
 
       - name: Analysing the code with our lint
@@ -112,7 +120,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache_test
-          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
       - name: Analysing the code with our lint
         working-directory: ${{ inputs.working-directory }}

.github/workflows/_release.yml

@@ -122,6 +122,7 @@ jobs:
           fi
           {
             echo 'release-body<<EOF'
+            echo "# Release $TAG"
             echo $PREAMBLE
             echo
             git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR
@@ -189,7 +190,7 @@ jobs:
             --extra-index-url https://test.pypi.org/simple/ \
             "$PKG_NAME==$VERSION" || \
           ( \
-            sleep 15 && \
+            sleep 5 && \
             poetry run pip install \
               --extra-index-url https://test.pypi.org/simple/ \
               "$PKG_NAME==$VERSION" \
@@ -221,17 +222,12 @@ jobs:
         run: make tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: Check for prerelease versions
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          poetry run python $GITHUB_WORKSPACE/.github/scripts/check_prerelease_dependencies.py pyproject.toml
-
       - name: Get minimum versions
         working-directory: ${{ inputs.working-directory }}
         id: min-version
         run: |
           poetry run pip install packaging
-          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release)"
+          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
           echo "min-versions=$min_versions"
 
@@ -290,7 +286,6 @@ jobs:
           VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
           UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          UNSTRUCTURED_API_KEY: ${{ secrets.UNSTRUCTURED_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 

.github/workflows/_test.yml

@@ -11,10 +11,6 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -25,14 +21,22 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: "make test #${{ inputs.python-version }}"
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+          - "3.12"
+    name: "make test #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core
@@ -65,22 +69,3 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
-          
-      - name: Get minimum versions
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
-        run: |
-          poetry run pip install packaging tomli
-          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-# Temporarily disabled until we can get the minimum versions working
-#      - name: Run unit tests with minimum dependency versions
-#        if: ${{ steps.min-version.outputs.min-versions != '' }}
-#        env:
-#          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-#        run: |
-#          poetry run pip install --force-reinstall $MIN_VERSIONS --editable .
-#          make tests
-#        working-directory: ${{ inputs.working-directory }}

.github/workflows/_test_doc_imports.yml

@@ -2,11 +2,6 @@ name: test_doc_imports
 
 on:
   workflow_call:
-    inputs:
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -14,14 +9,18 @@ env:
 jobs:
   build:
     runs-on: ubuntu-latest
-    name: "check doc imports #${{ inputs.python-version }}"
+    strategy:
+      matrix:
+        python-version:
+          - "3.12"
+    name: "check doc imports #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           cache-key: core
 

.github/workflows/check_diffs.yml

@@ -33,96 +33,91 @@ jobs:
         run: |
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
-      lint: ${{ steps.set-matrix.outputs.lint }}
-      test: ${{ steps.set-matrix.outputs.test }}
-      extended-tests: ${{ steps.set-matrix.outputs.extended-tests }}
-      compile-integration-tests: ${{ steps.set-matrix.outputs.compile-integration-tests }}
-      dependencies: ${{ steps.set-matrix.outputs.dependencies }}
-      test-doc-imports: ${{ steps.set-matrix.outputs.test-doc-imports }}
+      dirs-to-lint: ${{ steps.set-matrix.outputs.dirs-to-lint }}
+      dirs-to-test: ${{ steps.set-matrix.outputs.dirs-to-test }}
+      dirs-to-extended-test: ${{ steps.set-matrix.outputs.dirs-to-extended-test }}
+      docs-edited: ${{ steps.set-matrix.outputs.docs-edited }}
   lint:
-    name: cd ${{ matrix.job-configs.working-directory }}
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.lint != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-lint != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.lint) }}
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-lint) }}
     uses: ./.github/workflows/_lint.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
   test:
-    name: cd ${{ matrix.job-configs.working-directory }}
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.test != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test) }}
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
     uses: ./.github/workflows/_test.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
   test-doc-imports:
     needs: [ build ]
-    if: ${{ needs.build.outputs.test-doc-imports != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test-doc-imports) }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' || needs.build.outputs.docs-edited }}
     uses: ./.github/workflows/_test_doc_imports.yml
     secrets: inherit
-    with:
-      python-version: ${{ matrix.job-configs.python-version }}
 
   compile-integration-tests:
-    name: cd ${{ matrix.job-configs.working-directory }}
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.compile-integration-tests) }}
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
     uses: ./.github/workflows/_compile_integration_test.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
   dependencies:
-    name: cd ${{ matrix.job-configs.working-directory }}
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dependencies != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.dependencies) }}
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
     uses: ./.github/workflows/_dependencies.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
   extended-tests:
-    name: "cd ${{ matrix.job-configs.working-directory }} / make extended_tests #${{ matrix.job-configs.python-version }}"
+    name: "cd ${{ matrix.working-directory }} / make extended_tests #${{ matrix.python-version }}"
     needs: [ build ]
-    if: ${{ needs.build.outputs.extended-tests != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-extended-test != '[]' }}
     strategy:
       matrix:
         # note different variable for extended test dirs
-        job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-extended-test) }}
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+          - "3.12"
     runs-on: ubuntu-latest
     defaults:
       run:
-        working-directory: ${{ matrix.job-configs.working-directory }}
+        working-directory: ${{ matrix.working-directory }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.job-configs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.job-configs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ matrix.job-configs.working-directory }}
+          working-directory: ${{ matrix.working-directory }}
           cache-key: extended
 
       - name: Install dependencies

.github/workflows/check_new_docs.yml

@@ -26,11 +26,6 @@ jobs:
           python-version: '3.10'
       - id: files
         uses: Ana06/get-changed-files@v2.2.0
-        with:
-          filter: |
-            *.ipynb
-            *.md
-            *.mdx
       - name: Check new docs
         run: |
           python docs/scripts/check_templates.py ${{ steps.files.outputs.added }}

.github/workflows/scheduled_test.yml

@@ -27,6 +27,7 @@ jobs:
           - "libs/partners/groq"
           - "libs/partners/mistralai"
           - "libs/partners/together"
+          - "libs/partners/cohere"
           - "libs/partners/google-vertexai"
           - "libs/partners/google-genai"
           - "libs/partners/aws"
@@ -39,6 +40,10 @@ jobs:
         with:
           repository: langchain-ai/langchain-google
           path: langchain-google
+      - uses: actions/checkout@v4
+        with:
+          repository: langchain-ai/langchain-cohere
+          path: langchain-cohere
       - uses: actions/checkout@v4
         with:
           repository: langchain-ai/langchain-aws
@@ -48,9 +53,11 @@ jobs:
         run: |
           rm -rf \
             langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai
+            langchain/libs/partners/google-vertexai \
+            langchain/libs/partners/cohere
           mv langchain-google/libs/genai langchain/libs/partners/google-genai
           mv langchain-google/libs/vertexai langchain/libs/partners/google-vertexai
+          mv langchain-cohere/libs/cohere langchain/libs/partners/cohere
           mv langchain-aws/libs/aws langchain/libs/partners/aws
 
       - name: Set up Python ${{ matrix.python-version }}
@@ -109,6 +116,7 @@ jobs:
           rm -rf \
             langchain/libs/partners/google-genai \
             langchain/libs/partners/google-vertexai \
+            langchain/libs/partners/cohere \
             langchain/libs/partners/aws
 
       - name: Ensure the tests did not create any additional files

README.md

@@ -11,6 +11,7 @@
 [![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/issues)
 [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode&style=flat-square)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
 [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
+[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
 
 Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).

cookbook/Multi_modal_RAG.ipynb

@@ -64,7 +64,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -355,7 +355,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/Multi_modal_RAG_google.ipynb

@@ -37,7 +37,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -U --quiet langchain langchain-chroma langchain-community openai langchain-experimental\n",
+    "%pip install -U --quiet langchain langchain_community openai chromadb langchain-experimental\n",
     "%pip install --quiet \"unstructured[all-docs]\" pypdf pillow pydantic lxml pillow matplotlib chromadb tiktoken"
    ]
   },
@@ -344,8 +344,8 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import VertexAIEmbeddings\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "\n",
     "\n",

cookbook/RAPTOR.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pip install -U langchain umap-learn scikit-learn langchain_community tiktoken langchain-openai langchainhub langchain-chroma langchain-anthropic"
+    "pip install -U langchain umap-learn scikit-learn langchain_community tiktoken langchain-openai langchainhub chromadb langchain-anthropic"
    ]
   },
   {
@@ -645,7 +645,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "# Initialize all_texts with leaf_texts\n",
     "all_texts = leaf_texts.copy()\n",

cookbook/README.md

@@ -36,7 +36,6 @@ Notebook | Description
 [llm_symbolic_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_symbolic_math.ipynb) | Solve algebraic equations with the help of llms (language learning models) and sympy, a python library for symbolic mathematics.
 [meta_prompt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/meta_prompt.ipynb) | Implement the meta-prompt concept, which is a method for building self-improving agents that reflect on their own performance and modify their instructions accordingly.
 [multi_modal_output_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_output_agent.ipynb) | Generate multi-modal outputs, specifically images and text.
-[multi_modal_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_RAG_vdms.ipynb) | Perform retrieval-augmented generation (rag) on documents including text and images, using unstructured for parsing, Intel's Visual Data Management System (VDMS) as the vectorstore, and chains.
 [multi_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_player_dnd.ipynb) | Simulate multi-player dungeons & dragons games, with a custom function determining the speaking schedule of the agents.
 [multiagent_authoritarian.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_authoritarian.ipynb) | Implement a multi-agent simulation where a privileged agent controls the conversation, including deciding who speaks and when the conversation ends, in the context of a simulated news network.
 [multiagent_bidding.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_bidding.ipynb) | Implement a multi-agent simulation where agents bid to speak, with the highest bidder speaking next, demonstrated through a fictitious presidential debate example.
@@ -58,6 +57,4 @@ Notebook | Description
 [two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
 [two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialogue simulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
 [wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.
-[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
-[rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.
-[visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.
+[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.

cookbook/Semi_Structured_RAG.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma unstructured[all-docs] pydantic lxml langchainhub"
+    "! pip install langchain unstructured[all-docs] pydantic lxml langchainhub"
    ]
   },
   {
@@ -320,7 +320,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/Semi_structured_and_multi_modal_RAG.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma unstructured[all-docs] pydantic lxml"
+    "! pip install langchain unstructured[all-docs] pydantic lxml"
    ]
   },
   {
@@ -375,7 +375,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma unstructured[all-docs] pydantic lxml"
+    "! pip install langchain unstructured[all-docs] pydantic lxml"
    ]
   },
   {
@@ -378,8 +378,8 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import GPT4AllEmbeddings\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "\n",
     "# The vectorstore to use to index the child chunks\n",

cookbook/advanced_rag_eval.ipynb

@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai langchain_chroma langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -132,7 +132,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "baseline = Chroma.from_texts(\n",

cookbook/agent_vectorstore.ipynb

@@ -28,7 +28,7 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",

cookbook/airbyte_github.ipynb

@@ -14,7 +14,7 @@
     }
    ],
    "source": [
-    "%pip install -qU langchain-airbyte langchain_chroma"
+    "%pip install -qU langchain-airbyte"
    ]
   },
   {
@@ -123,7 +123,7 @@
    "outputs": [],
    "source": [
     "import tiktoken\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "enc = tiktoken.get_encoding(\"cl100k_base\")\n",

cookbook/docugami_xml_kg_rag.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain docugami==0.0.8 dgml-utils==0.3.0 pydantic langchainhub langchain-chroma hnswlib --upgrade --quiet"
+    "! pip install langchain docugami==0.0.8 dgml-utils==0.3.0 pydantic langchainhub chromadb hnswlib --upgrade --quiet"
    ]
   },
   {
@@ -547,7 +547,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores.chroma import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/fireworks_rag.ipynb

@@ -84,7 +84,7 @@
     }
    ],
    "source": [
-    "%pip install --quiet pypdf langchain-chroma tiktoken openai \n",
+    "%pip install --quiet pypdf chromadb tiktoken openai \n",
     "%pip uninstall -y langchain-fireworks\n",
     "%pip install --editable /mnt/disks/data/langchain/libs/partners/fireworks"
    ]
@@ -138,7 +138,7 @@
     "all_splits = text_splitter.split_documents(data)\n",
     "\n",
     "# Add to vectorDB\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_fireworks.embeddings import FireworksEmbeddings\n",
     "\n",
     "vectorstore = Chroma.from_documents(\n",

cookbook/hypothetical_document_embeddings.ipynb

@@ -170,7 +170,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "with open(\"../../state_of_the_union.txt\") as f:\n",

cookbook/langgraph_agentic_rag.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub langchain langgraph"
+    "! pip install langchain_community tiktoken langchain-openai langchainhub chromadb langchain langgraph"
    ]
   },
   {
@@ -30,8 +30,8 @@
    "outputs": [],
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "urls = [\n",

cookbook/langgraph_crag.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub langchain langgraph tavily-python"
+    "! pip install langchain_community tiktoken langchain-openai langchainhub chromadb langchain langgraph tavily-python"
    ]
   },
   {
@@ -77,8 +77,8 @@
    "outputs": [],
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "urls = [\n",
@@ -180,8 +180,8 @@
     "from langchain.output_parsers.openai_tools import PydanticToolsParser\n",
     "from langchain.prompts import PromptTemplate\n",
     "from langchain.schema import Document\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.tools.tavily_search import TavilySearchResults\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.messages import BaseMessage, FunctionMessage\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.pydantic_v1 import BaseModel, Field\n",

cookbook/langgraph_self_rag.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub langchain langgraph"
+    "! pip install langchain_community tiktoken langchain-openai langchainhub chromadb langchain langgraph"
    ]
   },
   {
@@ -86,8 +86,8 @@
    "outputs": [],
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "urls = [\n",
@@ -188,7 +188,7 @@
     "from langchain.output_parsers import PydanticOutputParser\n",
     "from langchain.output_parsers.openai_tools import PydanticToolsParser\n",
     "from langchain.prompts import PromptTemplate\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.messages import BaseMessage, FunctionMessage\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.pydantic_v1 import BaseModel, Field\n",

cookbook/multi_modal_RAG_chroma.ipynb

@@ -58,7 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -187,7 +187,7 @@
     "\n",
     "import chromadb\n",
     "import numpy as np\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_experimental.open_clip import OpenCLIPEmbeddings\n",
     "from PIL import Image as _PILImage\n",
     "\n",

cookbook/multi_modal_RAG_vdms.ipynb

@@ -18,7 +18,26 @@
     "* Use of multimodal embeddings (such as [CLIP](https://openai.com/research/clip)) to embed images and text\n",
     "* Use of [VDMS](https://github.com/IntelLabs/vdms/blob/master/README.md) as a vector store with support for multi-modal\n",
     "* Retrieval of both images and text using similarity search\n",
-    "* Passing raw images and text chunks to a multimodal LLM for answer synthesis "
+    "* Passing raw images and text chunks to a multimodal LLM for answer synthesis \n",
+    "\n",
+    "\n",
+    "## Packages\n",
+    "\n",
+    "For `unstructured`, you will also need `poppler` ([installation instructions](https://pdf2image.readthedocs.io/en/latest/installation.html)) and `tesseract` ([installation instructions](https://tesseract-ocr.github.io/tessdoc/Installation.html)) in your system."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "febbc459-ebba-4c1a-a52b-fed7731593f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# (newest versions required for multi-modal)\n",
+    "! pip install --quiet -U vdms langchain-experimental\n",
+    "\n",
+    "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
+    "! pip install --quiet pdf2image \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml open_clip_torch"
    ]
   },
   {
@@ -34,7 +53,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "id": "5f483872",
    "metadata": {},
    "outputs": [
@@ -42,7 +61,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "a1b9206b08ef626e15b356bf9e031171f7c7eb8f956a2733f196f0109246fe2b\n"
+      "docker: Error response from daemon: Conflict. The container name \"/vdms_rag_nb\" is already in use by container \"0c19ed281463ac10d7efe07eb815643e3e534ddf24844357039453ad2b0c27e8\". You have to remove (or rename) that container to be able to reuse that name.\n",
+      "See 'docker run --help'.\n"
      ]
     }
    ],
@@ -55,32 +75,9 @@
     "vdms_client = VDMS_Client(port=55559)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "2498a0a1",
-   "metadata": {},
-   "source": [
-    "## Packages\n",
-    "\n",
-    "For `unstructured`, you will also need `poppler` ([installation instructions](https://pdf2image.readthedocs.io/en/latest/installation.html)) and `tesseract` ([installation instructions](https://tesseract-ocr.github.io/tessdoc/Installation.html)) in your system."
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "id": "febbc459-ebba-4c1a-a52b-fed7731593f8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "! pip install --quiet -U vdms langchain-experimental\n",
-    "\n",
-    "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
-    "! pip install --quiet pdf2image \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml open_clip_torch"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "78ac6543",
    "metadata": {},
    "outputs": [],
@@ -98,9 +95,14 @@
     "\n",
     "### Partition PDF text and images\n",
     "  \n",
-    "Let's use famous photographs from the PDF version of Library of Congress Magazine in this example.\n",
+    "Let's look at an example pdf containing interesting images.\n",
     "\n",
-    "We can use `partition_pdf` from [Unstructured](https://unstructured-io.github.io/unstructured/introduction.html#key-concepts) to extract text and images."
+    "Famous photographs from library of congress:\n",
+    "\n",
+    "* https://www.loc.gov/lcm/pdf/LCM_2020_1112.pdf\n",
+    "* We'll use this as an example below\n",
+    "\n",
+    "We can use `partition_pdf` below from [Unstructured](https://unstructured-io.github.io/unstructured/introduction.html#key-concepts) to extract text and images."
    ]
   },
   {
@@ -114,8 +116,8 @@
     "\n",
     "import requests\n",
     "\n",
-    "# Folder to store pdf and extracted images\n",
-    "datapath = Path(\"./data/multimodal_files\").resolve()\n",
+    "# Folder with pdf and extracted images\n",
+    "datapath = Path(\"./multimodal_files\").resolve()\n",
     "datapath.mkdir(parents=True, exist_ok=True)\n",
     "\n",
     "pdf_url = \"https://www.loc.gov/lcm/pdf/LCM_2020_1112.pdf\"\n",
@@ -172,8 +174,14 @@
    "source": [
     "## Multi-modal embeddings with our document\n",
     "\n",
-    "In this section, we initialize the VDMS vector store for both text and images. For better performance, we use model `ViT-g-14` from [OpenClip multimodal embeddings](https://python.langchain.com/docs/integrations/text_embedding/open_clip).\n",
-    "The images are stored as base64 encoded strings with `vectorstore.add_images`.\n"
+    "We will use [OpenClip multimodal embeddings](https://python.langchain.com/docs/integrations/text_embedding/open_clip).\n",
+    "\n",
+    "We use a larger model for better performance (set in `langchain_experimental.open_clip.py`).\n",
+    "\n",
+    "```\n",
+    "model_name = \"ViT-g-14\"\n",
+    "checkpoint = \"laion2b_s34b_b88k\"\n",
+    "```"
    ]
   },
   {
@@ -192,7 +200,9 @@
     "vectorstore = VDMS(\n",
     "    client=vdms_client,\n",
     "    collection_name=\"mm_rag_clip_photos\",\n",
-    "    embedding=OpenCLIPEmbeddings(model_name=\"ViT-g-14\", checkpoint=\"laion2b_s34b_b88k\"),\n",
+    "    embedding_function=OpenCLIPEmbeddings(\n",
+    "        model_name=\"ViT-g-14\", checkpoint=\"laion2b_s34b_b88k\"\n",
+    "    ),\n",
     ")\n",
     "\n",
     "# Get image URIs with .jpg extension only\n",
@@ -223,7 +233,7 @@
    "source": [
     "## RAG\n",
     "\n",
-    "Here we define helper functions for image results."
+    "`vectorstore.add_images` will store / retrieve images as base64 encoded strings."
    ]
   },
   {
@@ -382,8 +392,7 @@
    "id": "1566096d-97c2-4ddc-ba4a-6ef88c525e4e",
    "metadata": {},
    "source": [
-    "## Test retrieval and run RAG\n",
-    "Now let's query for a `woman with children` and retrieve the top results."
+    "## Test retrieval and run RAG"
    ]
   },
   {
@@ -443,14 +452,6 @@
     "        print(doc.page_content)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "15e9b54d",
-   "metadata": {},
-   "source": [
-    "Now let's use the `multi_modal_rag_chain` to process the same query and display the response."
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 11,
@@ -461,10 +462,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " The image depicts a woman with several children. The woman appears to be of Cherokee heritage, as suggested by the text provided. The image is described as having been initially regretted by the subject, Florence Owens Thompson, due to her feeling that it did not accurately represent her leadership qualities.\n",
-      "The historical and cultural context of the image is tied to the Great Depression and the Dust Bowl, both of which affected the Cherokee people in Oklahoma. The photograph was taken during this period, and its subject, Florence Owens Thompson, was a leader within her community who worked tirelessly to help those affected by these crises.\n",
-      "The image's symbolism and meaning can be interpreted as a representation of resilience and strength in the face of adversity. The woman is depicted with multiple children, which could signify her role as a caregiver and protector during difficult times.\n",
-      "Connections between the image and the related text include Florence Owens Thompson's leadership qualities and her regretted feelings about the photograph. Additionally, the mention of Dorothea Lange, the photographer who took this photo, ties the image to its historical context and the broader narrative of the Great Depression and Dust Bowl in Oklahoma. \n"
+      "1. Detailed description of the visual elements in the image: The image features a woman with children, likely a mother and her family, standing together outside. They appear to be poor or struggling financially, as indicated by their attire and surroundings.\n",
+      "2. Historical and cultural context of the image: The photo was taken in 1936 during the Great Depression, when many families struggled to make ends meet. Dorothea Lange, a renowned American photographer, took this iconic photograph that became an emblem of poverty and hardship experienced by many Americans at that time.\n",
+      "3. Interpretation of the image's symbolism and meaning: The image conveys a sense of unity and resilience despite adversity. The woman and her children are standing together, displaying their strength as a family unit in the face of economic challenges. The photograph also serves as a reminder of the importance of empathy and support for those who are struggling.\n",
+      "4. Connections between the image and the related text: The text provided offers additional context about the woman in the photo, her background, and her feelings towards the photograph. It highlights the historical backdrop of the Great Depression and emphasizes the significance of this particular image as a representation of that time period.\n"
      ]
     }
    ],
@@ -491,6 +492,14 @@
    "source": [
     "! docker kill vdms_rag_nb"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8ba652da",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -509,7 +518,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,

cookbook/nomic_embedding_rag.ipynb

@@ -58,7 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain-nomic langchain-chroma langchain-community tiktoken langchain-openai langchain"
+    "! pip install -U langchain-nomic langchain_community tiktoken langchain-openai chromadb langchain"
    ]
   },
   {
@@ -167,7 +167,7 @@
    "source": [
     "import os\n",
     "\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.runnables import RunnableLambda, RunnablePassthrough\n",
     "from langchain_nomic import NomicEmbeddings\n",

cookbook/nomic_multimodal_rag.ipynb

@@ -56,7 +56,7 @@
    },
    "outputs": [],
    "source": [
-    "! pip install -U langchain-nomic langchain-chroma langchain-community tiktoken langchain-openai langchain # (newest versions required for multi-modal)"
+    "! pip install -U langchain-nomic langchain_community tiktoken langchain-openai chromadb langchain # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -194,7 +194,7 @@
     "\n",
     "import chromadb\n",
     "import numpy as np\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_nomic import NomicEmbeddings\n",
     "from PIL import Image as _PILImage\n",
     "\n",

cookbook/openai_functions_retrieval_qa.ipynb

@@ -20,8 +20,8 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter"
    ]

cookbook/optimization.ipynb

@@ -80,7 +80,7 @@
    "outputs": [],
    "source": [
     "from langchain.schema import Document\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "embeddings = OpenAIEmbeddings()"

cookbook/rag-locally-on-intel-cpu.ipynb

@@ -1,756 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "10f50955-be55-422f-8c62-3a32f8cf02ed",
-   "metadata": {},
-   "source": [
-    "# RAG application running locally on Intel Xeon CPU using langchain and open-source models"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "48113be6-44bb-4aac-aed3-76a1365b9561",
-   "metadata": {},
-   "source": [
-    "Author - Pratool Bharti (pratool.bharti@intel.com)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8b10b54b-1572-4ea1-9c1e-1d29fcc3dcd9",
-   "metadata": {},
-   "source": [
-    "In this cookbook, we use langchain tools and open source models to execute locally on CPU. This notebook has been validated to run on Intel Xeon 8480+ CPU. Here we implement a RAG pipeline for Llama2 model to answer questions about Intel Q1 2024 earnings release."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "acadbcec-3468-4926-8ce5-03b678041c0a",
-   "metadata": {},
-   "source": [
-    "**Create a conda or virtualenv environment with python >=3.10 and install following libraries**\n",
-    "<br>\n",
-    "\n",
-    "`pip install --upgrade langchain langchain-community langchainhub langchain-chroma bs4 gpt4all pypdf pysqlite3-binary` <br>\n",
-    "`pip install llama-cpp-python   --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu`"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "84c392c8-700a-42ec-8e94-806597f22e43",
-   "metadata": {},
-   "source": [
-    "**Load pysqlite3 in sys modules since ChromaDB requires sqlite3.**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "145cd491-b388-4ea7-bdc8-2f4995cac6fd",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "__import__(\"pysqlite3\")\n",
-    "import sys\n",
-    "\n",
-    "sys.modules[\"sqlite3\"] = sys.modules.pop(\"pysqlite3\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "14dde7e2-b236-49b9-b3a0-08c06410418c",
-   "metadata": {},
-   "source": [
-    "**Import essential components from langchain to load and split data**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "887643ba-249e-48d6-9aa7-d25087e8dfbf",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
-    "from langchain_community.document_loaders import PyPDFLoader"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "922c0eba-8736-4de5-bd2f-3d0f00b16e43",
-   "metadata": {},
-   "source": [
-    "**Download Intel Q1 2024 earnings release**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "2d6a2419-5338-4188-8615-a40a65ff8019",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "--2024-07-15 15:04:43--  https://d1io3yog0oux5.cloudfront.net/_11d435a500963f99155ee058df09f574/intel/db/887/9014/earnings_release/Q1+24_EarningsRelease_FINAL.pdf\n",
-      "Resolving proxy-dmz.intel.com (proxy-dmz.intel.com)... 10.7.211.16\n",
-      "Connecting to proxy-dmz.intel.com (proxy-dmz.intel.com)|10.7.211.16|:912... connected.\n",
-      "Proxy request sent, awaiting response... 200 OK\n",
-      "Length: 133510 (130K) [application/pdf]\n",
-      "Saving to: ‘intel_q1_2024_earnings.pdf’\n",
-      "\n",
-      "intel_q1_2024_earni 100%[===================>] 130.38K  --.-KB/s    in 0.005s  \n",
-      "\n",
-      "2024-07-15 15:04:44 (24.6 MB/s) - ‘intel_q1_2024_earnings.pdf’ saved [133510/133510]\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "!wget  'https://d1io3yog0oux5.cloudfront.net/_11d435a500963f99155ee058df09f574/intel/db/887/9014/earnings_release/Q1+24_EarningsRelease_FINAL.pdf' -O intel_q1_2024_earnings.pdf"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e3612627-e105-453d-8a50-bbd6e39dedb5",
-   "metadata": {},
-   "source": [
-    "**Loading earning release pdf document through PyPDFLoader**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "cac6278e-ebad-4224-a062-bf6daca24cb0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = PyPDFLoader(\"intel_q1_2024_earnings.pdf\")\n",
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a7dca43b-1c62-41df-90c7-6ed2904f823d",
-   "metadata": {},
-   "source": [
-    "**Splitting entire document in several chunks with each chunk size is 500 tokens**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "4486adbe-0d0e-4685-8c08-c1774ed6e993",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
-    "all_splits = text_splitter.split_documents(data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "af142346-e793-4a52-9a56-63e3be416b3d",
-   "metadata": {},
-   "source": [
-    "**Looking at the first split of the document**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "e4240fd1-898e-4bfc-a377-02c9bc25b56e",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Document(metadata={'source': 'intel_q1_2024_earnings.pdf', 'page': 0}, page_content='Intel Corporation\\n2200 Mission College Blvd.\\nSanta Clara, CA 95054-1549\\n                                                         \\nNews Release\\n Intel Reports First -Quarter 2024  Financial Results\\nNEWS SUMMARY\\n▪First-quarter revenue of $12.7 billion , up 9%  year over year (YoY).\\n▪First-quarter GAAP earnings (loss) per share (EPS) attributable to Intel was $(0.09) ; non-GAAP EPS \\nattributable to Intel was $0.18 .')"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "all_splits[0]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b88d2632-7c1b-49ef-a691-c0eb67d23e6a",
-   "metadata": {},
-   "source": [
-    "**One of the major step in RAG is to convert each split of document into embeddings and store in a vector database such that searching relevant documents are efficient.** <br>\n",
-    "**For that, importing Chroma vector database from langchain. Also, importing open source GPT4All for embedding models**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "9ff99dd7-9d47-4239-ba0a-d775792334ba",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_chroma import Chroma\n",
-    "from langchain_community.embeddings import GPT4AllEmbeddings"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b5d1f4dd-dd8d-4a20-95d1-2dbdd204375a",
-   "metadata": {},
-   "source": [
-    "**In next step, we will download one of the most popular embedding model \"all-MiniLM-L6-v2\". Find more details of the model at this link https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "05db3494-5d8e-4a13-9941-26330a86f5e5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model_name = \"all-MiniLM-L6-v2.gguf2.f16.gguf\"\n",
-    "gpt4all_kwargs = {\"allow_download\": \"True\"}\n",
-    "embeddings = GPT4AllEmbeddings(model_name=model_name, gpt4all_kwargs=gpt4all_kwargs)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4e53999e-1983-46ac-8039-2783e194c3ae",
-   "metadata": {},
-   "source": [
-    "**Store all the embeddings in the Chroma database**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "0922951a-9ddf-4761-973d-8e9a86f61284",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "vectorstore = Chroma.from_documents(documents=all_splits, embedding=embeddings)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "29f94fa0-6c75-4a65-a1a3-debc75422479",
-   "metadata": {},
-   "source": [
-    "**Now, let's find relevant splits from the documents related to the question**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "88c8152d-ec7a-4f0b-9d86-877789407537",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "4\n"
-     ]
-    }
-   ],
-   "source": [
-    "question = \"What is Intel CCG revenue in Q1 2024\"\n",
-    "docs = vectorstore.similarity_search(question)\n",
-    "print(len(docs))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "53330c6b-cb0f-43f9-b379-2e57ac1e5335",
-   "metadata": {},
-   "source": [
-    "**Look at the first retrieved document from the vector database**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "43a6d94f-b5c4-47b0-a353-2db4c3d24d9c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Document(metadata={'page': 1, 'source': 'intel_q1_2024_earnings.pdf'}, page_content='Client Computing Group (CCG) $7.5 billion up31%\\nData Center and AI (DCAI) $3.0 billion up5%\\nNetwork and Edge (NEX) $1.4 billion down 8%\\nTotal Intel Products revenue $11.9 billion up17%\\nIntel Foundry $4.4 billion down 10%\\nAll other:\\nAltera $342 million down 58%\\nMobileye $239 million down 48%\\nOther $194 million up17%\\nTotal all other revenue $775 million down 46%\\nIntersegment eliminations $(4.4) billion\\nTotal net revenue $12.7 billion up9%\\nIntel Products Highlights')"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "docs[0]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "64ba074f-4b36-442e-b7e2-b26d6e2815c3",
-   "metadata": {},
-   "source": [
-    "**Download Lllama-2 model from Huggingface and store locally** <br>\n",
-    "**You can download different quantization variant of Lllama-2 model from the link below. We are using Q8 version here (7.16GB).** <br>\n",
-    "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c8dd0811-6f43-4bc6-b854-2ab377639c9a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!huggingface-cli download TheBloke/Llama-2-7b-Chat-GGUF llama-2-7b-chat.Q8_0.gguf --local-dir . --local-dir-use-symlinks False"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3895b1f5-f51d-4539-abf0-af33d7ca48ea",
-   "metadata": {},
-   "source": [
-    "**Import langchain components required to load downloaded LLMs model**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "fb087088-aa62-44c0-8356-061e9b9f1186",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.callbacks.manager import CallbackManager\n",
-    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
-    "from langchain_community.llms import LlamaCpp"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5a8a111e-2614-4b70-b034-85cd3e7304cb",
-   "metadata": {},
-   "source": [
-    "**Loading the local Lllama-2 model using Llama-cpp library**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "fb917da2-c0d7-4995-b56d-26254276e0da",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from llama-2-7b-chat.Q8_0.gguf (version GGUF V2)\n",
-      "llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.\n",
-      "llama_model_loader: - kv   0:                       general.architecture str              = llama\n",
-      "llama_model_loader: - kv   1:                               general.name str              = LLaMA v2\n",
-      "llama_model_loader: - kv   2:                       llama.context_length u32              = 4096\n",
-      "llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096\n",
-      "llama_model_loader: - kv   4:                          llama.block_count u32              = 32\n",
-      "llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 11008\n",
-      "llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128\n",
-      "llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32\n",
-      "llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 32\n",
-      "llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000001\n",
-      "llama_model_loader: - kv  10:                          general.file_type u32              = 7\n",
-      "llama_model_loader: - kv  11:                       tokenizer.ggml.model str              = llama\n",
-      "llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr[str,32000]   = [\"<unk>\", \"<s>\", \"</s>\", \"<0x00>\", \"<...\n",
-      "llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...\n",
-      "llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...\n",
-      "llama_model_loader: - kv  15:                tokenizer.ggml.bos_token_id u32              = 1\n",
-      "llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32              = 2\n",
-      "llama_model_loader: - kv  17:            tokenizer.ggml.unknown_token_id u32              = 0\n",
-      "llama_model_loader: - kv  18:               general.quantization_version u32              = 2\n",
-      "llama_model_loader: - type  f32:   65 tensors\n",
-      "llama_model_loader: - type q8_0:  226 tensors\n",
-      "llm_load_vocab: special tokens cache size = 259\n",
-      "llm_load_vocab: token to piece cache size = 0.1684 MB\n",
-      "llm_load_print_meta: format           = GGUF V2\n",
-      "llm_load_print_meta: arch             = llama\n",
-      "llm_load_print_meta: vocab type       = SPM\n",
-      "llm_load_print_meta: n_vocab          = 32000\n",
-      "llm_load_print_meta: n_merges         = 0\n",
-      "llm_load_print_meta: vocab_only       = 0\n",
-      "llm_load_print_meta: n_ctx_train      = 4096\n",
-      "llm_load_print_meta: n_embd           = 4096\n",
-      "llm_load_print_meta: n_layer          = 32\n",
-      "llm_load_print_meta: n_head           = 32\n",
-      "llm_load_print_meta: n_head_kv        = 32\n",
-      "llm_load_print_meta: n_rot            = 128\n",
-      "llm_load_print_meta: n_swa            = 0\n",
-      "llm_load_print_meta: n_embd_head_k    = 128\n",
-      "llm_load_print_meta: n_embd_head_v    = 128\n",
-      "llm_load_print_meta: n_gqa            = 1\n",
-      "llm_load_print_meta: n_embd_k_gqa     = 4096\n",
-      "llm_load_print_meta: n_embd_v_gqa     = 4096\n",
-      "llm_load_print_meta: f_norm_eps       = 0.0e+00\n",
-      "llm_load_print_meta: f_norm_rms_eps   = 1.0e-06\n",
-      "llm_load_print_meta: f_clamp_kqv      = 0.0e+00\n",
-      "llm_load_print_meta: f_max_alibi_bias = 0.0e+00\n",
-      "llm_load_print_meta: f_logit_scale    = 0.0e+00\n",
-      "llm_load_print_meta: n_ff             = 11008\n",
-      "llm_load_print_meta: n_expert         = 0\n",
-      "llm_load_print_meta: n_expert_used    = 0\n",
-      "llm_load_print_meta: causal attn      = 1\n",
-      "llm_load_print_meta: pooling type     = 0\n",
-      "llm_load_print_meta: rope type        = 0\n",
-      "llm_load_print_meta: rope scaling     = linear\n",
-      "llm_load_print_meta: freq_base_train  = 10000.0\n",
-      "llm_load_print_meta: freq_scale_train = 1\n",
-      "llm_load_print_meta: n_ctx_orig_yarn  = 4096\n",
-      "llm_load_print_meta: rope_finetuned   = unknown\n",
-      "llm_load_print_meta: ssm_d_conv       = 0\n",
-      "llm_load_print_meta: ssm_d_inner      = 0\n",
-      "llm_load_print_meta: ssm_d_state      = 0\n",
-      "llm_load_print_meta: ssm_dt_rank      = 0\n",
-      "llm_load_print_meta: model type       = 7B\n",
-      "llm_load_print_meta: model ftype      = Q8_0\n",
-      "llm_load_print_meta: model params     = 6.74 B\n",
-      "llm_load_print_meta: model size       = 6.67 GiB (8.50 BPW) \n",
-      "llm_load_print_meta: general.name     = LLaMA v2\n",
-      "llm_load_print_meta: BOS token        = 1 '<s>'\n",
-      "llm_load_print_meta: EOS token        = 2 '</s>'\n",
-      "llm_load_print_meta: UNK token        = 0 '<unk>'\n",
-      "llm_load_print_meta: LF token         = 13 '<0x0A>'\n",
-      "llm_load_print_meta: max token length = 48\n",
-      "llm_load_tensors: ggml ctx size =    0.14 MiB\n",
-      "llm_load_tensors:        CPU buffer size =  6828.64 MiB\n",
-      "...................................................................................................\n",
-      "llama_new_context_with_model: n_ctx      = 2048\n",
-      "llama_new_context_with_model: n_batch    = 512\n",
-      "llama_new_context_with_model: n_ubatch   = 512\n",
-      "llama_new_context_with_model: flash_attn = 0\n",
-      "llama_new_context_with_model: freq_base  = 10000.0\n",
-      "llama_new_context_with_model: freq_scale = 1\n",
-      "llama_kv_cache_init:        CPU KV buffer size =  1024.00 MiB\n",
-      "llama_new_context_with_model: KV self size  = 1024.00 MiB, K (f16):  512.00 MiB, V (f16):  512.00 MiB\n",
-      "llama_new_context_with_model:        CPU  output buffer size =     0.12 MiB\n",
-      "llama_new_context_with_model:        CPU compute buffer size =   164.01 MiB\n",
-      "llama_new_context_with_model: graph nodes  = 1030\n",
-      "llama_new_context_with_model: graph splits = 1\n",
-      "AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 0 | \n",
-      "Model metadata: {'tokenizer.ggml.unknown_token_id': '0', 'tokenizer.ggml.eos_token_id': '2', 'general.architecture': 'llama', 'llama.context_length': '4096', 'general.name': 'LLaMA v2', 'llama.embedding_length': '4096', 'llama.feed_forward_length': '11008', 'llama.attention.layer_norm_rms_epsilon': '0.000001', 'llama.rope.dimension_count': '128', 'llama.attention.head_count': '32', 'tokenizer.ggml.bos_token_id': '1', 'llama.block_count': '32', 'llama.attention.head_count_kv': '32', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'llama', 'general.file_type': '7'}\n",
-      "Using fallback chat format: llama-2\n"
-     ]
-    }
-   ],
-   "source": [
-    "llm = LlamaCpp(\n",
-    "    model_path=\"llama-2-7b-chat.Q8_0.gguf\",\n",
-    "    n_gpu_layers=-1,\n",
-    "    n_batch=512,\n",
-    "    n_ctx=2048,\n",
-    "    f16_kv=True,  # MUST set to True, otherwise you will run into problem after a couple of calls\n",
-    "    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),\n",
-    "    verbose=True,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "43e06f56-ef97-451b-87d9-8465ea442aed",
-   "metadata": {},
-   "source": [
-    "**Now let's ask the same question to Llama model without showing them the earnings release.**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "1033dd82-5532-437d-a548-27695e109589",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "?\n",
-      "(NASDAQ:INTC)\n",
-      "Intel's CCG (Client Computing Group) revenue for Q1 2024 was $9.6 billion, a decrease of 35% from the previous quarter and a decrease of 42% from the same period last year."
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "llama_print_timings:        load time =     131.20 ms\n",
-      "llama_print_timings:      sample time =      16.05 ms /    68 runs   (    0.24 ms per token,  4236.76 tokens per second)\n",
-      "llama_print_timings: prompt eval time =     131.14 ms /    16 tokens (    8.20 ms per token,   122.01 tokens per second)\n",
-      "llama_print_timings:        eval time =    3225.00 ms /    67 runs   (   48.13 ms per token,    20.78 tokens per second)\n",
-      "llama_print_timings:       total time =    3466.40 ms /    83 tokens\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\"?\\n(NASDAQ:INTC)\\nIntel's CCG (Client Computing Group) revenue for Q1 2024 was $9.6 billion, a decrease of 35% from the previous quarter and a decrease of 42% from the same period last year.\""
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm.invoke(question)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "75f5cb10-746f-4e37-9386-b85a4d2b84ef",
-   "metadata": {},
-   "source": [
-    "**As you can see, model is giving wrong information. Correct asnwer is CCG revenue in Q1 2024 is $7.5B. Now let's apply RAG using the earning release document**"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0f4150ec-5692-4756-b11a-22feb7ab88ff",
-   "metadata": {},
-   "source": [
-    "**in RAG, we modify the input prompt by adding relevent documents with the question. Here, we use one of the popular RAG prompt**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "226c14b0-f43e-4a1f-a1e4-04731d467ec4",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['context', 'question'], template=\"You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\\nQuestion: {question} \\nContext: {context} \\nAnswer:\"))]"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import hub\n",
-    "\n",
-    "rag_prompt = hub.pull(\"rlm/rag-prompt\")\n",
-    "rag_prompt.messages"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "77deb6a0-0950-450a-916a-f2a029676c20",
-   "metadata": {},
-   "source": [
-    "**Appending all retreived documents in a single document**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "2dbc3327-6ef3-4c1f-8797-0c71964b0921",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def format_docs(docs):\n",
-    "    return \"\\n\\n\".join(doc.page_content for doc in docs)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2e2d9f18-49d0-43a3-bea8-78746ffa86b7",
-   "metadata": {},
-   "source": [
-    "**The last step is to create a chain using langchain tool that will create an e2e pipeline. It will take question and context as an input.**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "427379c2-51ff-4e0f-8278-a45221363299",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.runnables import RunnablePassthrough, RunnablePick\n",
-    "\n",
-    "# Chain\n",
-    "chain = (\n",
-    "    RunnablePassthrough.assign(context=RunnablePick(\"context\") | format_docs)\n",
-    "    | rag_prompt\n",
-    "    | llm\n",
-    "    | StrOutputParser()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "095d6280-c949-4d00-8e32-8895a82d245f",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Llama.generate: prefix-match hit\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      " Based on the provided context, Intel CCG revenue in Q1 2024 was $7.5 billion up 31%."
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "llama_print_timings:        load time =     131.20 ms\n",
-      "llama_print_timings:      sample time =       7.74 ms /    31 runs   (    0.25 ms per token,  4004.13 tokens per second)\n",
-      "llama_print_timings: prompt eval time =    2529.41 ms /   674 tokens (    3.75 ms per token,   266.46 tokens per second)\n",
-      "llama_print_timings:        eval time =    1542.94 ms /    30 runs   (   51.43 ms per token,    19.44 tokens per second)\n",
-      "llama_print_timings:       total time =    4123.68 ms /   704 tokens\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "' Based on the provided context, Intel CCG revenue in Q1 2024 was $7.5 billion up 31%.'"
-      ]
-     },
-     "execution_count": 21,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"context\": docs, \"question\": question})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "638364b2-6bd2-4471-9961-d3a1d1b9d4ee",
-   "metadata": {},
-   "source": [
-    "**Now we see the results are correct as it is mentioned in earnings release.** <br>\n",
-    "**To further automate, we will create a chain that will take input as question and retriever so that we don't need to retrieve documents seperately**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "4654e5b7-635f-4767-8b31-4c430164cdd5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "retriever = vectorstore.as_retriever()\n",
-    "qa_chain = (\n",
-    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
-    "    | rag_prompt\n",
-    "    | llm\n",
-    "    | StrOutputParser()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0979f393-fd0a-4e82-b844-68371c6ad68f",
-   "metadata": {},
-   "source": [
-    "**Now we only need to pass the question to the chain and it will fetch the contexts directly from the vector database to generate the answer**\n",
-    "<br>\n",
-    "**Let's try with another question**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "id": "3ea07b82-e6ec-4084-85f4-191373530172",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Llama.generate: prefix-match hit\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      " According to the provided context, Intel DCAI revenue in Q1 2024 was $3.0 billion up 5%."
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "llama_print_timings:        load time =     131.20 ms\n",
-      "llama_print_timings:      sample time =       6.28 ms /    31 runs   (    0.20 ms per token,  4937.88 tokens per second)\n",
-      "llama_print_timings: prompt eval time =    2681.93 ms /   730 tokens (    3.67 ms per token,   272.19 tokens per second)\n",
-      "llama_print_timings:        eval time =    1471.07 ms /    30 runs   (   49.04 ms per token,    20.39 tokens per second)\n",
-      "llama_print_timings:       total time =    4206.77 ms /   760 tokens\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "' According to the provided context, Intel DCAI revenue in Q1 2024 was $3.0 billion up 5%.'"
-      ]
-     },
-     "execution_count": 26,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "qa_chain.invoke(\"what is Intel DCAI revenue in Q1 2024?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "9407f2a0-4a35-4315-8e96-02fcb80f210c",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "rag-on-intel",
-   "language": "python",
-   "name": "rag-on-intel"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/rag_with_quantized_embeddings.ipynb

@@ -36,10 +36,10 @@
     "from bs4 import BeautifulSoup as Soup\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryByteStore, LocalFileStore\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders.recursive_url_loader import (\n",
     "    RecursiveUrlLoader,\n",
     ")\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "# For our example, we'll load docs from the web\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
@@ -370,14 +370,13 @@
    ],
    "source": [
     "import torch\n",
-    "from langchain_huggingface.llms import HuggingFacePipeline\n",
-    "from optimum.intel.ipex import IPEXModelForCausalLM\n",
-    "from transformers import AutoTokenizer, pipeline\n",
+    "from langchain.llms.huggingface_pipeline import HuggingFacePipeline\n",
+    "from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline\n",
     "\n",
     "model_id = \"Intel/neural-chat-7b-v3-3\"\n",
     "tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
-    "model = IPEXModelForCausalLM.from_pretrained(\n",
-    "    model_id, torch_dtype=torch.bfloat16, export=True\n",
+    "model = AutoModelForCausalLM.from_pretrained(\n",
+    "    model_id, device_map=\"auto\", torch_dtype=torch.bfloat16\n",
     ")\n",
     "\n",
     "pipe = pipeline(\"text-generation\", model=model, tokenizer=tokenizer, max_new_tokens=100)\n",
@@ -582,7 +581,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.14"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,

cookbook/sql_db_qa.mdx

@@ -740,7 +740,7 @@ Even this relatively large model will most likely fail to generate more complica
 
 
 ```bash
-poetry run pip install pyyaml langchain_chroma
+poetry run pip install pyyaml chromadb
 import yaml
 ```
 
@@ -994,7 +994,7 @@ from langchain.prompts import FewShotPromptTemplate, PromptTemplate
 from langchain.chains.sql_database.prompt import _sqlite_prompt, PROMPT_SUFFIX
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain.prompts.example_selector.semantic_similarity import SemanticSimilarityExampleSelector
-from langchain_chroma import Chroma
+from langchain_community.vectorstores import Chroma
 
 example_prompt = PromptTemplate(
     input_variables=["table_info", "input", "sql_cmd", "sql_result", "answer"],

cookbook/together_ai.ipynb

@@ -22,7 +22,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install --quiet pypdf tiktoken openai langchain-chroma langchain-together"
+    "! pip install --quiet pypdf chromadb tiktoken openai langchain-together"
    ]
   },
   {
@@ -45,8 +45,8 @@
     "all_splits = text_splitter.split_documents(data)\n",
     "\n",
     "# Add to vectorDB\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import OpenAIEmbeddings\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "\"\"\"\n",
     "from langchain_together.embeddings import TogetherEmbeddings\n",

docs/Makefile

@@ -13,7 +13,7 @@ OUTPUT_NEW_DOCS_DIR = $(OUTPUT_NEW_DIR)/docs
 
 PYTHON = .venv/bin/python
 
-PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm|couchbase" | tr '\n' ' ')
+PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm" | tr '\n' ' ')
 
 PORT ?= 3001
 
@@ -38,8 +38,6 @@ generate-files:
 
 	$(PYTHON) scripts/model_feat_table.py $(INTERMEDIATE_DIR)
 
-	$(PYTHON) scripts/tool_feat_table.py $(INTERMEDIATE_DIR)
-
 	$(PYTHON) scripts/document_loader_feat_table.py $(INTERMEDIATE_DIR)
 
 	$(PYTHON) scripts/copy_templates.py $(INTERMEDIATE_DIR)

docs/api_reference/conf.py

@@ -178,10 +178,3 @@ autosummary_generate = True
 
 html_copy_source = False
 html_show_sourcelink = False
-
-# Set canonical URL from the Read the Docs Domain
-html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "")
-
-# Tell Jinja2 templates the build is running on Read the Docs
-if os.environ.get("READTHEDOCS", "") == "True":
-    html_context["READTHEDOCS"] = True

docs/api_reference/create_api_rst.py

@@ -78,7 +78,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
             continue
 
         if inspect.isclass(type_):
-            # The type of the class is used to select a template
+            # The clasification of the class is used to select a template
             # for the object when rendering the documentation.
             # See `templates` directory for defined templates.
             # This is a hacky solution to distinguish between different

docs/docs/concepts.mdx

@@ -55,7 +55,6 @@ A developer platform that lets you debug, test, evaluate, and monitor LLM applic
     dark: useBaseUrl('/svg/langchain_stack_062024_dark.svg'),
   }}
   title="LangChain Framework Overview"
-  style={{ width: "100%" }}
 />
 
 ## LangChain Expression Language (LCEL)
@@ -86,13 +85,8 @@ Input and output schemas give every LCEL chain Pydantic and JSONSchema schemas i
 As your chains get more and more complex, it becomes increasingly important to understand what exactly is happening at every step.
 With LCEL, **all** steps are automatically logged to [LangSmith](https://docs.smith.langchain.com/) for maximum observability and debuggability.
 
-LCEL aims to provide consistency around behavior and customization over legacy subclassed chains such as `LLMChain` and
-`ConversationalRetrievalChain`. Many of these legacy chains hide important details like prompts, and as a wider variety
-of viable models emerge, customization has become more and more important.
-
-If you are currently using one of these legacy chains, please see [this guide for guidance on how to migrate](/docs/versions/migrating_chains).
-
-For guides on how to do specific tasks with LCEL, check out [the relevant how-to guides](/docs/how_to/#langchain-expression-language-lcel).
+[**Seamless LangServe deployment**](/docs/langserve)
+Any chain created with LCEL can be easily deployed using [LangServe](/docs/langserve).
 
 ### Runnable interface
 <span data-heading-keywords="invoke,runnable"></span>
@@ -165,7 +159,7 @@ Some important things to note:
 ChatModels also accept other parameters that are specific to that integration. To find all the parameters supported by a ChatModel head to the API reference for that model.
 
 :::important
-Some chat models have been fine-tuned for **tool calling** and provide a dedicated API for it.
+**Tool Calling** Some chat models have been fine-tuned for tool calling and provide a dedicated API for tool calling.
 Generally, such models are better at tool calling than non-fine-tuned models, and are recommended for use cases that require tool calling.
 Please see the [tool calling section](/docs/concepts/#functiontool-calling) for more information.
 :::
@@ -236,7 +230,7 @@ This is where information like log-probs and token usage may be stored.
 These represent a decision from an language model to call a tool. They are included as part of an `AIMessage` output.
 They can be accessed from there with the `.tool_calls` property.
 
-This property returns a list of `ToolCall`s. A `ToolCall` is a dictionary with the following arguments:
+This property returns a list of dictionaries. Each dictionary has the following keys:
 
 - `name`: The name of the tool that should be called.
 - `args`: The arguments to that tool.
@@ -246,19 +240,14 @@ This property returns a list of `ToolCall`s. A `ToolCall` is a dictionary with t
 
 This represents a system message, which tells the model how to behave. Not every model provider supports this.
 
-#### ToolMessage
-
-This represents the result of a tool call. In addition to `role` and `content`, this message has:
-
-- a `tool_call_id` field which conveys the id of the call to the tool that was called to produce this result.
-- an `artifact` field which can be used to pass along arbitrary artifacts of the tool execution which are useful to track but which should not be sent to the model.
-
-#### (Legacy) FunctionMessage
-
-This is a legacy message type, corresponding to OpenAI's legacy function-calling API. `ToolMessage` should be used instead to correspond to the updated tool-calling API.
+#### FunctionMessage
 
 This represents the result of a function call. In addition to `role` and `content`, this message has a `name` parameter which conveys the name of the function that was called to produce this result.
 
+#### ToolMessage
+
+This represents the result of a tool call. This is distinct from a FunctionMessage in order to match OpenAI's `function` and `tool` message types. In addition to `role` and `content`, this message has a `tool_call_id` parameter which conveys the id of the call to the tool that was called to produce this result.
+
 
 ### Prompt templates
 <span data-heading-keywords="prompt,prompttemplate,chatprompttemplate"></span>
@@ -498,113 +487,36 @@ Retrievers accept a string query as input and return a list of Document's as out
 
 For specifics on how to use retrievers, see the [relevant how-to guides here](/docs/how_to/#retrievers).
 
-### Key-value stores
-
-For some techniques, such as [indexing and retrieval with multiple vectors per document](/docs/how_to/multi_vector/), having some sort of key-value (KV) storage is helpful.
-
-LangChain includes a [`BaseStore`](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.BaseStore.html) interface,
-which allows for storage of arbitrary data. However, LangChain components that require KV-storage accept a
-more specific `BaseStore[str, bytes]` instance that stores binary data (referred to as a `ByteStore`), and internally take care of
-encoding and decoding data for their specific needs.
-
-This means that as a user, you only need to think about one type of store rather than different ones for different types of data.
-
-#### Interface
-
-All [`BaseStores`](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.BaseStore.html) support the following interface. Note that the interface allows
-for modifying **multiple** key-value pairs at once:
-
-- `mget(key: Sequence[str]) -> List[Optional[bytes]]`: get the contents of multiple keys, returning `None` if the key does not exist
-- `mset(key_value_pairs: Sequence[Tuple[str, bytes]]) -> None`: set the contents of multiple keys
-- `mdelete(key: Sequence[str]) -> None`: delete multiple keys
-- `yield_keys(prefix: Optional[str] = None) -> Iterator[str]`: yield all keys in the store, optionally filtering by a prefix
-
-For key-value store implementations, see [this section](/docs/integrations/stores/).
-
 ### Tools
 <span data-heading-keywords="tool,tools"></span>
 
-Tools are utilities designed to be called by a model: their inputs are designed to be generated by models, and their outputs are designed to be passed back to models.
-Tools are needed whenever you want a model to control parts of your code or call out to external APIs.
+Tools are interfaces that an agent, a chain, or a chat model / LLM can use to interact with the world.
 
-A tool consists of:
+A tool consists of the following components:
 
-1. The name of the tool.
-2. A description of what the tool does.
-3. A JSON schema defining the inputs to the tool.
-4. A function (and, optionally, an async variant of the function).
+1. The name of the tool
+2. A description of what the tool does
+3. JSON schema of what the inputs to the tool are
+4. The function to call
+5. Whether the result of a tool should be returned directly to the user (only relevant for agents)
 
-When a tool is bound to a model, the name, description and JSON schema are provided as context to the model.
-Given a list of tools and a set of instructions, a model can request to call one or more tools with specific inputs.
-Typical usage may look like the following:
+The name, description and JSON schema are provided as context
+to the LLM, allowing the LLM to determine how to use the tool
+appropriately.
 
-```python
-tools = [...] # Define a list of tools
-llm_with_tools = llm.bind_tools(tools)
-ai_msg = llm_with_tools.invoke("do xyz...")  # AIMessage(tool_calls=[ToolCall(...), ...], ...)
-```
+Given a list of available tools and a prompt, an LLM can request
+that one or more tools be invoked with appropriate arguments.
 
-The `AIMessage` returned from the model MAY have `tool_calls` associated with it.
-Read [this guide](/docs/concepts/#aimessage) for more information on what the response type may look like.
+Generally, when designing tools to be used by a chat model or LLM, it is important to keep in mind the following:
 
-Once the chosen tools are invoked, the results can be passed back to the model so that it can complete whatever task
-it's performing.
-There are generally two different ways to invoke the tool and pass back the response:
+- Chat models that have been fine-tuned for tool calling will be better at tool calling than non-fine-tuned models.
+- Non fine-tuned models may not be able to use tools at all, especially if the tools are complex or require multiple tool calls.
+- Models will perform better if the tools have well-chosen names, descriptions, and JSON schemas.
+- Simpler tools are generally easier for models to use than more complex tools.
 
-#### Invoke with just the arguments
-
-When you invoke a tool with just the arguments, you will get back the raw tool output (usually a string).
-This generally looks like:
-
-```python
-# You will want to previously check that the LLM returned tool calls
-tool_call = ai_msg.tool_calls[0]  # ToolCall(args={...}, id=..., ...)
-tool_output = tool.invoke(tool_call["args"])
-tool_message = ToolMessage(content=tool_output, tool_call_id=tool_call["id"], name=tool_call["name"])
-```
-
-Note that the `content` field will generally be passed back to the model.
-If you do not want the raw tool response to be passed to the model, but you still want to keep it around,
-you can transform the tool output but also pass it as an artifact (read more about [`ToolMessage.artifact` here](/docs/concepts/#toolmessage))
-
-```python
-... # Same code as above
-response_for_llm = transform(response)
-tool_message = ToolMessage(content=response_for_llm, tool_call_id=tool_call["id"], name=tool_call["name"], artifact=tool_output)
-```
-
-#### Invoke with `ToolCall`
-
-The other way to invoke a tool is to call it with the full `ToolCall` that was generated by the model.
-When you do this, the tool will return a ToolMessage.
-The benefits of this are that you don't have to write the logic yourself to transform the tool output into a ToolMessage.
-This generally looks like:
-
-```python
-tool_call = ai_msg.tool_calls[0]  # ToolCall(args={...}, id=..., ...)
-tool_message = tool.invoke(tool_call)
-# -> ToolMessage(content="tool result foobar...", tool_call_id=..., name="tool_name")
-```
-
-If you are invoking the tool this way and want to include an [artifact](/docs/concepts/#toolmessage) for the ToolMessage, you will need to have the tool return two things.
-Read more about [defining tools that return artifacts here](/docs/how_to/tool_artifacts/).
-
-#### Best practices
-
-When designing tools to be used by a model, it is important to keep in mind that:
-
-- Chat models that have explicit [tool-calling APIs](/docs/concepts/#functiontool-calling) will be better at tool calling than non-fine-tuned models.
-- Models will perform better if the tools have well-chosen names, descriptions, and JSON schemas. This another form of prompt engineering.
-- Simple, narrowly scoped tools are easier for models to use than complex tools.
-
-#### Related
-
-For specifics on how to use tools, see the [tools how-to guides](/docs/how_to/#tools).
-
-To use a pre-built tool, see the [tool integration docs](/docs/integrations/tools/).
+For specifics on how to use tools, see the [relevant how-to guides here](/docs/how_to/#tools).
 
 ### Toolkits
-<span data-heading-keywords="toolkit,toolkits"></span>
 
 Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.
 
@@ -849,61 +761,6 @@ units (like words or subwords) that carry meaning, rather than individual charac
 to learn and understand the structure of the language, including grammar and context.
 Furthermore, using tokens can also improve efficiency, since the model processes fewer units of text compared to character-level processing.
 
-### Function/tool calling
-
-:::info
-We use the term tool calling interchangeably with function calling. Although
-function calling is sometimes meant to refer to invocations of a single function,
-we treat all models as though they can return multiple tool or function calls in
-each message.
-:::
-
-Tool calling allows a [chat model](/docs/concepts/#chat-models) to respond to a given prompt by generating output that
-matches a user-defined schema.
-
-While the name implies that the model is performing
-some action, this is actually not the case! The model only generates the arguments to a tool, and actually running the tool (or not) is up to the user.
-One common example where you **wouldn't** want to call a function with the generated arguments
-is if you want to [extract structured output matching some schema](/docs/concepts/#structured-output)
-from unstructured text. You would give the model an "extraction" tool that takes
-parameters matching the desired schema, then treat the generated output as your final
-result.
-
-![Diagram of a tool call by a chat model](/img/tool_call.png)
-
-Tool calling is not universal, but is supported by many popular LLM providers, including [Anthropic](/docs/integrations/chat/anthropic/), 
-[Cohere](/docs/integrations/chat/cohere/), [Google](/docs/integrations/chat/google_vertex_ai_palm/), 
-[Mistral](/docs/integrations/chat/mistralai/), [OpenAI](/docs/integrations/chat/openai/), and even for locally-running models via [Ollama](/docs/integrations/chat/ollama/).
-
-LangChain provides a standardized interface for tool calling that is consistent across different models.
-
-The standard interface consists of:
-
-* `ChatModel.bind_tools()`: a method for specifying which tools are available for a model to call. This method accepts [LangChain tools](/docs/concepts/#tools) as well as [Pydantic](https://pydantic.dev/) objects.
-* `AIMessage.tool_calls`: an attribute on the `AIMessage` returned from the model for accessing the tool calls requested by the model.
-
-#### Tool usage
-
-After the model calls tools, you can use the tool by invoking it, then passing the arguments back to the model.
-LangChain provides the [`Tool`](/docs/concepts/#tools) abstraction to help you handle this.
-
-The general flow is this:
-
-1. Generate tool calls with a chat model in response to a query.
-2. Invoke the appropriate tools using the generated tool call as arguments.
-3. Format the result of the tool invocations as [`ToolMessages`](/docs/concepts/#toolmessage).
-4. Pass the entire list of messages back to the model so that it can generate a final answer (or call more tools).
-
-![Diagram of a complete tool calling flow](/img/tool_calling_flow.png)
-
-This is how tool calling [agents](/docs/concepts/#agents) perform tasks and answer queries.
-
-Check out some more focused guides below:
-
-- [How to use chat models to call tools](/docs/how_to/tool_calling/)
-- [How to pass tool outputs to chat models](/docs/how_to/tool_results_pass_to_model/)
-- [Building an agent with LangGraph](https://langchain-ai.github.io/langgraph/tutorials/introduction/)
-
 ### Structured output
 
 LLMs are capable of generating arbitrary text. This enables the model to respond appropriately to a wide
@@ -919,54 +776,14 @@ a few ways to get structured output from models in LangChain.
 
 #### `.with_structured_output()`
 
-For convenience, some LangChain chat models support a [`.with_structured_output()`](/docs/how_to/structured_output/#the-with_structured_output-method)
-method. This method only requires a schema as input, and returns a dict or Pydantic object.
+For convenience, some LangChain chat models support a `.with_structured_output()` method.
+This method only requires a schema as input, and returns a dict or Pydantic object.
 Generally, this method is only present on models that support one of the more advanced methods described below,
 and will use one of them under the hood. It takes care of importing a suitable output parser and
 formatting the schema in the right format for the model.
 
-Here's an example:
-
-```python
-from typing import Optional
-
-from langchain_core.pydantic_v1 import BaseModel, Field
-
-
-class Joke(BaseModel):
-    """Joke to tell user."""
-
-    setup: str = Field(description="The setup of the joke")
-    punchline: str = Field(description="The punchline to the joke")
-    rating: Optional[int] = Field(description="How funny the joke is, from 1 to 10")
-
-structured_llm = llm.with_structured_output(Joke)
-
-structured_llm.invoke("Tell me a joke about cats")
-```
-
-```
-Joke(setup='Why was the cat sitting on the computer?', punchline='To keep an eye on the mouse!', rating=None)
-
-```
-
-We recommend this method as a starting point when working with structured output:
-
-- It uses other model-specific features under the hood, without the need to import an output parser.
-- For the models that use tool calling, no special prompting is needed.
-- If multiple underlying techniques are supported, you can supply a `method` parameter to
-[toggle which one is used](/docs/how_to/structured_output/#advanced-specifying-the-method-for-structuring-outputs).
-
-You may want or need to use other techniques if:
-
-- The chat model you are using does not support tool calling.
-- You are working with very complex schemas and the model is having trouble generating outputs that conform.
-
 For more information, check out this [how-to guide](/docs/how_to/structured_output/#the-with_structured_output-method).
 
-You can also check out [this table](/docs/integrations/chat/#advanced-features) for a list of models that support
-`with_structured_output()`.
-
 #### Raw prompting
 
 The most intuitive way to get a model to structure output is to ask nicely.
@@ -989,8 +806,9 @@ for smooth parsing can be surprisingly difficult and model-specific.
 Some may be better at interpreting [JSON schema](https://json-schema.org/), others may be best with TypeScript definitions,
 and still others may prefer XML.
 
-While features offered by model providers may increase reliability, prompting techniques remain important for tuning your
-results no matter which method you choose.
+While we'll next go over some ways that you can take advantage of features offered by
+model providers to increase reliability, prompting techniques remain important for tuning your
+results no matter what method you choose.
 
 #### JSON mode
 <span data-heading-keywords="json mode"></span>
@@ -1000,11 +818,10 @@ Some models, such as [Mistral](/docs/integrations/chat/mistralai/), [OpenAI](/do
 support a feature called **JSON mode**, usually enabled via config.
 
 When enabled, JSON mode will constrain the model's output to always be some sort of valid JSON.
-Often they require some custom prompting, but it's usually much less burdensome than completely raw prompting and
-more along the lines of, `"you must always return JSON"`. The [output also generally easier to parse](/docs/how_to/output_parser_json/).
+Often they require some custom prompting, but it's usually much less burdensome and along the lines of,
+`"you must always return JSON"`, and the [output is easier to parse](/docs/how_to/output_parser_json/).
 
-It's also generally simpler to use directly and more commonly available than tool calling, and can give
-more flexibility around prompting and shaping results than tool calling.
+It's also generally simpler and more commonly available than tool calling.
 
 Here's an example:
 
@@ -1036,48 +853,48 @@ chain.invoke({ "question": "What is the powerhouse of the cell?" })
 
 For a full list of model providers that support JSON mode, see [this table](/docs/integrations/chat/#advanced-features).
 
-#### Tool calling {#structured-output-tool-calling}
+#### Function/tool calling
 
-For models that support it, [tool calling](/docs/concepts/#functiontool-calling) can be very convenient for structured output. It removes the
-guesswork around how best to prompt schemas in favor of a built-in model feature.
+:::info
+We use the term tool calling interchangeably with function calling. Although
+function calling is sometimes meant to refer to invocations of a single function,
+we treat all models as though they can return multiple tool or function calls in
+each message
+:::
 
-It works by first binding the desired schema either directly or via a [LangChain tool](/docs/concepts/#tools) to a
-[chat model](/docs/concepts/#chat-models) using the `.bind_tools()` method. The model will then generate an `AIMessage` containing
-a `tool_calls` field containing `args` that match the desired shape.
+Tool calling allows a model to respond to a given prompt by generating output that
+matches a user-defined schema. While the name implies that the model is performing
+some action, this is actually not the case! The model is coming up with the
+arguments to a tool, and actually running the tool (or not) is up to the user -
+for example, if you want to [extract output matching some schema](/docs/tutorials/extraction)
+from unstructured text, you could give the model an "extraction" tool that takes
+parameters matching the desired schema, then treat the generated output as your final
+result.
 
-There are several acceptable formats you can use to bind tools to a model in LangChain. Here's one example:
+For models that support it, tool calling can be very convenient. It removes the
+guesswork around how best to prompt schemas in favor of a built-in model feature. It can also
+more naturally support agentic flows, since you can just pass multiple tool schemas instead
+of fiddling with enums or unions.
 
-```python
-from langchain_core.pydantic_v1 import BaseModel, Field
-from langchain_openai import ChatOpenAI
+Many LLM providers, including [Anthropic](https://www.anthropic.com/),
+[Cohere](https://cohere.com/), [Google](https://cloud.google.com/vertex-ai),
+[Mistral](https://mistral.ai/), [OpenAI](https://openai.com/), and others,
+support variants of a tool calling feature. These features typically allow requests
+to the LLM to include available tools and their schemas, and for responses to include
+calls to these tools. For instance, given a search engine tool, an LLM might handle a
+query by first issuing a call to the search engine. The system calling the LLM can
+receive the tool call, execute it, and return the output to the LLM to inform its
+response. LangChain includes a suite of [built-in tools](/docs/integrations/tools/)
+and supports several methods for defining your own [custom tools](/docs/how_to/custom_tools).
 
-class ResponseFormatter(BaseModel):
-    """Always use this tool to structure your response to the user."""
+LangChain provides a standardized interface for tool calling that is consistent across different models.
 
-    answer: str = Field(description="The answer to the user's question")
-    followup_question: str = Field(description="A followup question the user could ask")
+The standard interface consists of:
 
-model = ChatOpenAI(
-    model="gpt-4o",
-    temperature=0,
-)
+* `ChatModel.bind_tools()`: a method for specifying which tools are available for a model to call. This method accepts [LangChain tools](/docs/concepts/#tools) here.
+* `AIMessage.tool_calls`: an attribute on the `AIMessage` returned from the model for accessing the tool calls requested by the model.
 
-model_with_tools = model.bind_tools([ResponseFormatter])
-
-ai_msg = model_with_tools.invoke("What is the powerhouse of the cell?")
-
-ai_msg.tool_calls[0]["args"]
-```
-
-```
-{'answer': "The powerhouse of the cell is the mitochondrion. It generates most of the cell's supply of adenosine triphosphate (ATP), which is used as a source of chemical energy.",
- 'followup_question': 'How do mitochondria generate ATP?'}
-```
-
-Tool calling is a generally consistent way to get a model to generate structured output, and is the default technique
-used for the [`.with_structured_output()`](/docs/concepts/#with_structured_output) method when a model supports it.
-
-The following how-to guides are good practical resources for using function/tool calling for structured output:
+The following how-to guides are good practical resources for using function/tool calling:
 
 - [How to return structured data from an LLM](/docs/how_to/structured_output/)
 - [How to use a model to call tools](/docs/how_to/tool_calling)
@@ -1158,7 +975,7 @@ See our [blog post overview](https://blog.langchain.dev/query-construction/) and
 
 #### Indexing
 
-Fourth, consider the design of your document index. A simple and powerful idea is to **decouple the documents that you index for retrieval from the documents that you pass to the LLM for generation.** Indexing frequently uses embedding models with vector stores, which [compress the semantic information in documents to fixed-size vectors](/docs/concepts/#embedding-models).
+Fouth, consider the design of your document index. A simple and powerful idea is to **decouple the documents that you index for retrieval from the documents that you pass to the LLM for generation.** Indexing frequently uses embedding models with vector stores, which [compress the semantic information in documents to fixed-size vectors](/docs/concepts/#embedding-models).
 
 Many RAG approaches focus on splitting documents into chunks and retrieving some number based on similarity to an input question for the LLM. But chunk size and chunk number can be difficult to set and affect results if they do not provide full context for the LLM to answer a question. Furthermore, LLMs are increasingly capable of processing millions of tokens. 
 
@@ -1266,7 +1083,7 @@ Table columns:
 | Token    | [many classes](/docs/how_to/split_by_token/)                                                                                                                                  | Tokens                                                                                                          |               | Splits text on tokens. There exist a few different ways to measure tokens.                                                                                                                                                                                                   |
 | Character  | [CharacterTextSplitter](/docs/how_to/character_text_splitter/)                                                                                                                | A user defined character                                                                                        |               | Splits text based on a user defined character. One of the simpler methods.                                                                                                                                                                                                   |
 | Semantic Chunker (Experimental) | [SemanticChunker](/docs/how_to/semantic-chunker/)                                                                                                                             | Sentences                                                                                                       |               | First splits on sentences. Then combines ones next to each other if they are semantically similar enough. Taken from [Greg Kamradt](https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb) |
-| Integration: AI21 Semantic | [AI21SemanticTextSplitter](/docs/integrations/document_transformers/ai21_semantic_text_splitter/)                                                                                                 |                  |    ✅           | Identifies distinct topics that form coherent pieces of text and splits along those.                                                                                                                                                                                         |
+| Integration: AI21 Semantic | [AI21SemanticTextSplitter](/docs/integrations/document_transformers/ai21_semantic_text_splitter/)                                                                                                                    |    ✅           | Identifies distinct topics that form coherent pieces of text and splits along those.                                                                                                                                                                                         |
 
 ### Evaluation
 <span data-heading-keywords="evaluation,evaluate"></span>

docs/docs/contributing/documentation/style_guide.mdx

@@ -33,8 +33,6 @@ Some examples include:
 
 - [Build a Simple LLM Application with LCEL](/docs/tutorials/llm_chain/)
 - [Build a Retrieval Augmented Generation (RAG) App](/docs/tutorials/rag/)
-
-A good structural rule of thumb is to follow the structure of this [example from Numpy](https://numpy.org/numpy-tutorials/content/tutorial-svd.html).
   
 Here are some high-level tips on writing a good tutorial:
 

docs/docs/contributing/integrations.mdx

@@ -11,7 +11,7 @@ There are a few different places you can contribute integrations for LangChain:
 - **Community**: For lighter-weight integrations that are primarily maintained by LangChain and the Open Source Community.
 - **Partner Packages**: For independent packages that are co-maintained by LangChain and a partner.
 
-For the most part, **new integrations should be added to the Community package**. Partner packages require more maintenance as separate packages, so please confirm with the LangChain team before creating a new partner package.
+For the most part, new integrations should be added to the Community package. Partner packages require more maintenance as separate packages, so please confirm with the LangChain team before creating a new partner package.
 
 In the following sections, we'll walk through how to contribute to each of these packages from a fake company, `Parrot Link AI`.
 
@@ -60,10 +60,6 @@ And add documentation to:
 
 ## Partner package in LangChain repo
 
-:::caution
-Before starting a **partner** package, please confirm your intent with the LangChain team. Partner packages require more maintenance as separate packages, so we will close PRs that add new partner packages without prior discussion. See the above section for how to add a community integration.
-:::
-
 Partner packages can be hosted in the `LangChain` monorepo or in an external repo.
 
 Partner package in the `LangChain` repo is placed in `libs/partners/{partner}` 

docs/docs/how_to/MultiQueryRetriever.ipynb

@@ -153,7 +153,7 @@
     "\n",
     "    def parse(self, text: str) -> List[str]:\n",
     "        lines = text.strip().split(\"\\n\")\n",
-    "        return list(filter(None, lines))  # Remove empty lines\n",
+    "        return lines\n",
     "\n",
     "\n",
     "output_parser = LineListOutputParser()\n",

docs/docs/how_to/callbacks_custom_events.ipynb

@@ -1,342 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to dispatch custom callback events\n",
-    "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "\n",
-    "- [Callbacks](/docs/concepts/#callbacks)\n",
-    "- [Custom callback handlers](/docs/how_to/custom_callbacks)\n",
-    "- [Astream Events API](/docs/concepts/#astream_events) the `astream_events` method will surface custom callback events.\n",
-    ":::\n",
-    "\n",
-    "In some situations, you may want to dipsatch a custom callback event from within a [Runnable](/docs/concepts/#runnable-interface) so it can be surfaced\n",
-    "in a custom callback handler or via the [Astream Events API](/docs/concepts/#astream_events).\n",
-    "\n",
-    "For example, if you have a long running tool with multiple steps, you can dispatch custom events between the steps and use these custom events to monitor progress.\n",
-    "You could also surface these custom events to an end user of your application to show them how the current task is progressing.\n",
-    "\n",
-    "To dispatch a custom event you need to decide on two attributes for the event: the `name` and the `data`.\n",
-    "\n",
-    "| Attribute | Type | Description                                                                                              |\n",
-    "|-----------|------|----------------------------------------------------------------------------------------------------------|\n",
-    "| name      | str  | A user defined name for the event.                                                                       |\n",
-    "| data      | Any  | The data associated with the event. This can be anything, though we suggest making it JSON serializable. |\n",
-    "\n",
-    "\n",
-    ":::{.callout-important}\n",
-    "* Dispatching custom callback events requires `langchain-core>=0.2.15`.\n",
-    "* Custom callback events can only be dispatched from within an existing `Runnable`.\n",
-    "* If using `astream_events`, you must use `version='v2'` to see custom events.\n",
-    "* Sending or rendering custom callbacks events in LangSmith is not yet supported.\n",
-    ":::\n",
-    "\n",
-    "\n",
-    ":::caution COMPATIBILITY\n",
-    "LangChain cannot automatically propagate configuration, including callbacks necessary for astream_events(), to child runnables if you are running async code in python<=3.10. This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
-    "\n",
-    "If you are running python<=3.10, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
-    "\n",
-    "If you are running python>=3.11, the `RunnableConfig` will automatically propagate to child runnables in async environment. However, it is still a good idea to propagate the `RunnableConfig` manually if your code may run in other Python versions.\n",
-    ":::"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# | output: false\n",
-    "# | echo: false\n",
-    "\n",
-    "%pip install -qU langchain-core"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Astream Events API\n",
-    "\n",
-    "The most useful way to consume custom events is via the [Astream Events API](/docs/concepts/#astream_events).\n",
-    "\n",
-    "We can use the `async` `adispatch_custom_event` API to emit custom events in an async setting. \n",
-    "\n",
-    "\n",
-    ":::{.callout-important}\n",
-    "\n",
-    "To see custom events via the astream events API, you need to use the newer `v2` API of `astream_events`.\n",
-    ":::"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'event': 'on_chain_start', 'data': {'input': 'hello world'}, 'name': 'foo', 'tags': [], 'run_id': 'f354ffe8-4c22-4881-890a-c1cad038a9a6', 'metadata': {}, 'parent_ids': []}\n",
-      "{'event': 'on_custom_event', 'run_id': 'f354ffe8-4c22-4881-890a-c1cad038a9a6', 'name': 'event1', 'tags': [], 'metadata': {}, 'data': {'x': 'hello world'}, 'parent_ids': []}\n",
-      "{'event': 'on_custom_event', 'run_id': 'f354ffe8-4c22-4881-890a-c1cad038a9a6', 'name': 'event2', 'tags': [], 'metadata': {}, 'data': 5, 'parent_ids': []}\n",
-      "{'event': 'on_chain_stream', 'run_id': 'f354ffe8-4c22-4881-890a-c1cad038a9a6', 'name': 'foo', 'tags': [], 'metadata': {}, 'data': {'chunk': 'hello world'}, 'parent_ids': []}\n",
-      "{'event': 'on_chain_end', 'data': {'output': 'hello world'}, 'run_id': 'f354ffe8-4c22-4881-890a-c1cad038a9a6', 'name': 'foo', 'tags': [], 'metadata': {}, 'parent_ids': []}\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_core.callbacks.manager import (\n",
-    "    adispatch_custom_event,\n",
-    ")\n",
-    "from langchain_core.runnables import RunnableLambda\n",
-    "from langchain_core.runnables.config import RunnableConfig\n",
-    "\n",
-    "\n",
-    "@RunnableLambda\n",
-    "async def foo(x: str) -> str:\n",
-    "    await adispatch_custom_event(\"event1\", {\"x\": x})\n",
-    "    await adispatch_custom_event(\"event2\", 5)\n",
-    "    return x\n",
-    "\n",
-    "\n",
-    "async for event in foo.astream_events(\"hello world\", version=\"v2\"):\n",
-    "    print(event)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In python <= 3.10, you must propagate the config manually!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'event': 'on_chain_start', 'data': {'input': 'hello world'}, 'name': 'bar', 'tags': [], 'run_id': 'c787b09d-698a-41b9-8290-92aaa656f3e7', 'metadata': {}, 'parent_ids': []}\n",
-      "{'event': 'on_custom_event', 'run_id': 'c787b09d-698a-41b9-8290-92aaa656f3e7', 'name': 'event1', 'tags': [], 'metadata': {}, 'data': {'x': 'hello world'}, 'parent_ids': []}\n",
-      "{'event': 'on_custom_event', 'run_id': 'c787b09d-698a-41b9-8290-92aaa656f3e7', 'name': 'event2', 'tags': [], 'metadata': {}, 'data': 5, 'parent_ids': []}\n",
-      "{'event': 'on_chain_stream', 'run_id': 'c787b09d-698a-41b9-8290-92aaa656f3e7', 'name': 'bar', 'tags': [], 'metadata': {}, 'data': {'chunk': 'hello world'}, 'parent_ids': []}\n",
-      "{'event': 'on_chain_end', 'data': {'output': 'hello world'}, 'run_id': 'c787b09d-698a-41b9-8290-92aaa656f3e7', 'name': 'bar', 'tags': [], 'metadata': {}, 'parent_ids': []}\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_core.callbacks.manager import (\n",
-    "    adispatch_custom_event,\n",
-    ")\n",
-    "from langchain_core.runnables import RunnableLambda\n",
-    "from langchain_core.runnables.config import RunnableConfig\n",
-    "\n",
-    "\n",
-    "@RunnableLambda\n",
-    "async def bar(x: str, config: RunnableConfig) -> str:\n",
-    "    \"\"\"An example that shows how to manually propagate config.\n",
-    "\n",
-    "    You must do this if you're running python<=3.10.\n",
-    "    \"\"\"\n",
-    "    await adispatch_custom_event(\"event1\", {\"x\": x}, config=config)\n",
-    "    await adispatch_custom_event(\"event2\", 5, config=config)\n",
-    "    return x\n",
-    "\n",
-    "\n",
-    "async for event in bar.astream_events(\"hello world\", version=\"v2\"):\n",
-    "    print(event)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Async Callback Handler\n",
-    "\n",
-    "You can also consume the dispatched event via an async callback handler."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Received event event1 with data: {'x': 1}, with tags: ['foo', 'bar'], with metadata: {} and run_id: a62b84be-7afd-4829-9947-7165df1f37d9\n",
-      "Received event event2 with data: 5, with tags: ['foo', 'bar'], with metadata: {} and run_id: a62b84be-7afd-4829-9947-7165df1f37d9\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "1"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from typing import Any, Dict, List, Optional\n",
-    "from uuid import UUID\n",
-    "\n",
-    "from langchain_core.callbacks import AsyncCallbackHandler\n",
-    "from langchain_core.callbacks.manager import (\n",
-    "    adispatch_custom_event,\n",
-    ")\n",
-    "from langchain_core.runnables import RunnableLambda\n",
-    "from langchain_core.runnables.config import RunnableConfig\n",
-    "\n",
-    "\n",
-    "class AsyncCustomCallbackHandler(AsyncCallbackHandler):\n",
-    "    async def on_custom_event(\n",
-    "        self,\n",
-    "        name: str,\n",
-    "        data: Any,\n",
-    "        *,\n",
-    "        run_id: UUID,\n",
-    "        tags: Optional[List[str]] = None,\n",
-    "        metadata: Optional[Dict[str, Any]] = None,\n",
-    "        **kwargs: Any,\n",
-    "    ) -> None:\n",
-    "        print(\n",
-    "            f\"Received event {name} with data: {data}, with tags: {tags}, with metadata: {metadata} and run_id: {run_id}\"\n",
-    "        )\n",
-    "\n",
-    "\n",
-    "@RunnableLambda\n",
-    "async def bar(x: str, config: RunnableConfig) -> str:\n",
-    "    \"\"\"An example that shows how to manually propagate config.\n",
-    "\n",
-    "    You must do this if you're running python<=3.10.\n",
-    "    \"\"\"\n",
-    "    await adispatch_custom_event(\"event1\", {\"x\": x}, config=config)\n",
-    "    await adispatch_custom_event(\"event2\", 5, config=config)\n",
-    "    return x\n",
-    "\n",
-    "\n",
-    "async_handler = AsyncCustomCallbackHandler()\n",
-    "await foo.ainvoke(1, {\"callbacks\": [async_handler], \"tags\": [\"foo\", \"bar\"]})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Sync Callback Handler\n",
-    "\n",
-    "Let's see how to emit custom events in a sync environment using `dispatch_custom_event`.\n",
-    "\n",
-    "You **must** call `dispatch_custom_event` from within an existing `Runnable`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Received event event1 with data: {'x': 1}, with tags: ['foo', 'bar'], with metadata: {} and run_id: 27b5ce33-dc26-4b34-92dd-08a89cb22268\n",
-      "Received event event2 with data: {'x': 1}, with tags: ['foo', 'bar'], with metadata: {} and run_id: 27b5ce33-dc26-4b34-92dd-08a89cb22268\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "1"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from typing import Any, Dict, List, Optional\n",
-    "from uuid import UUID\n",
-    "\n",
-    "from langchain_core.callbacks import BaseCallbackHandler\n",
-    "from langchain_core.callbacks.manager import (\n",
-    "    dispatch_custom_event,\n",
-    ")\n",
-    "from langchain_core.runnables import RunnableLambda\n",
-    "from langchain_core.runnables.config import RunnableConfig\n",
-    "\n",
-    "\n",
-    "class CustomHandler(BaseCallbackHandler):\n",
-    "    def on_custom_event(\n",
-    "        self,\n",
-    "        name: str,\n",
-    "        data: Any,\n",
-    "        *,\n",
-    "        run_id: UUID,\n",
-    "        tags: Optional[List[str]] = None,\n",
-    "        metadata: Optional[Dict[str, Any]] = None,\n",
-    "        **kwargs: Any,\n",
-    "    ) -> None:\n",
-    "        print(\n",
-    "            f\"Received event {name} with data: {data}, with tags: {tags}, with metadata: {metadata} and run_id: {run_id}\"\n",
-    "        )\n",
-    "\n",
-    "\n",
-    "@RunnableLambda\n",
-    "def foo(x: int, config: RunnableConfig) -> int:\n",
-    "    dispatch_custom_event(\"event1\", {\"x\": x})\n",
-    "    dispatch_custom_event(\"event2\", {\"x\": x})\n",
-    "    return x\n",
-    "\n",
-    "\n",
-    "handler = CustomHandler()\n",
-    "foo.invoke(1, {\"callbacks\": [handler], \"tags\": [\"foo\", \"bar\"]})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You've seen how to emit custom events, you can check out the more in depth guide for [astream events](/docs/how_to/streaming/#using-stream-events) which is the easiest way to leverage custom events."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

docs/docs/how_to/chat_model_rate_limiting.ipynb

@@ -1,146 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "dcf87b32",
-   "metadata": {},
-   "source": [
-    "# How to handle rate limits\n",
-    "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [Chat models](/docs/concepts/#chat-models)\n",
-    "- [LLMs](/docs/concepts/#llms)\n",
-    ":::\n",
-    "\n",
-    "\n",
-    "You may find yourself in a situation where you are getting rate limited by the model provider API because you're making too many requests.\n",
-    "\n",
-    "For example, this might happen if you are running many parallel queries to benchmark the chat model on a test dataset.\n",
-    "\n",
-    "If you are facing such a situation, you can use a rate limiter to help match the rate at which you're making request to the rate allowed\n",
-    "by the API.\n",
-    "\n",
-    ":::info Requires ``langchain-core >= 0.2.24``\n",
-    "\n",
-    "This functionality was added in ``langchain-core == 0.2.24``. Please make sure your package is up to date.\n",
-    ":::"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cbc3c873-6109-4e03-b775-b73c1003faea",
-   "metadata": {},
-   "source": [
-    "## Initialize a rate limiter\n",
-    "\n",
-    "Langchain comes with a built-in in memory rate limiter. This rate limiter is thread safe and can be shared by multiple threads in the same process.\n",
-    "\n",
-    "The provided rate limiter can only limit the number of requests per unit time. It will not help if you need to also limited based on the size\n",
-    "of the requests."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "aa9c3c8c-0464-4190-a8c5-d69d173505a6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.rate_limiters import InMemoryRateLimiter\n",
-    "\n",
-    "rate_limiter = InMemoryRateLimiter(\n",
-    "    requests_per_second=0.1,  # <-- Super slow! We can only make a request once every 10 seconds!!\n",
-    "    check_every_n_seconds=0.1,  # Wake up every 100 ms to check whether allowed to make a request,\n",
-    "    max_bucket_size=10,  # Controls the maximum burst size.\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8e058bde-9413-4b08-8cc6-0c9cb638f19f",
-   "metadata": {},
-   "source": [
-    "## Choose a model\n",
-    "\n",
-    "Choose any model and pass to it the rate_limiter via the `rate_limiter` attribute."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "0f880a3a-c047-4e94-a323-fff2a4c0e96d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "import time\n",
-    "from getpass import getpass\n",
-    "\n",
-    "if \"ANTHROPIC_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"ANTHROPIC_API_KEY\"] = getpass()\n",
-    "\n",
-    "\n",
-    "from langchain_anthropic import ChatAnthropic\n",
-    "\n",
-    "model = ChatAnthropic(model_name=\"claude-3-opus-20240229\", rate_limiter=rate_limiter)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "80c9ab3a-299a-460f-985c-90280a046f52",
-   "metadata": {},
-   "source": [
-    "Let's confirm that the rate limiter works. We should only be able to invoke the model once per 10 seconds."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "d074265c-9f32-4c5f-b914-944148993c4d",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "11.599073648452759\n",
-      "10.7502121925354\n",
-      "10.244257926940918\n",
-      "8.83088755607605\n",
-      "11.645203590393066\n"
-     ]
-    }
-   ],
-   "source": [
-    "for _ in range(5):\n",
-    "    tic = time.time()\n",
-    "    model.invoke(\"hello\")\n",
-    "    toc = time.time()\n",
-    "    print(toc - tic)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/how_to/chat_models_universal_init.ipynb

@@ -15,12 +15,6 @@
     "\n",
     "Make sure you have the integration packages installed for any model providers you want to support. E.g. you should have `langchain-openai` installed to init an OpenAI model.\n",
     "\n",
-    ":::\n",
-    "\n",
-    ":::info Requires ``langchain >= 0.2.8``\n",
-    "\n",
-    "This functionality was added in ``langchain-core == 0.2.8``. Please make sure your package is up to date.\n",
-    "\n",
     ":::"
    ]
   },
@@ -31,7 +25,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -qU langchain>=0.2.8 langchain-openai langchain-anthropic langchain-google-vertexai"
+    "%pip install -qU langchain langchain-openai langchain-anthropic langchain-google-vertexai"
    ]
   },
   {
@@ -82,6 +76,32 @@
     "print(\"Gemini 1.5: \" + gemini_15.invoke(\"what's your name\").content + \"\\n\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "fff9a4c8-b6ee-4a1a-8d3d-0ecaa312d4ed",
+   "metadata": {},
+   "source": [
+    "## Simple config example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "75c25d39-bf47-4b51-a6c6-64d9c572bfd6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "user_config = {\n",
+    "    \"model\": \"...user-specified...\",\n",
+    "    \"model_provider\": \"...user-specified...\",\n",
+    "    \"temperature\": 0,\n",
+    "    \"max_tokens\": 1000,\n",
+    "}\n",
+    "\n",
+    "llm = init_chat_model(**user_config)\n",
+    "llm.invoke(\"what's your name\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "f811f219-5e78-4b62-b495-915d52a22532",
@@ -104,216 +124,13 @@
     "gemini_15 = init_chat_model(\"gemini-1.5-pro\", temperature=0)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "476a44db-c50d-4846-951d-0f1c9ba8bbaa",
-   "metadata": {},
-   "source": [
-    "## Creating a configurable model\n",
-    "\n",
-    "You can also create a runtime-configurable model by specifying `configurable_fields`. If you don't specify a `model` value, then \"model\" and \"model_provider\" be configurable by default."
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "6c037f27-12d7-4e83-811e-4245c0e3ba58",
+   "execution_count": null,
+   "id": "da07b5c0-d2e6-42e4-bfcd-2efcfaae6221",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"I'm an AI language model created by OpenAI, and I don't have a personal name. You can call me Assistant or any other name you prefer! How can I assist you today?\", response_metadata={'token_usage': {'completion_tokens': 37, 'prompt_tokens': 11, 'total_tokens': 48}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_d576307f90', 'finish_reason': 'stop', 'logprobs': None}, id='run-5428ab5c-b5c0-46de-9946-5d4ca40dbdc8-0', usage_metadata={'input_tokens': 11, 'output_tokens': 37, 'total_tokens': 48})"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "configurable_model = init_chat_model(temperature=0)\n",
-    "\n",
-    "configurable_model.invoke(\n",
-    "    \"what's your name\", config={\"configurable\": {\"model\": \"gpt-4o\"}}\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "321e3036-abd2-4e1f-bcc6-606efd036954",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"My name is Claude. It's nice to meet you!\", response_metadata={'id': 'msg_012XvotUJ3kGLXJUWKBVxJUi', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 11, 'output_tokens': 15}}, id='run-1ad1eefe-f1c6-4244-8bc6-90e2cb7ee554-0', usage_metadata={'input_tokens': 11, 'output_tokens': 15, 'total_tokens': 26})"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "configurable_model.invoke(\n",
-    "    \"what's your name\", config={\"configurable\": {\"model\": \"claude-3-5-sonnet-20240620\"}}\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7f3b3d4a-4066-45e4-8297-ea81ac8e70b7",
-   "metadata": {},
-   "source": [
-    "### Configurable model with default values\n",
-    "\n",
-    "We can create a configurable model with default model values, specify which parameters are configurable, and add prefixes to configurable params:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "814a2289-d0db-401e-b555-d5116112b413",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"I'm an AI language model created by OpenAI, and I don't have a personal name. You can call me Assistant or any other name you prefer! How can I assist you today?\", response_metadata={'token_usage': {'completion_tokens': 37, 'prompt_tokens': 11, 'total_tokens': 48}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_ce0793330f', 'finish_reason': 'stop', 'logprobs': None}, id='run-3923e328-7715-4cd6-b215-98e4b6bf7c9d-0', usage_metadata={'input_tokens': 11, 'output_tokens': 37, 'total_tokens': 48})"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "first_llm = init_chat_model(\n",
-    "    model=\"gpt-4o\",\n",
-    "    temperature=0,\n",
-    "    configurable_fields=(\"model\", \"model_provider\", \"temperature\", \"max_tokens\"),\n",
-    "    config_prefix=\"first\",  # useful when you have a chain with multiple models\n",
-    ")\n",
-    "\n",
-    "first_llm.invoke(\"what's your name\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "6c8755ba-c001-4f5a-a497-be3f1db83244",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"My name is Claude. It's nice to meet you!\", response_metadata={'id': 'msg_01RyYR64DoMPNCfHeNnroMXm', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 11, 'output_tokens': 15}}, id='run-22446159-3723-43e6-88df-b84797e7751d-0', usage_metadata={'input_tokens': 11, 'output_tokens': 15, 'total_tokens': 26})"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "first_llm.invoke(\n",
-    "    \"what's your name\",\n",
-    "    config={\n",
-    "        \"configurable\": {\n",
-    "            \"first_model\": \"claude-3-5-sonnet-20240620\",\n",
-    "            \"first_temperature\": 0.5,\n",
-    "            \"first_max_tokens\": 100,\n",
-    "        }\n",
-    "    },\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0072b1a3-7e44-4b4e-8b07-efe1ba91a689",
-   "metadata": {},
-   "source": [
-    "### Using a configurable model declaratively\n",
-    "\n",
-    "We can call declarative operations like `bind_tools`, `with_structured_output`, `with_configurable`, etc. on a configurable model and chain a configurable model in the same way that we would a regularly instantiated chat model object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "067dabee-1050-4110-ae24-c48eba01e13b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[{'name': 'GetPopulation',\n",
-       "  'args': {'location': 'Los Angeles, CA'},\n",
-       "  'id': 'call_sYT3PFMufHGWJD32Hi2CTNUP'},\n",
-       " {'name': 'GetPopulation',\n",
-       "  'args': {'location': 'New York, NY'},\n",
-       "  'id': 'call_j1qjhxRnD3ffQmRyqjlI1Lnk'}]"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "\n",
-    "class GetWeather(BaseModel):\n",
-    "    \"\"\"Get the current weather in a given location\"\"\"\n",
-    "\n",
-    "    location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
-    "\n",
-    "\n",
-    "class GetPopulation(BaseModel):\n",
-    "    \"\"\"Get the current population in a given location\"\"\"\n",
-    "\n",
-    "    location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
-    "\n",
-    "\n",
-    "llm = init_chat_model(temperature=0)\n",
-    "llm_with_tools = llm.bind_tools([GetWeather, GetPopulation])\n",
-    "\n",
-    "llm_with_tools.invoke(\n",
-    "    \"what's bigger in 2024 LA or NYC\", config={\"configurable\": {\"model\": \"gpt-4o\"}}\n",
-    ").tool_calls"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "e57dfe9f-cd24-4e37-9ce9-ccf8daf78f89",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[{'name': 'GetPopulation',\n",
-       "  'args': {'location': 'Los Angeles, CA'},\n",
-       "  'id': 'toolu_01CxEHxKtVbLBrvzFS7GQ5xR'},\n",
-       " {'name': 'GetPopulation',\n",
-       "  'args': {'location': 'New York City, NY'},\n",
-       "  'id': 'toolu_013A79qt5toWSsKunFBDZd5S'}]"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_with_tools.invoke(\n",
-    "    \"what's bigger in 2024 LA or NYC\",\n",
-    "    config={\"configurable\": {\"model\": \"claude-3-5-sonnet-20240620\"}},\n",
-    ").tool_calls"
-   ]
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -332,7 +149,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/how_to/chat_token_usage_tracking.ipynb

@@ -16,7 +16,7 @@
     "\n",
     "Tracking token usage to calculate cost is an important part of putting your app in production. This guide goes over how to obtain this information from your LangChain model calls.\n",
     "\n",
-    "This guide requires `langchain-openai >= 0.1.9`."
+    "This guide requires `langchain-openai >= 0.1.8`."
    ]
   },
   {
@@ -153,7 +153,7 @@
     "\n",
     "#### OpenAI\n",
     "\n",
-    "For example, OpenAI will return a message [chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html) at the end of a stream with token usage information. This behavior is supported by `langchain-openai >= 0.1.9` and can be enabled by setting `stream_usage=True`. This attribute can also be set when `ChatOpenAI` is instantiated.\n",
+    "For example, OpenAI will return a message [chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html) at the end of a stream with token usage information. This behavior is supported by `langchain-openai >= 0.1.8` and can be enabled by setting `stream_options={\"include_usage\": True}`.\n",
     "\n",
     "```{=mdx}\n",
     ":::note\n",
@@ -172,18 +172,18 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "content='' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content='Hello' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content='!' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' How' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' can' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' I' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' assist' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' you' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' today' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content='?' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content='' response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-3.5-turbo-0125'} id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content='' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}\n"
+      "content='' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content='Hello' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content='!' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' How' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' can' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' I' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' assist' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' you' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' today' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content='?' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content='' response_metadata={'finish_reason': 'stop'} id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content='' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}\n"
      ]
     }
    ],
@@ -191,7 +191,7 @@
     "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
     "\n",
     "aggregate = None\n",
-    "for chunk in llm.stream(\"hello\", stream_usage=True):\n",
+    "for chunk in llm.stream(\"hello\", stream_options={\"include_usage\": True}):\n",
     "    print(chunk)\n",
     "    aggregate = chunk if aggregate is None else aggregate + chunk"
    ]
@@ -229,7 +229,7 @@
    "id": "7dba63e8-0ed7-4533-8f0f-78e19c38a25c",
    "metadata": {},
    "source": [
-    "To disable streaming token counts for OpenAI, set `stream_usage` to False, or omit it from the parameters:"
+    "To disable streaming token counts for OpenAI, set `\"include_usage\"` to False in `stream_options`, or omit it from the parameters:"
    ]
   },
   {
@@ -242,17 +242,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "content='' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content='Hello' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content='!' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' How' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' can' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' I' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' assist' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' you' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' today' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content='?' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content='' response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-3.5-turbo-0125'} id='run-8e758550-94b0-4cca-a298-57482793c25d'\n"
+      "content='' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content='Hello' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content='!' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' How' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' can' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' I' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' assist' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' you' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' today' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content='?' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content='' response_metadata={'finish_reason': 'stop'} id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n"
      ]
     }
    ],
@@ -267,7 +267,7 @@
    "id": "6a5d9617-be3a-419a-9276-de9c29fa50ae",
    "metadata": {},
    "source": [
-    "You can also enable streaming token usage by setting `stream_usage` when instantiating the chat model. This can be useful when incorporating chat models into LangChain [chains](/docs/concepts#langchain-expression-language-lcel): usage metadata can be monitored when [streaming intermediate steps](/docs/how_to/streaming#using-stream-events) or using tracing software such as [LangSmith](https://docs.smith.langchain.com/).\n",
+    "You can also enable streaming token usage by setting `model_kwargs` when instantiating the chat model. This can be useful when incorporating chat models into LangChain [chains](/docs/concepts#langchain-expression-language-lcel): usage metadata can be monitored when [streaming intermediate steps](/docs/how_to/streaming#using-stream-events) or using tracing software such as [LangSmith](https://docs.smith.langchain.com/).\n",
     "\n",
     "See the below example, where we return output structured to a desired schema, but can still observe token usage streamed from intermediate steps."
    ]
@@ -275,7 +275,7 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "0b1523d8-127e-4314-82fa-bd97aca37f9a",
+   "id": "57dec1fb-bd9c-4c98-8798-8fbbe67f6b2c",
    "metadata": {},
    "outputs": [
     {
@@ -301,7 +301,7 @@
     "\n",
     "llm = ChatOpenAI(\n",
     "    model=\"gpt-3.5-turbo-0125\",\n",
-    "    stream_usage=True,\n",
+    "    model_kwargs={\"stream_options\": {\"include_usage\": True}},\n",
     ")\n",
     "# Under the hood, .with_structured_output binds tools to the\n",
     "# chat model and appends a parser.\n",
@@ -341,7 +341,7 @@
   {
    "cell_type": "code",
    "execution_count": 9,
-   "id": "b04a4486-72fd-48ce-8f9e-5d281b441195",
+   "id": "31667d54",
    "metadata": {},
    "outputs": [
     {
@@ -361,11 +361,7 @@
     "\n",
     "from langchain_community.callbacks.manager import get_openai_callback\n",
     "\n",
-    "llm = ChatOpenAI(\n",
-    "    model=\"gpt-3.5-turbo-0125\",\n",
-    "    temperature=0,\n",
-    "    stream_usage=True,\n",
-    ")\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
     "\n",
     "with get_openai_callback() as cb:\n",
     "    result = llm.invoke(\"Tell me a joke\")\n",
@@ -383,14 +379,14 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "05f22a1d-b021-490f-8840-f628a07459f2",
+   "id": "e09420f4",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "54\n"
+      "55\n"
      ]
     }
    ],
@@ -401,29 +397,37 @@
     "    print(cb.total_tokens)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "9ac51188-c8f4-4230-90fd-3cd78cdd955d",
+   "metadata": {},
+   "source": [
+    "```{=mdx}\n",
+    ":::note\n",
+    "Cost information is currently not available in streaming mode. This is because model names are currently not propagated through chunks in streaming mode, and the model name is used to look up the correct pricing. Token counts however are available:\n",
+    ":::\n",
+    "```"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 11,
-   "id": "c00c9158-7bb4-4279-88e6-ea70f46e6ac2",
+   "id": "b241069a-265d-4497-af34-b0a5f95ae67f",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Tokens Used: 27\n",
-      "\tPrompt Tokens: 11\n",
-      "\tCompletion Tokens: 16\n",
-      "Successful Requests: 1\n",
-      "Total Cost (USD): $2.95e-05\n"
+      "28\n"
      ]
     }
    ],
    "source": [
     "with get_openai_callback() as cb:\n",
-    "    for chunk in llm.stream(\"Tell me a joke\"):\n",
+    "    for chunk in llm.stream(\"Tell me a joke\", stream_options={\"include_usage\": True}):\n",
     "        pass\n",
-    "    print(cb)"
+    "    print(cb.total_tokens)"
    ]
   },
   {
@@ -453,7 +457,21 @@
     ")\n",
     "tools = load_tools([\"wikipedia\"])\n",
     "agent = create_tool_calling_agent(llm, tools, prompt)\n",
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
+    "agent_executor = AgentExecutor(\n",
+    "    agent=agent, tools=tools, verbose=True, stream_runnable=False\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9c1ae74d-8300-4041-9ff4-66093ee592b1",
+   "metadata": {},
+   "source": [
+    "```{=mdx}\n",
+    ":::note\n",
+    "We have to set `stream_runnable=False` for cost information, as described above. By default the AgentExecutor will stream the underlying agent so that you can get the most granular results when streaming events via AgentExecutor.stream_events.\n",
+    ":::\n",
+    "```"
    ]
   },
   {
@@ -485,30 +503,36 @@
       "\n",
       "\n",
       "\n",
-      "Page: Allen's hummingbird\n",
-      "Summary: Allen's hummingbird (Selasphorus sasin) is a species of hummingbird that breeds in the western United States. It is one of seven species in the genus Selasphorus.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
+      "Page: Anna's hummingbird\n",
+      "Summary: Anna's hummingbird (Calypte anna) is a North American species of hummingbird. It was named after Anna Masséna, Duchess of Rivoli.\n",
+      "It is native to western coastal regions of North America. In the early 20th century, Anna's hummingbirds bred only in northern Baja California and Southern California. The transplanting of exotic ornamental plants in residential areas throughout the Pacific coast and inland deserts provided expanded nectar and nesting sites, allowing the species to expand its breeding range. Year-round residence of Anna's hummingbirds in the Pacific Northwest is an example of ecological release dependent on acclimation to colder winter temperatures, introduced plants, and human provision of nectar feeders during winter.\n",
+      "These birds feed on nectar from flowers using a long extendable tongue. They also consume small insects and other arthropods caught in flight or gleaned from vegetation.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
       "Invoking: `wikipedia` with `{'query': 'fastest bird species'}`\n",
       "\n",
       "\n",
       "\u001b[0m\u001b[36;1m\u001b[1;3mPage: List of birds by flight speed\n",
       "Summary: This is a list of the fastest flying birds in the world. A bird's velocity is necessarily variable; a hunting bird will reach much greater speeds while diving to catch prey than when flying horizontally. The bird that can achieve the greatest airspeed is the peregrine falcon (Falco peregrinus), able to exceed 320 km/h (200 mph) in its dives. A close relative of the common swift, the white-throated needletail (Hirundapus caudacutus), is commonly reported as the fastest bird in level flight with a reported top speed of 169 km/h (105 mph). This record remains unconfirmed as the measurement methods have never been published or verified. The record for the fastest confirmed level flight by a bird is 111.5 km/h (69.3 mph) held by the common swift.\n",
       "\n",
+      "\n",
+      "\n",
       "Page: Fastest animals\n",
       "Summary: This is a list of the fastest animals in the world, by types of animal.\n",
       "\n",
+      "\n",
+      "\n",
       "Page: Falcon\n",
       "Summary: Falcons () are birds of prey in the genus Falco, which includes about 40 species. Falcons are widely distributed on all continents of the world except Antarctica, though closely related raptors did occur there in the Eocene.\n",
       "Adult falcons have thin, tapered wings, which enable them to fly at high speed and change direction rapidly. Fledgling falcons, in their first year of flying, have longer flight feathers, which make their configuration more like that of a general-purpose bird such as a broad wing. This makes flying easier while learning the exceptional skills required to be effective hunters as adults.\n",
       "The falcons are the largest genus in the Falconinae subfamily of Falconidae, which itself also includes another subfamily comprising caracaras and a few other species. All these birds kill with their beaks, using a tomial \"tooth\" on the side of their beaks—unlike the hawks, eagles, and other birds of prey in the Accipitridae, which use their feet.\n",
       "The largest falcon is the gyrfalcon at up to 65 cm in length.  The smallest falcon species is the pygmy falcon, which measures just 20 cm.  As with hawks and owls, falcons exhibit sexual dimorphism, with the females typically larger than the males, thus allowing a wider range of prey species.\n",
       "Some small falcons with long, narrow wings are called \"hobbies\" and some which hover while hunting are called \"kestrels\".\n",
-      "As is the case with many birds of prey, falcons have exceptional powers of vision; the visual acuity of one species has been measured at 2.6 times that of a normal human. Peregrine falcons have been recorded diving at speeds of 320 km/h (200 mph), making them the fastest-moving creatures on Earth; the fastest recorded dive attained a vertical speed of 390 km/h (240 mph).\u001b[0m\u001b[32;1m\u001b[1;3mThe scientific name for a hummingbird is Trochilidae. The fastest bird species in level flight is the common swift, which holds the record for the fastest confirmed level flight by a bird at 111.5 km/h (69.3 mph). The peregrine falcon is known to exceed speeds of 320 km/h (200 mph) in its dives, making it the fastest bird in terms of diving speed.\u001b[0m\n",
+      "As is the case with many birds of prey, falcons have exceptional powers of vision; the visual acuity of one species has been measured at 2.6 times that of a normal human. Peregrine falcons have been recorded diving at speeds of 320 km/h (200 mph), making them the fastest-moving creatures on Earth; the fastest recorded dive attained a vertical speed of 390 km/h (240 mph).\u001b[0m\u001b[32;1m\u001b[1;3mThe scientific name for a hummingbird is Trochilidae. The fastest bird species is the peregrine falcon (Falco peregrinus), which can exceed speeds of 320 km/h (200 mph) in its dives.\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n",
-      "Total Tokens: 1675\n",
-      "Prompt Tokens: 1538\n",
-      "Completion Tokens: 137\n",
-      "Total Cost (USD): $0.0009745000000000001\n"
+      "Total Tokens: 1787\n",
+      "Prompt Tokens: 1687\n",
+      "Completion Tokens: 100\n",
+      "Total Cost (USD): $0.0009935\n"
      ]
     }
    ],

docs/docs/how_to/code_splitter.ipynb

@@ -54,7 +54,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2bb9c73f-9d00-4a19-a81f-cab2f0fd921a",
+   "id": "9e4144de-d925-4d4c-91c3-685ef8baa57c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -63,7 +63,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "id": "a9e37aa1",
    "metadata": {},
    "outputs": [],
@@ -300,7 +300,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 8,
    "id": "ac9295d3",
    "metadata": {},
    "outputs": [],
@@ -312,8 +312,10 @@
     "\n",
     "## Quick Install\n",
     "\n",
+    "```bash\n",
     "# Hopefully this code block isn't split\n",
     "pip install langchain\n",
+    "```\n",
     "\n",
     "As an open-source project in a rapidly developing field, we are extremely open to contributions.\n",
     "\"\"\""
@@ -321,7 +323,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 9,
    "id": "3a0cb17a",
    "metadata": {},
    "outputs": [
@@ -330,14 +332,15 @@
       "text/plain": [
        "[Document(page_content='# 🦜️🔗 LangChain'),\n",
        " Document(page_content='⚡ Building applications with LLMs through composability ⚡'),\n",
-       " Document(page_content='## Quick Install'),\n",
+       " Document(page_content='## Quick Install\\n\\n```bash'),\n",
        " Document(page_content=\"# Hopefully this code block isn't split\"),\n",
        " Document(page_content='pip install langchain'),\n",
+       " Document(page_content='```'),\n",
        " Document(page_content='As an open-source project in a rapidly developing field, we'),\n",
        " Document(page_content='are extremely open to contributions.')]"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -718,44 +721,8 @@
     "php_splitter = RecursiveCharacterTextSplitter.from_language(\n",
     "    language=Language.PHP, chunk_size=50, chunk_overlap=0\n",
     ")\n",
-    "php_docs = php_splitter.create_documents([PHP_CODE])\n",
-    "php_docs"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e9fa62c1",
-   "metadata": {},
-   "source": [
-    "## PowerShell\n",
-    "Here's an example using the PowerShell text splitter:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7e6893ad",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "POWERSHELL_CODE = \"\"\"\n",
-    "$directoryPath = Get-Location\n",
-    "\n",
-    "$items = Get-ChildItem -Path $directoryPath\n",
-    "\n",
-    "$files = $items | Where-Object { -not $_.PSIsContainer }\n",
-    "\n",
-    "$sortedFiles = $files | Sort-Object LastWriteTime\n",
-    "\n",
-    "foreach ($file in $sortedFiles) {\n",
-    "    Write-Output (\"Name: \" + $file.Name + \" | Last Write Time: \" + $file.LastWriteTime)\n",
-    "}\n",
-    "\"\"\"\n",
-    "powershell_splitter = RecursiveCharacterTextSplitter.from_language(\n",
-    "    language=Language.POWERSHELL, chunk_size=100, chunk_overlap=0\n",
-    ")\n",
-    "powershell_docs = powershell_splitter.create_documents([POWERSHELL_CODE])\n",
-    "powershell_docs"
+    "haskell_docs = php_splitter.create_documents([PHP_CODE])\n",
+    "haskell_docs"
    ]
   }
  ],

docs/docs/how_to/configure.ipynb

@@ -48,10 +48,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "40ed76a2",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 24.0 is available.\n",
+      "You should consider upgrading via the '/Users/jacoblee/.pyenv/versions/3.10.5/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n",
+      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
     "%pip install --upgrade --quiet langchain langchain-openai\n",
     "\n",

docs/docs/how_to/contextual_compression.ipynb

@@ -220,57 +220,6 @@
     "pretty_print_docs(compressed_docs)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "14002ec8-7ee5-4f91-9315-dd21c3808776",
-   "metadata": {},
-   "source": [
-    "### `LLMListwiseRerank`\n",
-    "\n",
-    "[LLMListwiseRerank](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.document_compressors.listwise_rerank.LLMListwiseRerank.html) uses [zero-shot listwise document reranking](https://arxiv.org/pdf/2305.02156) and functions similarly to `LLMChainFilter` as a robust but more expensive option. It is recommended to use a more powerful LLM.\n",
-    "\n",
-    "Note that `LLMListwiseRerank` requires a model with the [with_structured_output](/docs/integrations/chat/) method implemented."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "4ab9ee9f-917e-4d6f-9344-eb7f01533228",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Document 1:\n",
-      "\n",
-      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
-      "\n",
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain.retrievers.document_compressors import LLMListwiseRerank\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
-    "\n",
-    "_filter = LLMListwiseRerank.from_llm(llm, top_n=1)\n",
-    "compression_retriever = ContextualCompressionRetriever(\n",
-    "    base_compressor=_filter, base_retriever=retriever\n",
-    ")\n",
-    "\n",
-    "compressed_docs = compression_retriever.invoke(\n",
-    "    \"What did the president say about Ketanji Jackson Brown\"\n",
-    ")\n",
-    "pretty_print_docs(compressed_docs)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "7194da42",
@@ -346,7 +295,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "617a1756",
    "metadata": {},
    "outputs": [],

docs/docs/how_to/convert_runnable_to_tool.ipynb

@@ -1,549 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "9a8bceb3-95bd-4496-bb9e-57655136e070",
-   "metadata": {},
-   "source": [
-    "# How to convert Runnables as Tools\n",
-    "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "\n",
-    "- [Runnables](/docs/concepts#runnable-interface)\n",
-    "- [Tools](/docs/concepts#tools)\n",
-    "- [Agents](/docs/tutorials/agents)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Here we will demonstrate how to convert a LangChain `Runnable` into a tool that can be used by agents, chains, or chat models.\n",
-    "\n",
-    "## Dependencies\n",
-    "\n",
-    "**Note**: this guide requires `langchain-core` >= 0.2.13. We will also use [OpenAI](/docs/integrations/platforms/openai/) for embeddings, but any LangChain embeddings should suffice. We will use a simple [LangGraph](https://langchain-ai.github.io/langgraph/) agent for demonstration purposes."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "92341f48-2c29-4ce9-8ab8-0a7c7a7c98a1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install -U langchain-core langchain-openai langgraph"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2b0dcc1a-48e8-4a81-b920-3563192ce076",
-   "metadata": {},
-   "source": [
-    "LangChain [tools](/docs/concepts#tools) are interfaces that an agent, chain, or chat model can use to interact with the world. See [here](/docs/how_to/#tools) for how-to guides covering tool-calling, built-in tools, custom tools, and more information.\n",
-    "\n",
-    "LangChain tools-- instances of [BaseTool](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html)-- are [Runnables](/docs/concepts/#runnable-interface) with additional constraints that enable them to be invoked effectively by language models:\n",
-    "\n",
-    "- Their inputs are constrained to be serializable, specifically strings and Python `dict` objects;\n",
-    "- They contain names and descriptions indicating how and when they should be used;\n",
-    "- They may contain a detailed [args_schema](https://python.langchain.com/v0.2/docs/how_to/custom_tools/) for their arguments. That is, while a tool (as a `Runnable`) might accept a single `dict` input, the specific keys and type information needed to populate a dict should be specified in the `args_schema`.\n",
-    "\n",
-    "Runnables that accept string or `dict` input can be converted to tools using the [as_tool](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.as_tool) method, which allows for the specification of names, descriptions, and additional schema information for arguments."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b4d76680-1b6b-4862-8c4f-22766a1d41f2",
-   "metadata": {},
-   "source": [
-    "## Basic usage\n",
-    "\n",
-    "With typed `dict` input:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "b2cc4231-64a3-4733-a284-932dcbf2fcc3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import List\n",
-    "\n",
-    "from langchain_core.runnables import RunnableLambda\n",
-    "from typing_extensions import TypedDict\n",
-    "\n",
-    "\n",
-    "class Args(TypedDict):\n",
-    "    a: int\n",
-    "    b: List[int]\n",
-    "\n",
-    "\n",
-    "def f(x: Args) -> str:\n",
-    "    return str(x[\"a\"] * max(x[\"b\"]))\n",
-    "\n",
-    "\n",
-    "runnable = RunnableLambda(f)\n",
-    "as_tool = runnable.as_tool(\n",
-    "    name=\"My tool\",\n",
-    "    description=\"Explanation of when to use tool.\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "57f2d435-624d-459a-903d-8509fbbde610",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Explanation of when to use tool.\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'title': 'My tool',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'a': {'title': 'A', 'type': 'integer'},\n",
-       "  'b': {'title': 'B', 'type': 'array', 'items': {'type': 'integer'}}},\n",
-       " 'required': ['a', 'b']}"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "print(as_tool.description)\n",
-    "\n",
-    "as_tool.args_schema.schema()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "54ae7384-a03d-4fa4-8cdf-9604a4bc39ee",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'6'"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "as_tool.invoke({\"a\": 3, \"b\": [1, 2]})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9038f587-4613-4f50-b349-135f9e7e3b15",
-   "metadata": {},
-   "source": [
-    "Without typing information, arg types can be specified via `arg_types`:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "169f733c-4936-497f-8577-ee769dc16b88",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import Any, Dict\n",
-    "\n",
-    "\n",
-    "def g(x: Dict[str, Any]) -> str:\n",
-    "    return str(x[\"a\"] * max(x[\"b\"]))\n",
-    "\n",
-    "\n",
-    "runnable = RunnableLambda(g)\n",
-    "as_tool = runnable.as_tool(\n",
-    "    name=\"My tool\",\n",
-    "    description=\"Explanation of when to use tool.\",\n",
-    "    arg_types={\"a\": int, \"b\": List[int]},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "32b1a992-8997-4c98-8eb2-c9fe9431b799",
-   "metadata": {},
-   "source": [
-    "Alternatively, the schema can be fully specified by directly passing the desired [args_schema](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html#langchain_core.tools.BaseTool.args_schema) for the tool:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "eb102705-89b7-48dc-9158-d36d5f98ae8e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "\n",
-    "class GSchema(BaseModel):\n",
-    "    \"\"\"Apply a function to an integer and list of integers.\"\"\"\n",
-    "\n",
-    "    a: int = Field(..., description=\"Integer\")\n",
-    "    b: List[int] = Field(..., description=\"List of ints\")\n",
-    "\n",
-    "\n",
-    "runnable = RunnableLambda(g)\n",
-    "as_tool = runnable.as_tool(GSchema)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7c474d85-4e01-4fae-9bba-0c6c8c26475c",
-   "metadata": {},
-   "source": [
-    "String input is also supported:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "c475282a-58d6-4c2b-af7d-99b73b7d8a13",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def f(x: str) -> str:\n",
-    "    return x + \"a\"\n",
-    "\n",
-    "\n",
-    "def g(x: str) -> str:\n",
-    "    return x + \"z\"\n",
-    "\n",
-    "\n",
-    "runnable = RunnableLambda(f) | g\n",
-    "as_tool = runnable.as_tool()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "ad6d8d96-3a87-40bd-a2ac-44a8acde0a8e",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'baz'"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "as_tool.invoke(\"b\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "89fdb3a7-d228-48f0-8f73-262af4febb58",
-   "metadata": {},
-   "source": [
-    "## In agents\n",
-    "\n",
-    "Below we will incorporate LangChain Runnables as tools in an [agent](/docs/concepts/#agents) application. We will demonstrate with:\n",
-    "\n",
-    "- a document [retriever](/docs/concepts/#retrievers);\n",
-    "- a simple [RAG](/docs/tutorials/rag/) chain, allowing an agent to delegate relevant queries to it.\n",
-    "\n",
-    "We first instantiate a chat model that supports [tool calling](/docs/how_to/tool_calling/):\n",
-    "\n",
-    "```{=mdx}\n",
-    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
-    "\n",
-    "<ChatModelTabs customVarName=\"llm\" />\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "d06c9f2a-4475-450f-9106-54db1d99623b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# | output: false\n",
-    "# | echo: false\n",
-    "\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e8a2038a-d762-4196-b5e3-fdb89c11e71d",
-   "metadata": {},
-   "source": [
-    "Following the [RAG tutorial](/docs/tutorials/rag/), let's first construct a retriever:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "23d2a47e-6712-4294-81c8-2c1d76b4bb81",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.documents import Document\n",
-    "from langchain_core.vectorstores import InMemoryVectorStore\n",
-    "from langchain_openai import OpenAIEmbeddings\n",
-    "\n",
-    "documents = [\n",
-    "    Document(\n",
-    "        page_content=\"Dogs are great companions, known for their loyalty and friendliness.\",\n",
-    "    ),\n",
-    "    Document(\n",
-    "        page_content=\"Cats are independent pets that often enjoy their own space.\",\n",
-    "    ),\n",
-    "]\n",
-    "\n",
-    "vectorstore = InMemoryVectorStore.from_documents(\n",
-    "    documents, embedding=OpenAIEmbeddings()\n",
-    ")\n",
-    "\n",
-    "retriever = vectorstore.as_retriever(\n",
-    "    search_type=\"similarity\",\n",
-    "    search_kwargs={\"k\": 1},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9ba737ac-43a2-4a6f-b855-5bd0305017f1",
-   "metadata": {},
-   "source": [
-    "We next create use a simple pre-built [LangGraph agent](https://python.langchain.com/v0.2/docs/tutorials/agents/) and provide it the tool:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "c939cf2a-60e9-4afd-8b47-84d76ccb13f5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import create_react_agent\n",
-    "\n",
-    "tools = [\n",
-    "    retriever.as_tool(\n",
-    "        name=\"pet_info_retriever\",\n",
-    "        description=\"Get information about pets.\",\n",
-    "    )\n",
-    "]\n",
-    "agent = create_react_agent(llm, tools)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "be29437b-a187-4a0a-9a5d-419c56f2434e",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_W8cnfOjwqEn4cFcg19LN9mYD', 'function': {'arguments': '{\"__arg1\":\"dogs\"}', 'name': 'pet_info_retriever'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 19, 'prompt_tokens': 60, 'total_tokens': 79}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-d7f81de9-1fb7-4caf-81ed-16dcdb0b2ab4-0', tool_calls=[{'name': 'pet_info_retriever', 'args': {'__arg1': 'dogs'}, 'id': 'call_W8cnfOjwqEn4cFcg19LN9mYD'}], usage_metadata={'input_tokens': 60, 'output_tokens': 19, 'total_tokens': 79})]}}\n",
-      "----\n",
-      "{'tools': {'messages': [ToolMessage(content=\"[Document(id='86f835fe-4bbe-4ec6-aeb4-489a8b541707', page_content='Dogs are great companions, known for their loyalty and friendliness.')]\", name='pet_info_retriever', tool_call_id='call_W8cnfOjwqEn4cFcg19LN9mYD')]}}\n",
-      "----\n",
-      "{'agent': {'messages': [AIMessage(content='Dogs are known for being great companions, known for their loyalty and friendliness.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 134, 'total_tokens': 152}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-9ca5847a-a5eb-44c0-a774-84cc2c5bbc5b-0', usage_metadata={'input_tokens': 134, 'output_tokens': 18, 'total_tokens': 152})]}}\n",
-      "----\n"
-     ]
-    }
-   ],
-   "source": [
-    "for chunk in agent.stream({\"messages\": [(\"human\", \"What are dogs known for?\")]}):\n",
-    "    print(chunk)\n",
-    "    print(\"----\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "96f2ac9c-36f4-4b7a-ae33-f517734c86aa",
-   "metadata": {},
-   "source": [
-    "See [LangSmith trace](https://smith.langchain.com/public/44e438e3-2faf-45bd-b397-5510fc145eb9/r) for the above run."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a722fd8a-b957-4ba7-b408-35596b76835f",
-   "metadata": {},
-   "source": [
-    "Going further, we can create a simple [RAG](/docs/tutorials/rag/) chain that takes an additional parameter-- here, the \"style\" of the answer."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "bea518c9-c711-47c2-b8cc-dbd102f71f09",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from operator import itemgetter\n",
-    "\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "\n",
-    "system_prompt = \"\"\"\n",
-    "You are an assistant for question-answering tasks.\n",
-    "Use the below context to answer the question. If\n",
-    "you don't know the answer, say you don't know.\n",
-    "Use three sentences maximum and keep the answer\n",
-    "concise.\n",
-    "\n",
-    "Answer in the style of {answer_style}.\n",
-    "\n",
-    "Question: {question}\n",
-    "\n",
-    "Context: {context}\n",
-    "\"\"\"\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages([(\"system\", system_prompt)])\n",
-    "\n",
-    "rag_chain = (\n",
-    "    {\n",
-    "        \"context\": itemgetter(\"question\") | retriever,\n",
-    "        \"question\": itemgetter(\"question\"),\n",
-    "        \"answer_style\": itemgetter(\"answer_style\"),\n",
-    "    }\n",
-    "    | prompt\n",
-    "    | llm\n",
-    "    | StrOutputParser()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "955a23db-5218-4c34-8486-450a2ddb3443",
-   "metadata": {},
-   "source": [
-    "Note that the input schema for our chain contains the required arguments, so it converts to a tool without further specification:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "2c9f6e61-80ed-4abb-8e77-84de3ccbc891",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'title': 'RunnableParallel<context,question,answer_style>Input',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'question': {'title': 'Question'},\n",
-       "  'answer_style': {'title': 'Answer Style'}}}"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "rag_chain.input_schema.schema()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "a3f9cf5b-8c71-4b0f-902b-f92e028780c9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "rag_tool = rag_chain.as_tool(\n",
-    "    name=\"pet_expert\",\n",
-    "    description=\"Get information about pets.\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4570615b-8f96-4d97-ae01-1c08b14be584",
-   "metadata": {},
-   "source": [
-    "Below we again invoke the agent. Note that the agent populates the required parameters in its `tool_calls`:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "06409913-a2ad-400f-a202-7b8dd2ef483a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_17iLPWvOD23zqwd1QVQ00Y63', 'function': {'arguments': '{\"question\":\"What are dogs known for according to pirates?\",\"answer_style\":\"quote\"}', 'name': 'pet_expert'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 28, 'prompt_tokens': 59, 'total_tokens': 87}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-7fef44f3-7bba-4e63-8c51-2ad9c5e65e2e-0', tool_calls=[{'name': 'pet_expert', 'args': {'question': 'What are dogs known for according to pirates?', 'answer_style': 'quote'}, 'id': 'call_17iLPWvOD23zqwd1QVQ00Y63'}], usage_metadata={'input_tokens': 59, 'output_tokens': 28, 'total_tokens': 87})]}}\n",
-      "----\n",
-      "{'tools': {'messages': [ToolMessage(content='\"Dogs are known for their loyalty and friendliness, making them great companions for pirates on long sea voyages.\"', name='pet_expert', tool_call_id='call_17iLPWvOD23zqwd1QVQ00Y63')]}}\n",
-      "----\n",
-      "{'agent': {'messages': [AIMessage(content='According to pirates, dogs are known for their loyalty and friendliness, making them great companions for pirates on long sea voyages.', response_metadata={'token_usage': {'completion_tokens': 27, 'prompt_tokens': 119, 'total_tokens': 146}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5a30edc3-7be0-4743-b980-ca2f8cad9b8d-0', usage_metadata={'input_tokens': 119, 'output_tokens': 27, 'total_tokens': 146})]}}\n",
-      "----\n"
-     ]
-    }
-   ],
-   "source": [
-    "agent = create_react_agent(llm, [rag_tool])\n",
-    "\n",
-    "for chunk in agent.stream(\n",
-    "    {\"messages\": [(\"human\", \"What would a pirate say dogs are known for?\")]}\n",
-    "):\n",
-    "    print(chunk)\n",
-    "    print(\"----\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "96cc9bc3-e79e-49a8-9915-428ea225358b",
-   "metadata": {},
-   "source": [
-    "See [LangSmith trace](https://smith.langchain.com/public/147ae4e6-4dfb-4dd9-8ca0-5c5b954f08ac/r) for the above run."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/how_to/custom_chat_model.ipynb

@@ -131,7 +131,7 @@
    "source": [
     "## Base Chat Model\n",
     "\n",
-    "Let's implement a chat model that echoes back the first `n` characters of the last message in the prompt!\n",
+    "Let's implement a chat model that echoes back the first `n` characetrs of the last message in the prompt!\n",
     "\n",
     "To do so, we will inherit from `BaseChatModel` and we'll need to implement the following:\n",
     "\n",

docs/docs/how_to/custom_tools.ipynb

@@ -5,7 +5,7 @@
    "id": "5436020b",
    "metadata": {},
    "source": [
-    "# How to create tools\n",
+    "# How to create custom tools\n",
     "\n",
     "When constructing an agent, you will need to provide it with a list of `Tool`s that it can use. Besides the actual function that is called, the Tool consists of several components:\n",
     "\n",
@@ -16,15 +16,13 @@
     "| args_schema   | Pydantic BaseModel      | Optional but recommended, can be used to provide more information (e.g., few-shot examples) or validation for expected parameters |\n",
     "| return_direct   | boolean      | Only relevant for agents. When True, after invoking the given tool, the agent will stop and return the result direcly to the user.  |\n",
     "\n",
-    "LangChain supports the creation of tools from:\n",
+    "LangChain provides 3 ways to create tools:\n",
     "\n",
-    "1. Functions;\n",
-    "2. LangChain [Runnables](/docs/concepts#runnable-interface);\n",
+    "1. Using [@tool decorator](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.tool.html#langchain_core.tools.tool) -- the simplest way to define a custom tool.\n",
+    "2. Using [StructuredTool.from_function](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.StructuredTool.html#langchain_core.tools.StructuredTool.from_function) class method -- this is similar to the `@tool` decorator, but allows more configuration and specification of both sync and async implementations.\n",
     "3. By sub-classing from [BaseTool](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html) -- This is the most flexible method, it provides the largest degree of control, at the expense of more effort and code.\n",
     "\n",
-    "Creating tools from functions may be sufficient for most use cases, and can be done via a simple [@tool decorator](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.tool.html#langchain_core.tools.tool). If more configuration is needed-- e.g., specification of both sync and async implementations-- one can also use the [StructuredTool.from_function](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.StructuredTool.html#langchain_core.tools.StructuredTool.from_function) class method.\n",
-    "\n",
-    "In this guide we provide an overview of these methods.\n",
+    "The `@tool` or the `StructuredTool.from_function` class method should be sufficient for most use cases.\n",
     "\n",
     ":::{.callout-tip}\n",
     "\n",
@@ -37,9 +35,7 @@
    "id": "c7326b23",
    "metadata": {},
    "source": [
-    "## Creating tools from functions\n",
-    "\n",
-    "### @tool decorator\n",
+    "## @tool decorator\n",
     "\n",
     "This `@tool` decorator is the simplest way to define a custom tool. The decorator uses the function name as the tool name by default, but this can be overridden by passing a string as the first argument. Additionally, the decorator will use the function's docstring as the tool's description - so a docstring MUST be provided. "
    ]
@@ -55,7 +51,7 @@
      "output_type": "stream",
      "text": [
       "multiply\n",
-      "Multiply two numbers.\n",
+      "multiply(a: int, b: int) -> int - Multiply two numbers.\n",
       "{'a': {'title': 'A', 'type': 'integer'}, 'b': {'title': 'B', 'type': 'integer'}}\n"
      ]
     }
@@ -100,57 +96,6 @@
     "    return a * b"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "8f0edc51-c586-414c-8941-c8abe779943f",
-   "metadata": {},
-   "source": [
-    "Note that `@tool` supports parsing of annotations, nested schemas, and other features:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "5626423f-053e-4a66-adca-1d794d835397",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'title': 'multiply_by_maxSchema',\n",
-       " 'description': 'Multiply a by the maximum of b.',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'a': {'title': 'A',\n",
-       "   'description': 'scale factor',\n",
-       "   'type': 'string'},\n",
-       "  'b': {'title': 'B',\n",
-       "   'description': 'list of ints over which to take maximum',\n",
-       "   'type': 'array',\n",
-       "   'items': {'type': 'integer'}}},\n",
-       " 'required': ['a', 'b']}"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from typing import Annotated, List\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def multiply_by_max(\n",
-    "    a: Annotated[str, \"scale factor\"],\n",
-    "    b: Annotated[List[int], \"list of ints over which to take maximum\"],\n",
-    ") -> int:\n",
-    "    \"\"\"Multiply a by the maximum of b.\"\"\"\n",
-    "    return a * max(b)\n",
-    "\n",
-    "\n",
-    "multiply_by_max.args_schema.schema()"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "98d6eee9",
@@ -161,7 +106,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "9216d03a-f6ea-4216-b7e1-0661823a4c0b",
    "metadata": {},
    "outputs": [
@@ -170,7 +115,7 @@
      "output_type": "stream",
      "text": [
       "multiplication-tool\n",
-      "Multiply two numbers.\n",
+      "multiplication-tool(a: int, b: int) -> int - Multiply two numbers.\n",
       "{'a': {'title': 'A', 'description': 'first number', 'type': 'integer'}, 'b': {'title': 'B', 'description': 'second number', 'type': 'integer'}}\n",
       "True\n"
      ]
@@ -198,84 +143,19 @@
     "print(multiply.return_direct)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "33a9e94d-0b60-48f3-a4c2-247dce096e66",
-   "metadata": {},
-   "source": [
-    "#### Docstring parsing"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6d0cb586-93d4-4ff1-9779-71df7853cb68",
-   "metadata": {},
-   "source": [
-    "`@tool` can optionally parse [Google Style docstrings](https://google.github.io/styleguide/pyguide.html#383-functions-and-methods) and associate the docstring components (such as arg descriptions) to the relevant parts of the tool schema. To toggle this behavior, specify `parse_docstring`:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "336f5538-956e-47d5-9bde-b732559f9e61",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'title': 'fooSchema',\n",
-       " 'description': 'The foo.',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'bar': {'title': 'Bar',\n",
-       "   'description': 'The bar.',\n",
-       "   'type': 'string'},\n",
-       "  'baz': {'title': 'Baz', 'description': 'The baz.', 'type': 'integer'}},\n",
-       " 'required': ['bar', 'baz']}"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "@tool(parse_docstring=True)\n",
-    "def foo(bar: str, baz: int) -> str:\n",
-    "    \"\"\"The foo.\n",
-    "\n",
-    "    Args:\n",
-    "        bar: The bar.\n",
-    "        baz: The baz.\n",
-    "    \"\"\"\n",
-    "    return bar\n",
-    "\n",
-    "\n",
-    "foo.args_schema.schema()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f18a2503-5393-421b-99fa-4a01dd824d0e",
-   "metadata": {},
-   "source": [
-    ":::{.callout-caution}\n",
-    "By default, `@tool(parse_docstring=True)` will raise `ValueError` if the docstring does not parse correctly. See [API Reference](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.tool.html) for detail and examples.\n",
-    ":::"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "b63fcc3b",
    "metadata": {},
    "source": [
-    "### StructuredTool\n",
+    "## StructuredTool\n",
     "\n",
-    "The `StructuredTool.from_function` class method provides a bit more configurability than the `@tool` decorator, without requiring much additional code."
+    "The `StrurcturedTool.from_function` class method provides a bit more configurability than the `@tool` decorator, without requiring much additional code."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "id": "564fbe6f-11df-402d-b135-ef6ff25e1e63",
    "metadata": {},
    "outputs": [
@@ -318,7 +198,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
    "id": "6bc055d4-1fbe-4db5-8881-9c382eba6b1b",
    "metadata": {},
    "outputs": [
@@ -328,7 +208,7 @@
      "text": [
       "6\n",
       "Calculator\n",
-      "multiply numbers\n",
+      "Calculator(a: int, b: int) -> int - multiply numbers\n",
       "{'a': {'title': 'A', 'description': 'first number', 'type': 'integer'}, 'b': {'title': 'B', 'description': 'second number', 'type': 'integer'}}\n"
      ]
     }
@@ -359,63 +239,6 @@
     "print(calculator.args)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "5517995d-54e3-449b-8fdb-03561f5e4647",
-   "metadata": {},
-   "source": [
-    "## Creating tools from Runnables\n",
-    "\n",
-    "LangChain [Runnables](/docs/concepts#runnable-interface) that accept string or `dict` input can be converted to tools using the [as_tool](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.as_tool) method, which allows for the specification of names, descriptions, and additional schema information for arguments.\n",
-    "\n",
-    "Example usage:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "8ef593c5-cf72-4c10-bfc9-7d21874a0c24",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'answer_style': {'title': 'Answer Style', 'type': 'string'}}"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.language_models import GenericFakeChatModel\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [(\"human\", \"Hello. Please respond in the style of {answer_style}.\")]\n",
-    ")\n",
-    "\n",
-    "# Placeholder LLM\n",
-    "llm = GenericFakeChatModel(messages=iter([\"hello matey\"]))\n",
-    "\n",
-    "chain = prompt | llm | StrOutputParser()\n",
-    "\n",
-    "as_tool = chain.as_tool(\n",
-    "    name=\"Style responder\", description=\"Description of when to use tool.\"\n",
-    ")\n",
-    "as_tool.args"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0521b787-a146-45a6-8ace-ae1ac4669dd7",
-   "metadata": {},
-   "source": [
-    "See [this guide](/docs/how_to/convert_runnable_to_tool) for more detail."
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "b840074b-9c10-4ca0-aed8-626c52b2398f",
@@ -428,7 +251,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 16,
    "id": "1dad8f8e",
    "metadata": {},
    "outputs": [],
@@ -477,7 +300,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 7,
    "id": "bb551c33",
    "metadata": {},
    "outputs": [
@@ -528,7 +351,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 8,
    "id": "6615cb77-fd4c-4676-8965-f92cc71d4944",
    "metadata": {},
    "outputs": [
@@ -560,7 +383,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 9,
    "id": "bb2af583-eadd-41f4-a645-bf8748bd3dcd",
    "metadata": {},
    "outputs": [
@@ -605,7 +428,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 10,
    "id": "4ad0932c-8610-4278-8c57-f9218f654c8a",
    "metadata": {},
    "outputs": [
@@ -650,7 +473,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 11,
    "id": "7094c0e8-6192-4870-a942-aad5b5ae48fd",
    "metadata": {},
    "outputs": [],
@@ -673,7 +496,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 12,
    "id": "b4d22022-b105-4ccc-a15b-412cb9ea3097",
    "metadata": {},
    "outputs": [
@@ -683,7 +506,7 @@
        "'Error: There is no city by the name of foobar.'"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -707,7 +530,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 13,
    "id": "3fad1728-d367-4e1b-9b54-3172981271cf",
    "metadata": {},
    "outputs": [
@@ -717,7 +540,7 @@
        "\"There is no such city, but it's probably above 0K there!\""
       ]
      },
-     "execution_count": 17,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -741,7 +564,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 14,
    "id": "ebfe7c1f-318d-4e58-99e1-f31e69473c46",
    "metadata": {},
    "outputs": [
@@ -751,7 +574,7 @@
        "'The following errors occurred during tool execution: `Error: There is no city by the name of foobar.`'"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -768,189 +591,13 @@
     "\n",
     "get_weather_tool.invoke({\"city\": \"foobar\"})"
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1a8d8383-11b3-445e-956f-df4e96995e00",
-   "metadata": {},
-   "source": [
-    "## Returning artifacts of Tool execution\n",
-    "\n",
-    "Sometimes there are artifacts of a tool's execution that we want to make accessible to downstream components in our chain or agent, but that we don't want to expose to the model itself. For example if a tool returns custom objects like Documents, we may want to pass some view or metadata about this output to the model without passing the raw output to the model. At the same time, we may want to be able to access this full output elsewhere, for example in downstream tools.\n",
-    "\n",
-    "The Tool and [ToolMessage](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolMessage.html) interfaces make it possible to distinguish between the parts of the tool output meant for the model (this is the ToolMessage.content) and those parts which are meant for use outside the model (ToolMessage.artifact).\n",
-    "\n",
-    ":::info Requires ``langchain-core >= 0.2.19``\n",
-    "\n",
-    "This functionality was added in ``langchain-core == 0.2.19``. Please make sure your package is up to date.\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "If we want our tool to distinguish between message content and other artifacts, we need to specify `response_format=\"content_and_artifact\"` when defining our tool and make sure that we return a tuple of (content, artifact):"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "14905425-0334-43a0-9de9-5bcf622ede0e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import random\n",
-    "from typing import List, Tuple\n",
-    "\n",
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool(response_format=\"content_and_artifact\")\n",
-    "def generate_random_ints(min: int, max: int, size: int) -> Tuple[str, List[int]]:\n",
-    "    \"\"\"Generate size random ints in the range [min, max].\"\"\"\n",
-    "    array = [random.randint(min, max) for _ in range(size)]\n",
-    "    content = f\"Successfully generated array of {size} random ints in [{min}, {max}].\"\n",
-    "    return content, array"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "49f057a6-8938-43ea-8faf-ae41e797ceb8",
-   "metadata": {},
-   "source": [
-    "If we invoke our tool directly with the tool arguments, we'll get back just the content part of the output:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "0f2e1528-404b-46e6-b87c-f0957c4b9217",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Successfully generated array of 10 random ints in [0, 9].'"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "generate_random_ints.invoke({\"min\": 0, \"max\": 9, \"size\": 10})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1e62ebba-1737-4b97-b61a-7313ade4e8c2",
-   "metadata": {},
-   "source": [
-    "If we invoke our tool with a ToolCall (like the ones generated by tool-calling models), we'll get back a ToolMessage that contains both the content and artifact generated by the Tool:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "cc197777-26eb-46b3-a83b-c2ce116c6311",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "ToolMessage(content='Successfully generated array of 10 random ints in [0, 9].', name='generate_random_ints', tool_call_id='123', artifact=[1, 4, 2, 5, 3, 9, 0, 4, 7, 7])"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "generate_random_ints.invoke(\n",
-    "    {\n",
-    "        \"name\": \"generate_random_ints\",\n",
-    "        \"args\": {\"min\": 0, \"max\": 9, \"size\": 10},\n",
-    "        \"id\": \"123\",  # required\n",
-    "        \"type\": \"tool_call\",  # required\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "dfdc1040-bf25-4790-b4c3-59452db84e11",
-   "metadata": {},
-   "source": [
-    "We can do the same when subclassing BaseTool:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "fe1a09d1-378b-4b91-bb5e-0697c3d7eb92",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.tools import BaseTool\n",
-    "\n",
-    "\n",
-    "class GenerateRandomFloats(BaseTool):\n",
-    "    name: str = \"generate_random_floats\"\n",
-    "    description: str = \"Generate size random floats in the range [min, max].\"\n",
-    "    response_format: str = \"content_and_artifact\"\n",
-    "\n",
-    "    ndigits: int = 2\n",
-    "\n",
-    "    def _run(self, min: float, max: float, size: int) -> Tuple[str, List[float]]:\n",
-    "        range_ = max - min\n",
-    "        array = [\n",
-    "            round(min + (range_ * random.random()), ndigits=self.ndigits)\n",
-    "            for _ in range(size)\n",
-    "        ]\n",
-    "        content = f\"Generated {size} floats in [{min}, {max}], rounded to {self.ndigits} decimals.\"\n",
-    "        return content, array\n",
-    "\n",
-    "    # Optionally define an equivalent async method\n",
-    "\n",
-    "    # async def _arun(self, min: float, max: float, size: int) -> Tuple[str, List[float]]:\n",
-    "    #     ..."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "8c3d16f6-1c4a-48ab-b05a-38547c592e79",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "ToolMessage(content='Generated 3 floats in [0.1, 3.3333], rounded to 4 decimals.', name='generate_random_floats', tool_call_id='123', artifact=[1.4277, 0.7578, 2.4871])"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "rand_gen = GenerateRandomFloats(ndigits=4)\n",
-    "\n",
-    "rand_gen.invoke(\n",
-    "    {\n",
-    "        \"name\": \"generate_random_floats\",\n",
-    "        \"args\": {\"min\": 0.1, \"max\": 3.3333, \"size\": 3},\n",
-    "        \"id\": \"123\",\n",
-    "        \"type\": \"tool_call\",\n",
-    "    }\n",
-    ")"
-   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv-311",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "poetry-venv-311"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -962,7 +609,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.4"
   },
   "vscode": {
    "interpreter": {

docs/docs/how_to/document_loader_html.ipynb

@@ -23,12 +23,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install unstructured"
+    "%pip install \"unstructured[html]\""
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "7d167ca3-c7c7-4ef0-b509-080629f0f482",
    "metadata": {},
    "outputs": [
@@ -36,14 +36,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[Document(page_content='My First Heading\\n\\nMy first paragraph.', metadata={'source': '../../docs/integrations/document_loaders/example_data/fake-content.html'})]\n"
+      "[Document(page_content='My First Heading\\n\\nMy first paragraph.', metadata={'source': '../../../docs/integrations/document_loaders/example_data/fake-content.html'})]\n"
      ]
     }
    ],
    "source": [
     "from langchain_community.document_loaders import UnstructuredHTMLLoader\n",
     "\n",
-    "file_path = \"../../docs/integrations/document_loaders/example_data/fake-content.html\"\n",
+    "file_path = \"../../../docs/integrations/document_loaders/example_data/fake-content.html\"\n",
     "\n",
     "loader = UnstructuredHTMLLoader(file_path)\n",
     "data = loader.load()\n",
@@ -73,7 +73,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
    "id": "0a2050a8-6df6-4696-9889-ba367d6f9caa",
    "metadata": {},
    "outputs": [
@@ -81,7 +81,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[Document(page_content='\\nTest Title\\n\\n\\nMy First Heading\\nMy first paragraph.\\n\\n\\n', metadata={'source': '../../docs/integrations/document_loaders/example_data/fake-content.html', 'title': 'Test Title'})]\n"
+      "[Document(page_content='\\nTest Title\\n\\n\\nMy First Heading\\nMy first paragraph.\\n\\n\\n', metadata={'source': '../../../docs/integrations/document_loaders/example_data/fake-content.html', 'title': 'Test Title'})]\n"
      ]
     }
    ],
@@ -111,7 +111,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/document_loader_markdown.ipynb

@@ -21,12 +21,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
    "id": "c8b147fb-6877-4f7a-b2ee-ee971c7bc662",
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install \"unstructured[md]\""
+    "# !pip install \"unstructured[md]\""
    ]
   },
   {
@@ -39,7 +39,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "id": "80c50cc4-7ce9-4418-81b9-29c52c7b3627",
    "metadata": {},
    "outputs": [
@@ -62,7 +62,7 @@
     "from langchain_community.document_loaders import UnstructuredMarkdownLoader\n",
     "from langchain_core.documents import Document\n",
     "\n",
-    "markdown_path = \"../../../README.md\"\n",
+    "markdown_path = \"../../../../README.md\"\n",
     "loader = UnstructuredMarkdownLoader(markdown_path)\n",
     "\n",
     "data = loader.load()\n",
@@ -84,7 +84,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "id": "a986bbce-7fd3-41d1-bc47-49f9f57c7cd1",
    "metadata": {},
    "outputs": [
@@ -92,11 +92,11 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Number of documents: 66\n",
+      "Number of documents: 65\n",
       "\n",
-      "page_content='🦜️🔗 LangChain' metadata={'source': '../../../README.md', 'category_depth': 0, 'last_modified': '2024-06-28T15:20:01', 'languages': ['eng'], 'filetype': 'text/markdown', 'file_directory': '../../..', 'filename': 'README.md', 'category': 'Title'}\n",
+      "page_content='🦜️🔗 LangChain' metadata={'source': '../../../../README.md', 'last_modified': '2024-04-29T13:40:19', 'page_number': 1, 'languages': ['eng'], 'filetype': 'text/markdown', 'file_directory': '../../../..', 'filename': 'README.md', 'category': 'Title'}\n",
       "\n",
-      "page_content='⚡ Build context-aware reasoning applications ⚡' metadata={'source': '../../../README.md', 'last_modified': '2024-06-28T15:20:01', 'languages': ['eng'], 'parent_id': '200b8a7d0dd03f66e4f13456566d2b3a', 'filetype': 'text/markdown', 'file_directory': '../../..', 'filename': 'README.md', 'category': 'NarrativeText'}\n",
+      "page_content='⚡ Build context-aware reasoning applications ⚡' metadata={'source': '../../../../README.md', 'last_modified': '2024-04-29T13:40:19', 'page_number': 1, 'languages': ['eng'], 'parent_id': 'c3223b6f7100be08a78f1e8c0c28fde1', 'filetype': 'text/markdown', 'file_directory': '../../../..', 'filename': 'README.md', 'category': 'NarrativeText'}\n",
       "\n"
      ]
     }
@@ -121,7 +121,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 3,
    "id": "75abc139-3ded-4e8e-9f21-d0c8ec40fdfc",
    "metadata": {},
    "outputs": [
@@ -129,21 +129,13 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'ListItem', 'NarrativeText', 'Title'}\n"
+      "{'Title', 'NarrativeText', 'ListItem'}\n"
      ]
     }
    ],
    "source": [
     "print(set(document.metadata[\"category\"] for document in data))"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "223b4c11",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -162,7 +154,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/dynamic_chain.ipynb

@@ -58,8 +58,6 @@
     }
    ],
    "source": [
-    "from operator import itemgetter\n",
-    "\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "from langchain_core.runnables import Runnable, RunnablePassthrough, chain\n",
@@ -88,7 +86,7 @@
     "        # NOTE: This is returning another Runnable, not an actual output.\n",
     "        return contextualize_question\n",
     "    else:\n",
-    "        return RunnablePassthrough() | itemgetter(\"question\")\n",
+    "        return RunnablePassthrough()\n",
     "\n",
     "\n",
     "@chain\n",

docs/docs/how_to/embed_text.mdx

@@ -67,16 +67,15 @@ If you'd prefer not to set an environment variable you can pass the key in direc
 ```python
 from langchain_cohere import CohereEmbeddings
 
-embeddings_model = CohereEmbeddings(cohere_api_key="...", model='embed-english-v3.0')
+embeddings_model = CohereEmbeddings(cohere_api_key="...")
 ```
 
-Otherwise you can initialize simply as shown below:
+Otherwise you can initialize without any params:
 ```python
 from langchain_cohere import CohereEmbeddings
 
-embeddings_model = CohereEmbeddings(model='embed-english-v3.0')
+embeddings_model = CohereEmbeddings()
 ```
-Do note that it is mandatory to pass the model parameter while initializing the CohereEmbeddings class.
 
   </TabItem>
   <TabItem value="huggingface" label="Hugging Face">

docs/docs/how_to/hybrid.ipynb

@@ -9,13 +9,11 @@
    "source": [
     "# Hybrid Search\n",
     "\n",
-    "The standard search in LangChain is done by vector similarity. However, a number of vectorstores implementations (Astra DB, ElasticSearch, Neo4J, AzureSearch, Qdrant...) also support more advanced search combining vector similarity search and other search techniques (full-text, BM25, and so on). This is generally referred to as \"Hybrid\" search.\n",
+    "The standard search in LangChain is done by vector similarity. However, a number of vectorstores implementations (Astra DB, ElasticSearch, Neo4J, AzureSearch, ...) also support more advanced search combining vector similarity search and other search techniques (full-text, BM25, and so on). This is generally referred to as \"Hybrid\" search.\n",
     "\n",
     "**Step 1: Make sure the vectorstore you are using supports hybrid search**\n",
     "\n",
-    "At the moment, there is no unified way to perform hybrid search in LangChain. Each vectorstore may have their own way to do it. This is generally exposed as a keyword argument that is passed in during `similarity_search`.\n",
-    "\n",
-    "By reading the documentation or source code, figure out whether the vectorstore you are using supports hybrid search, and, if so, how to use it.\n",
+    "At the moment, there is no unified way to perform hybrid search in LangChain. Each vectorstore may have their own way to do it. This is generally exposed as a keyword argument that is passed in during `similarity_search`. By reading the documentation or source code, figure out whether the vectorstore you are using supports hybrid search, and, if so, how to use it.\n",
     "\n",
     "**Step 2: Add that parameter as a configurable field for the chain**\n",
     "\n",

docs/docs/how_to/index.mdx

@@ -31,8 +31,6 @@ This highlights functionality that is core to using LangChain.
 
 [**LCEL cheatsheet**](/docs/how_to/lcel_cheatsheet/): For a quick overview of how to use the main LCEL primitives.
 
-[**Migration guide**](/docs/versions/migrating_chains): For migrating legacy chain abstractions to LCEL.
-
 - [How to: chain runnables](/docs/how_to/sequence)
 - [How to: stream runnables](/docs/how_to/streaming)
 - [How to: invoke runnables in parallel](/docs/how_to/parallel/)
@@ -45,7 +43,6 @@ This highlights functionality that is core to using LangChain.
 - [How to: create a dynamic (self-constructing) chain](/docs/how_to/dynamic_chain/)
 - [How to: inspect runnables](/docs/how_to/inspect)
 - [How to: add fallbacks to a runnable](/docs/how_to/fallbacks)
-- [How to: pass runtime secrets to a runnable](/docs/how_to/runnable_runtime_secrets)
 
 ## Components
 
@@ -82,12 +79,12 @@ These are the core building blocks you can use when building applications.
 - [How to: stream a response back](/docs/how_to/chat_streaming)
 - [How to: track token usage](/docs/how_to/chat_token_usage_tracking)
 - [How to: track response metadata across providers](/docs/how_to/response_metadata)
+- [How to: let your end users choose their model](/docs/how_to/chat_models_universal_init/)
 - [How to: use chat model to call tools](/docs/how_to/tool_calling)
 - [How to: stream tool calls](/docs/how_to/tool_streaming)
-- [How to: handle rate limits](/docs/how_to/chat_model_rate_limiting)
 - [How to: few shot prompt tool behavior](/docs/how_to/tools_few_shot)
-- [How to: bind model-specific formatted tools](/docs/how_to/tools_model_specific)
-- [How to: force a specific tool call](/docs/how_to/tool_choice)
+- [How to: bind model-specific formated tools](/docs/how_to/tools_model_specific)
+- [How to: force specific tool call](/docs/how_to/tool_choice)
 - [How to: init any model in one line](/docs/how_to/chat_models_universal_init/)
 
 ### Messages
@@ -185,23 +182,17 @@ Indexing is the process of keeping your vectorstore in-sync with the underlying
 
 ### Tools
 
-LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to pass to the language model) as well as the implementation of the function to call. Refer [here](/docs/integrations/tools/) for a list of pre-buit tools. 
+LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to pass to the language model) as well as the implementation of the function to call.
 
-- [How to: create tools](/docs/how_to/custom_tools)
-- [How to: use built-in tools and toolkits](/docs/how_to/tools_builtin)
-- [How to: use chat models to call tools](/docs/how_to/tool_calling)
-- [How to: pass tool outputs to chat models](/docs/how_to/tool_results_pass_to_model)
+- [How to: create custom tools](/docs/how_to/custom_tools)
+- [How to: use built-in tools and built-in toolkits](/docs/how_to/tools_builtin)
+- [How to: use chat model to call tools](/docs/how_to/tool_calling)
+- [How to: pass tool results back to model](/docs/how_to/tool_results_pass_to_model)
+- [How to: add ad-hoc tool calling capability to LLMs and chat models](/docs/how_to/tools_prompting)
 - [How to: pass run time values to tools](/docs/how_to/tool_runtime)
-- [How to: add a human-in-the-loop for tools](/docs/how_to/tools_human)
-- [How to: handle tool errors](/docs/how_to/tools_error)
-- [How to: force models to call a tool](/docs/how_to/tool_choice)
-- [How to: disable parallel tool calling](/docs/how_to/tool_calling_parallel)
-- [How to: access the `RunnableConfig` from a tool](/docs/how_to/tool_configure)
-- [How to: stream events from a tool](/docs/how_to/tool_stream_events)
-- [How to: return artifacts from a tool](/docs/how_to/tool_artifacts/)
-- [How to: convert Runnables to tools](/docs/how_to/convert_runnable_to_tool)
-- [How to: add ad-hoc tool calling capability to models](/docs/how_to/tools_prompting)
-- [How to: pass in runtime secrets](/docs/how_to/runnable_runtime_secrets)
+- [How to: add a human in the loop to tool usage](/docs/how_to/tools_human)
+- [How to: handle errors when calling tools](/docs/how_to/tools_error)
+- [How to: disable parallel tool calling](/docs/how_to/tool_choice)
 
 ### Multimodal
 
@@ -213,7 +204,7 @@ LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to p
 
 :::note
 
-For in depth how-to guides for agents, please check out [LangGraph](https://langchain-ai.github.io/langgraph/) documentation.
+For in depth how-to guides for agents, please check out [LangGraph](https://github.com/langchain-ai/langgraph) documentation.
 
 :::
 
@@ -229,7 +220,6 @@ For in depth how-to guides for agents, please check out [LangGraph](https://lang
 - [How to: pass callbacks into a module constructor](/docs/how_to/callbacks_constructor)
 - [How to: create custom callback handlers](/docs/how_to/custom_callbacks)
 - [How to: use callbacks in async environments](/docs/how_to/callbacks_async)
-- [How to: dispatch custom callback events](/docs/how_to/callbacks_custom_events)
 
 ### Custom
 
@@ -242,7 +232,6 @@ All of LangChain components can easily be extended to support your own versions.
 - [How to: write a custom output parser class](/docs/how_to/output_parser_custom)
 - [How to: create custom callback handlers](/docs/how_to/custom_callbacks)
 - [How to: define a custom tool](/docs/how_to/custom_tools)
-- [How to: dispatch custom callback events](/docs/how_to/callbacks_custom_events)
 
 ### Serialization
 - [How to: save and load LangChain objects](/docs/how_to/serialization)

docs/docs/how_to/indexing.ipynb

@@ -60,7 +60,7 @@
     "   * document addition by id (`add_documents` method with `ids` argument)\n",
     "   * delete by id (`delete` method with `ids` argument)\n",
     "\n",
-    "Compatible Vectorstores: `Aerospike`, `AnalyticDB`, `AstraDB`, `AwaDB`, `AzureCosmosDBNoSqlVectorSearch`, `AzureCosmosDBVectorSearch`, `Bagel`, `Cassandra`, `Chroma`, `CouchbaseVectorStore`, `DashVector`, `DatabricksVectorSearch`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `HanaDB`, `Milvus`, `MongoDBAtlasVectorSearch`, `MyScale`, `OpenSearchVectorSearch`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `Rockset`, `ScaNN`, `SingleStoreDB`, `SupabaseVectorStore`, `SurrealDBStore`, `TimescaleVector`, `Vald`, `VDMS`, `Vearch`, `VespaStore`, `Weaviate`, `Yellowbrick`, `ZepVectorStore`, `TencentVectorDB`, `OpenSearchVectorSearch`.\n",
+    "Compatible Vectorstores: `Aerospike`, `AnalyticDB`, `AstraDB`, `AwaDB`, `AzureCosmosDBNoSqlVectorSearch`, `AzureCosmosDBVectorSearch`, `Bagel`, `Cassandra`, `Chroma`, `CouchbaseVectorStore`, `DashVector`, `DatabricksVectorSearch`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `HanaDB`, `Milvus`, `MyScale`, `OpenSearchVectorSearch`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `Rockset`, `ScaNN`, `SupabaseVectorStore`, `SurrealDBStore`, `TimescaleVector`, `Vald`, `VDMS`, `Vearch`, `VespaStore`, `Weaviate`, `Yellowbrick`, `ZepVectorStore`, `TencentVectorDB`, `OpenSearchVectorSearch`.\n",
     "  \n",
     "## Caution\n",
     "\n",

docs/docs/how_to/llm_caching.ipynb

@@ -15,23 +15,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "25b0b0fa",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain_openai langchain_community\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
-    "# Please manually enter OpenAI Key"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "0aa6d335",
    "metadata": {},
    "outputs": [],
@@ -39,14 +23,13 @@
     "from langchain.globals import set_llm_cache\n",
     "from langchain_openai import OpenAI\n",
     "\n",
-    "# To make the caching really obvious, lets use a slower and older model.\n",
-    "# Caching supports newer chat models as well.\n",
-    "llm = OpenAI(model=\"gpt-3.5-turbo-instruct\", n=2, best_of=2)"
+    "# To make the caching really obvious, lets use a slower model.\n",
+    "llm = OpenAI(model_name=\"gpt-3.5-turbo-instruct\", n=2, best_of=2)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 12,
    "id": "f168ff0d",
    "metadata": {},
    "outputs": [
@@ -54,17 +37,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 546 ms, sys: 379 ms, total: 925 ms\n",
-      "Wall time: 1.11 s\n"
+      "CPU times: user 13.7 ms, sys: 6.54 ms, total: 20.2 ms\n",
+      "Wall time: 330 ms\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "\"\\nWhy don't scientists trust atoms?\\n\\nBecause they make up everything!\""
+       "\"\\n\\nWhy couldn't the bicycle stand up by itself? Because it was two-tired!\""
       ]
      },
-     "execution_count": 3,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -76,12 +59,12 @@
     "set_llm_cache(InMemoryCache())\n",
     "\n",
     "# The first time, it is not yet in cache, so it should take longer\n",
-    "llm.invoke(\"Tell me a joke\")"
+    "llm.predict(\"Tell me a joke\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 13,
    "id": "ce7620fb",
    "metadata": {},
    "outputs": [
@@ -89,17 +72,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 192 µs, sys: 77 µs, total: 269 µs\n",
-      "Wall time: 270 µs\n"
+      "CPU times: user 436 µs, sys: 921 µs, total: 1.36 ms\n",
+      "Wall time: 1.36 ms\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "\"\\nWhy don't scientists trust atoms?\\n\\nBecause they make up everything!\""
+       "\"\\n\\nWhy couldn't the bicycle stand up by itself? Because it was two-tired!\""
       ]
      },
-     "execution_count": 4,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -107,7 +90,7 @@
    "source": [
     "%%time\n",
     "# The second time it is, so it goes faster\n",
-    "llm.invoke(\"Tell me a joke\")"
+    "llm.predict(\"Tell me a joke\")"
    ]
   },
   {
@@ -120,7 +103,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
    "id": "2e65de83",
    "metadata": {},
    "outputs": [],
@@ -130,7 +113,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 9,
    "id": "0be83715",
    "metadata": {},
    "outputs": [],
@@ -143,7 +126,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 10,
    "id": "9b427ce7",
    "metadata": {},
    "outputs": [
@@ -151,17 +134,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 10.6 ms, sys: 4.21 ms, total: 14.8 ms\n",
-      "Wall time: 851 ms\n"
+      "CPU times: user 29.3 ms, sys: 17.3 ms, total: 46.7 ms\n",
+      "Wall time: 364 ms\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "\"\\n\\nWhy don't scientists trust atoms?\\n\\nBecause they make up everything!\""
+       "'\\n\\nWhy did the tomato turn red?\\n\\nBecause it saw the salad dressing!'"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -169,12 +152,12 @@
    "source": [
     "%%time\n",
     "# The first time, it is not yet in cache, so it should take longer\n",
-    "llm.invoke(\"Tell me a joke\")"
+    "llm.predict(\"Tell me a joke\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 11,
    "id": "87f52611",
    "metadata": {},
    "outputs": [
@@ -182,17 +165,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 59.7 ms, sys: 63.6 ms, total: 123 ms\n",
-      "Wall time: 134 ms\n"
+      "CPU times: user 4.58 ms, sys: 2.23 ms, total: 6.8 ms\n",
+      "Wall time: 4.68 ms\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "\"\\n\\nWhy don't scientists trust atoms?\\n\\nBecause they make up everything!\""
+       "'\\n\\nWhy did the tomato turn red?\\n\\nBecause it saw the salad dressing!'"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -200,7 +183,7 @@
    "source": [
     "%%time\n",
     "# The second time it is, so it goes faster\n",
-    "llm.invoke(\"Tell me a joke\")"
+    "llm.predict(\"Tell me a joke\")"
    ]
   },
   {
@@ -228,7 +211,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

docs/docs/how_to/merge_message_runs.ipynb

@@ -63,38 +63,6 @@
     "Notice that if the contents of one of the messages to merge is a list of content blocks then the merged message will have a list of content blocks. And if both messages to merge have string contents then those are concatenated with a newline character."
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "11f7e8d3",
-   "metadata": {},
-   "source": [
-    "The `merge_message_runs` utility also works with messages composed together using the overloaded `+` operation:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b51855c5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "messages = (\n",
-    "    SystemMessage(\"you're a good assistant.\")\n",
-    "    + SystemMessage(\"you always respond with a joke.\")\n",
-    "    + HumanMessage([{\"type\": \"text\", \"text\": \"i wonder why it's called langchain\"}])\n",
-    "    + HumanMessage(\"and who is harrison chasing anyways\")\n",
-    "    + AIMessage(\n",
-    "        'Well, I guess they thought \"WordRope\" and \"SentenceString\" just didn\\'t have the same ring to it!'\n",
-    "    )\n",
-    "    + AIMessage(\n",
-    "        \"Why, he's probably chasing after the last cup of coffee in the office!\"\n",
-    "    )\n",
-    ")\n",
-    "\n",
-    "merged = merge_message_runs(messages)\n",
-    "print(\"\\n\\n\".join([repr(x) for x in merged]))"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "1b2eee74-71c8-4168-b968-bca580c25d18",

docs/docs/how_to/migrate_agent.ipynb

@@ -41,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "662fac50",
    "metadata": {},
    "outputs": [],
@@ -50,26 +50,6 @@
     "%pip install -U langgraph langchain langchain-openai"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "6f8ec38f",
-   "metadata": {},
-   "source": [
-    "Then, set your OpenAI API key."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "5fca87ef",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"sk-...\""
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "8e50635c-1671-46e6-be65-ce95f8167c2f",
@@ -82,7 +62,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "1e425fea-2796-4b99-bee6-9a6ffe73f756",
    "metadata": {},
    "outputs": [],
@@ -115,7 +95,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "03ea357c-9c36-4464-b2cc-27bd150e1554",
    "metadata": {},
    "outputs": [
@@ -126,7 +106,7 @@
        " 'output': 'The value of `magic_function(3)` is 5.'}"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -162,7 +142,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "53a3737a-d167-4255-89bf-20ac37f89a3e",
    "metadata": {},
    "outputs": [
@@ -173,7 +153,7 @@
        " 'output': 'The value of `magic_function(3)` is 5.'}"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -193,7 +173,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "74ecebe3-512e-409c-a661-bdd5b0a2b782",
    "metadata": {},
    "outputs": [
@@ -201,10 +181,10 @@
      "data": {
       "text/plain": [
        "{'input': 'Pardon?',\n",
-       " 'output': 'The value you get when you apply `magic_function` to the input 3 is 5.'}"
+       " 'output': 'The result of applying `magic_function` to the input 3 is 5.'}"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -243,7 +223,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "a9a11ccd-75e2-4c11-844d-a34870b0ff91",
    "metadata": {},
    "outputs": [
@@ -254,7 +234,7 @@
        " 'output': 'El valor de `magic_function(3)` es 5.'}"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -283,19 +263,19 @@
    "source": [
     "Now, let's pass a custom system message to [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent).\n",
     "\n",
-    "LangGraph's prebuilt `create_react_agent` does not take a prompt template directly as a parameter, but instead takes a [`state_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) parameter. This modifies the graph state before the llm is called, and can be one of four values:\n",
+    "LangGraph's prebuilt `create_react_agent` does not take a prompt template directly as a parameter, but instead takes a [`messages_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) parameter. This modifies messages before they are passed into the model, and can be one of four values:\n",
     "\n",
     "- A `SystemMessage`, which is added to the beginning of the list of messages.\n",
     "- A `string`, which is converted to a `SystemMessage` and added to the beginning of the list of messages.\n",
-    "- A `Callable`, which should take in full graph state. The output is then passed to the language model.\n",
-    "- Or a [`Runnable`](/docs/concepts/#langchain-expression-language-lcel), which should take in full graph state. The output is then passed to the language model.\n",
+    "- A `Callable`, which should take in a list of messages. The output is then passed to the language model.\n",
+    "- Or a [`Runnable`](/docs/concepts/#langchain-expression-language-lcel), which should should take in a list of messages. The output is then passed to the language model.\n",
     "\n",
     "Here's how it looks in action:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "id": "a9486805-676a-4d19-a5c4-08b41b172989",
    "metadata": {},
    "outputs": [],
@@ -307,7 +287,7 @@
     "# This could also be a SystemMessage object\n",
     "# system_message = SystemMessage(content=\"You are a helpful assistant. Respond only in Spanish.\")\n",
     "\n",
-    "app = create_react_agent(model, tools, state_modifier=system_message)\n",
+    "app = create_react_agent(model, tools, messages_modifier=system_message)\n",
     "\n",
     "\n",
     "messages = app.invoke({\"messages\": [(\"user\", query)]})"
@@ -324,7 +304,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "d369ab45-0c82-45f4-9d3e-8efb8dd47e2c",
    "metadata": {},
    "outputs": [
@@ -337,8 +317,8 @@
     }
    ],
    "source": [
+    "from langchain_core.messages import AnyMessage\n",
     "from langgraph.prebuilt import create_react_agent\n",
-    "from langgraph.prebuilt.chat_agent_executor import AgentState\n",
     "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
@@ -348,13 +328,13 @@
     ")\n",
     "\n",
     "\n",
-    "def _modify_state_messages(state: AgentState):\n",
-    "    return prompt.invoke({\"messages\": state[\"messages\"]}).to_messages() + [\n",
+    "def _modify_messages(messages: list[AnyMessage]):\n",
+    "    return prompt.invoke({\"messages\": messages}).to_messages() + [\n",
     "        (\"user\", \"Also say 'Pandamonium!' after the answer.\")\n",
     "    ]\n",
     "\n",
     "\n",
-    "app = create_react_agent(model, tools, state_modifier=_modify_state_messages)\n",
+    "app = create_react_agent(model, tools, messages_modifier=_modify_messages)\n",
     "\n",
     "\n",
     "messages = app.invoke({\"messages\": [(\"human\", query)]})\n",
@@ -371,23 +351,15 @@
    "id": "68df3a09",
    "metadata": {},
    "source": [
-    "## Memory"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "96e7ffc8",
-   "metadata": {},
-   "source": [
-    "### In LangChain\n",
+    "## Memory\n",
     "\n",
     "With LangChain's [AgentExecutor](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.iter), you could add chat [Memory](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.memory) so it can engage in a multi-turn conversation."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "b97beba5-8f74-430c-9399-91b77c8fa15c",
+   "execution_count": 8,
+   "id": "1fb52a2c",
    "metadata": {},
    "outputs": [
     {
@@ -396,7 +368,7 @@
      "text": [
       "Hi Polly! The output of the magic function for the input 3 is 5.\n",
       "---\n",
-      "Yes, your name is Polly!\n",
+      "Yes, I remember your name, Polly! How can I assist you further?\n",
       "---\n",
       "The output of the magic function for the input 3 is 5.\n"
      ]
@@ -404,14 +376,14 @@
    ],
    "source": [
     "from langchain.agents import AgentExecutor, create_tool_calling_agent\n",
-    "from langchain_core.chat_history import InMemoryChatMessageHistory\n",
+    "from langchain_community.chat_message_histories import ChatMessageHistory\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
     "from langchain_core.tools import tool\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
     "model = ChatOpenAI(model=\"gpt-4o\")\n",
-    "memory = InMemoryChatMessageHistory(session_id=\"test-session\")\n",
+    "memory = ChatMessageHistory(session_id=\"test-session\")\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
     "        (\"system\", \"You are a helpful assistant.\"),\n",
@@ -467,7 +439,7 @@
    "id": "c2a5a32f",
    "metadata": {},
    "source": [
-    "### In LangGraph\n",
+    "#### In LangGraph\n",
     "\n",
     "Memory is just [persistence](https://langchain-ai.github.io/langgraph/how-tos/persistence/), aka [checkpointing](https://langchain-ai.github.io/langgraph/reference/checkpoints/).\n",
     "\n",
@@ -476,23 +448,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
-   "id": "baca3dc6-678b-4509-9275-2fd653102898",
+   "execution_count": 9,
+   "id": "035e1253",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Hi Polly! The output of the magic_function for the input of 3 is 5.\n",
+      "Hi Polly! The output of the magic_function for the input 3 is 5.\n",
       "---\n",
       "Yes, your name is Polly!\n",
       "---\n",
-      "The output of the magic_function for the input of 3 was 5.\n"
+      "The output of the magic_function for the input 3 was 5.\n"
      ]
     }
    ],
    "source": [
+    "from langchain_core.messages import SystemMessage\n",
     "from langgraph.checkpoint import MemorySaver  # an in-memory checkpointer\n",
     "from langgraph.prebuilt import create_react_agent\n",
     "\n",
@@ -502,7 +475,7 @@
     "\n",
     "memory = MemorySaver()\n",
     "app = create_react_agent(\n",
-    "    model, tools, state_modifier=system_message, checkpointer=memory\n",
+    "    model, tools, messages_modifier=system_message, checkpointer=memory\n",
     ")\n",
     "\n",
     "config = {\"configurable\": {\"thread_id\": \"test-thread\"}}\n",
@@ -537,23 +510,21 @@
    "source": [
     "## Iterating through steps\n",
     "\n",
-    "### In LangChain\n",
-    "\n",
     "With LangChain's [AgentExecutor](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.iter), you could iterate over the steps using the [stream](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.stream) (or async `astream`) methods or the [iter](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.iter) method. LangGraph supports stepwise iteration using [stream](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.stream) "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "e62843c4-1107-41f0-a50b-aea256e28053",
+   "execution_count": 10,
+   "id": "d640feb3",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'actions': [ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-5664e138-7085-4da7-a49e-5656a87b8d78', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_1exy0rScfPmo4fy27FbQ5qJ2')], 'messages': [AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-5664e138-7085-4da7-a49e-5656a87b8d78', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'index': 0, 'type': 'tool_call_chunk'}])]}\n",
-      "{'steps': [AgentStep(action=ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-5664e138-7085-4da7-a49e-5656a87b8d78', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_1exy0rScfPmo4fy27FbQ5qJ2'), observation=5)], 'messages': [FunctionMessage(content='5', name='magic_function')]}\n",
+      "{'actions': [ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-c68fd76f-a3c3-4c3c-bfd7-748c171ed4b8', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'index': 0}])], tool_call_id='call_q9MgGFjqJbV2xSUX93WqxmOt')], 'messages': [AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-c68fd76f-a3c3-4c3c-bfd7-748c171ed4b8', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'index': 0}])]}\n",
+      "{'steps': [AgentStep(action=ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-c68fd76f-a3c3-4c3c-bfd7-748c171ed4b8', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'index': 0}])], tool_call_id='call_q9MgGFjqJbV2xSUX93WqxmOt'), observation=5)], 'messages': [FunctionMessage(content='5', name='magic_function')]}\n",
       "{'output': 'The value of `magic_function(3)` is 5.', 'messages': [AIMessage(content='The value of `magic_function(3)` is 5.')]}\n"
      ]
     }
@@ -597,30 +568,30 @@
    "id": "46ccbcbf",
    "metadata": {},
    "source": [
-    "### In LangGraph\n",
+    "#### In LangGraph\n",
     "\n",
     "In LangGraph, things are handled natively using [stream](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.graph.CompiledGraph.stream) or the asynchronous `astream` method."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
-   "id": "076ebc85-f804-4093-a25a-a16334c9898e",
+   "execution_count": 11,
+   "id": "86abbe07",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_my9rzFSKR4T1yYKwCsfbZB8A', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 61, 'total_tokens': 75}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_bc2a86f5f5', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-dd705555-8fae-4fb1-a033-5d99a23e3c22-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_my9rzFSKR4T1yYKwCsfbZB8A', 'type': 'tool_call'}], usage_metadata={'input_tokens': 61, 'output_tokens': 14, 'total_tokens': 75})]}}\n",
-      "{'tools': {'messages': [ToolMessage(content='5', name='magic_function', tool_call_id='call_my9rzFSKR4T1yYKwCsfbZB8A')]}}\n",
-      "{'agent': {'messages': [AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 84, 'total_tokens': 98}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'stop', 'logprobs': None}, id='run-698cad05-8cb2-4d08-8c2a-881e354f6cc7-0', usage_metadata={'input_tokens': 84, 'output_tokens': 14, 'total_tokens': 98})]}}\n"
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_yTjXXibj76tyFyPRa1soLo0S', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 70, 'total_tokens': 84}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-b275f314-c42e-4e77-9dec-5c23f7dbd53b-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_yTjXXibj76tyFyPRa1soLo0S'}])]}}\n",
+      "{'tools': {'messages': [ToolMessage(content='5', name='magic_function', id='41c5f227-528d-4483-a313-b03b23b1d327', tool_call_id='call_yTjXXibj76tyFyPRa1soLo0S')]}}\n",
+      "{'agent': {'messages': [AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 93, 'total_tokens': 107}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'stop', 'logprobs': None}, id='run-0ef12b6e-415d-4758-9b62-5e5e1b350072-0')]}}\n"
      ]
     }
    ],
    "source": [
+    "from langchain_core.messages import AnyMessage\n",
     "from langgraph.prebuilt import create_react_agent\n",
-    "from langgraph.prebuilt.chat_agent_executor import AgentState\n",
     "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
@@ -630,11 +601,12 @@
     ")\n",
     "\n",
     "\n",
-    "def _modify_state_messages(state: AgentState):\n",
-    "    return prompt.invoke({\"messages\": state[\"messages\"]}).to_messages()\n",
+    "def _modify_messages(messages: list[AnyMessage]):\n",
+    "    return prompt.invoke({\"messages\": messages}).to_messages()\n",
     "\n",
     "\n",
-    "app = create_react_agent(model, tools, state_modifier=_modify_state_messages)\n",
+    "app = create_react_agent(model, tools, messages_modifier=_modify_messages)\n",
+    "\n",
     "\n",
     "for step in app.stream({\"messages\": [(\"human\", query)]}, stream_mode=\"updates\"):\n",
     "    print(step)"
@@ -647,22 +619,20 @@
    "source": [
     "## `return_intermediate_steps`\n",
     "\n",
-    "### In LangChain\n",
-    "\n",
     "Setting this parameter on AgentExecutor allows users to access intermediate_steps, which pairs agent actions (e.g., tool invocations) with their outcomes.\n"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 12,
-   "id": "a2f720f3-c121-4be2-b498-92c16bb44b0a",
+   "id": "4eff44bc-a620-4c8a-97b1-268692a842bb",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[(ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_uPZ2D1Bo5mdED3gwgaeWURrf', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-a792db4a-278d-4090-82ae-904a30eada93', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_uPZ2D1Bo5mdED3gwgaeWURrf', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_uPZ2D1Bo5mdED3gwgaeWURrf', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_uPZ2D1Bo5mdED3gwgaeWURrf'), 5)]\n"
+      "[(ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_ABI4hftfEdnVgKyfF6OzZbca', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-837e794f-cfd8-40e0-8abc-4d98ced11b75', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_ABI4hftfEdnVgKyfF6OzZbca'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_ABI4hftfEdnVgKyfF6OzZbca', 'index': 0}])], tool_call_id='call_ABI4hftfEdnVgKyfF6OzZbca'), 5)]\n"
      ]
     }
    ],
@@ -677,24 +647,22 @@
    "id": "594f7567-302f-4fa8-85bb-025ac8322162",
    "metadata": {},
    "source": [
-    "### In LangGraph\n",
-    "\n",
     "By default the [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) in LangGraph appends all messages to the central state. Therefore, it is easy to see any intermediate steps by just looking at the full state."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "ef23117a-5ccb-42ce-80c3-ea49a9d3a942",
+   "id": "4f4364ea-dffe-4d25-bdce-ef7d0020b880",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'messages': [HumanMessage(content='what is the value of magic_function(3)?', id='cd7d0f49-a0e0-425a-b2b0-603a716058ed'),\n",
-       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_VfZ9287DuybOSrBsQH5X12xf', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a1e965cd-bf61-44f9-aec1-8aaecb80955f-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_VfZ9287DuybOSrBsQH5X12xf', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}),\n",
-       "  ToolMessage(content='5', name='magic_function', id='20d5c2fe-a5d8-47fa-9e04-5282642e2039', tool_call_id='call_VfZ9287DuybOSrBsQH5X12xf'),\n",
-       "  AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 78, 'total_tokens': 92}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'stop', 'logprobs': None}, id='run-abf9341c-ef41-4157-935d-a3be5dfa2f41-0', usage_metadata={'input_tokens': 78, 'output_tokens': 14, 'total_tokens': 92})]}"
+       "{'messages': [HumanMessage(content='what is the value of magic_function(3)?', id='0f63e437-c4d8-4da9-b6f5-b293ebfe4a64'),\n",
+       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_S96v28LlI6hNkQrNnIio0JPh', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-ffef7898-14b1-4537-ad90-7c000a8a5d25-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_S96v28LlI6hNkQrNnIio0JPh'}]),\n",
+       "  ToolMessage(content='5', name='magic_function', id='fbd9df4e-1dda-4d3e-9044-b001f7875476', tool_call_id='call_S96v28LlI6hNkQrNnIio0JPh'),\n",
+       "  AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 87, 'total_tokens': 101}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'stop', 'logprobs': None}, id='run-e5d94c54-d9f4-45cd-be8e-a9101a8d88d6-0')]}"
       ]
      },
      "execution_count": 13,
@@ -719,14 +687,16 @@
    "source": [
     "## `max_iterations`\n",
     "\n",
-    "### In LangChain\n",
+    "`AgentExecutor` implements a `max_iterations` parameter, whereas this is controlled via `recursion_limit` in LangGraph.\n",
     "\n",
-    "`AgentExecutor` implements a `max_iterations` parameter, allowing users to abort a run that exceeds a specified number of iterations."
+    "Note that in AgentExecutor, an \"iteration\" includes a full turn of tool invocation and execution. In LangGraph, each step contributes to the recursion limit, so we will need to multiply by two (and add one) to get equivalent results.\n",
+    "\n",
+    "If the recursion limit is reached, LangGraph raises a specific exception type, that we can catch and manage similarly to AgentExecutor."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 14,
    "id": "16f189a7-fc78-4cb5-aa16-a94ca06401a6",
    "metadata": {},
    "outputs": [],
@@ -742,7 +712,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 15,
    "id": "c96aefd7-6f6e-4670-aca6-1ac3d4e7871f",
    "metadata": {},
    "outputs": [
@@ -757,7 +727,11 @@
       "Invoking: `magic_function` with `{'input': '3'}`\n",
       "\n",
       "\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3mSorry, there was an error. Please try again.\u001b[0m\u001b[32;1m\u001b[1;3mParece que hubo un error al intentar calcular el valor de la función mágica. ¿Te gustaría que lo intente de nuevo?\u001b[0m\n",
+      "\u001b[0m\u001b[36;1m\u001b[1;3mSorry, there was an error. Please try again.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
+      "Invoking: `magic_function` with `{'input': '3'}`\n",
+      "responded: Parece que hubo un error al intentar obtener el valor de `magic_function(3)`. Permíteme intentarlo de nuevo.\n",
+      "\n",
+      "\u001b[0m\u001b[36;1m\u001b[1;3mSorry, there was an error. Please try again.\u001b[0m\u001b[32;1m\u001b[1;3mAún no puedo obtener el valor de `magic_function(3)`. ¿Hay algo más en lo que pueda ayudarte?\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -766,10 +740,10 @@
      "data": {
       "text/plain": [
        "{'input': 'what is the value of magic_function(3)?',\n",
-       " 'output': 'Parece que hubo un error al intentar calcular el valor de la función mágica. ¿Te gustaría que lo intente de nuevo?'}"
+       " 'output': 'Aún no puedo obtener el valor de `magic_function(3)`. ¿Hay algo más en lo que pueda ayudarte?'}"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -795,23 +769,9 @@
     "agent_executor.invoke({\"input\": query})"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "dd3a933f",
-   "metadata": {},
-   "source": [
-    "### In LangGraph\n",
-    "\n",
-    "In LangGraph this is controlled via `recursion_limit` configuration parameter.\n",
-    "\n",
-    "Note that in `AgentExecutor`, an \"iteration\" includes a full turn of tool invocation and execution. In LangGraph, each step contributes to the recursion limit, so we will need to multiply by two (and add one) to get equivalent results.\n",
-    "\n",
-    "If the recursion limit is reached, LangGraph raises a specific exception type, that we can catch and manage similarly to AgentExecutor."
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 16,
    "id": "b974a91f-6ae8-4644-83d9-73666258a6db",
    "metadata": {},
    "outputs": [
@@ -819,12 +779,12 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "content='what is the value of magic_function(3)?' id='74e2d5e8-2b59-4820-979c-8d11ecfc14c2'\n",
-      "content='' additional_kwargs={'tool_calls': [{'id': 'call_ihtrH6IG95pDXpKluIwAgi3J', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-5a35e465-8a08-43dd-ac8b-4a76dcace305-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_ihtrH6IG95pDXpKluIwAgi3J', 'type': 'tool_call'}] usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}\n",
-      "content='Sorry, there was an error. Please try again.' name='magic_function' id='8c37c19b-3586-46b1-aab9-a045786801a2' tool_call_id='call_ihtrH6IG95pDXpKluIwAgi3J'\n",
-      "content='It seems there was an error in processing the request. Let me try again.' additional_kwargs={'tool_calls': [{'id': 'call_iF0vYWAd6rfely0cXSqdMOnF', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 31, 'prompt_tokens': 88, 'total_tokens': 119}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-eb88ec77-d492-43a5-a5dd-4cefef9a6920-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_iF0vYWAd6rfely0cXSqdMOnF', 'type': 'tool_call'}] usage_metadata={'input_tokens': 88, 'output_tokens': 31, 'total_tokens': 119}\n",
-      "content='Sorry, there was an error. Please try again.' name='magic_function' id='c9ff261f-a0f1-4c92-a9f2-cd749f62d911' tool_call_id='call_iF0vYWAd6rfely0cXSqdMOnF'\n",
-      "content='I am currently unable to process the request with the input \"3\" for the `magic_function`. If you have any other questions or need assistance with something else, please let me know!' response_metadata={'token_usage': {'completion_tokens': 39, 'prompt_tokens': 141, 'total_tokens': 180}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'stop', 'logprobs': None} id='run-d42508aa-f286-4b57-80fb-f8a76736d470-0' usage_metadata={'input_tokens': 141, 'output_tokens': 39, 'total_tokens': 180}\n"
+      "('human', 'what is the value of magic_function(3)?')\n",
+      "content='' additional_kwargs={'tool_calls': [{'id': 'call_pFdKcCu5taDTtOOfX14vEDRp', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-25836468-ba7e-43be-a7cf-76bba06a2a08-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_pFdKcCu5taDTtOOfX14vEDRp'}]\n",
+      "content='Sorry, there was an error. Please try again.' name='magic_function' id='1a08b883-9c7b-4969-9e9b-67ce64cdcb5f' tool_call_id='call_pFdKcCu5taDTtOOfX14vEDRp'\n",
+      "content='It seems there was an error when trying to apply the magic function. Let me try again.' additional_kwargs={'tool_calls': [{'id': 'call_DA0lpDIkBFg2GHy4WsEcZG4K', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 34, 'prompt_tokens': 97, 'total_tokens': 131}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-d571b774-0ea3-4e35-8b7d-f32932c3f3cc-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_DA0lpDIkBFg2GHy4WsEcZG4K'}]\n",
+      "content='Sorry, there was an error. Please try again.' name='magic_function' id='0b45787b-c82a-487f-9a5a-de129c30460f' tool_call_id='call_DA0lpDIkBFg2GHy4WsEcZG4K'\n",
+      "content='It appears that there is a consistent issue when trying to apply the magic function to the input \"3.\" This could be due to various reasons, such as the input not being in the correct format or an internal error.\\n\\nIf you have any other questions or if there\\'s something else you\\'d like to try, please let me know!' response_metadata={'token_usage': {'completion_tokens': 66, 'prompt_tokens': 153, 'total_tokens': 219}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'stop', 'logprobs': None} id='run-50a962e6-21b7-4327-8dea-8e2304062627-0'\n"
      ]
     }
    ],
@@ -854,14 +814,12 @@
    "source": [
     "## `max_execution_time`\n",
     "\n",
-    "### In LangChain\n",
-    "\n",
     "`AgentExecutor` implements a `max_execution_time` parameter, allowing users to abort a run that exceeds a total time limit."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 17,
    "id": "4b8498fc-a7af-4164-a401-d8714f082306",
    "metadata": {},
    "outputs": [
@@ -888,7 +846,7 @@
        " 'output': 'Agent stopped due to max iterations.'}"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -922,8 +880,6 @@
    "id": "d02eb025",
    "metadata": {},
    "source": [
-    "### In LangGraph\n",
-    "\n",
     "With LangGraph's react agent, you can control timeouts on two levels. \n",
     "\n",
     "You can set a `step_timeout` to bound each **step**:"
@@ -931,7 +887,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 18,
    "id": "a2b29113-e6be-4f91-aa4c-5c63dea3e423",
    "metadata": {},
    "outputs": [
@@ -939,7 +895,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_FKiTkTd0Ffd4rkYSzERprf1M', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-b842f7b6-ec10-40f8-8c0e-baa220b77e91-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_FKiTkTd0Ffd4rkYSzERprf1M', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69})]}}\n",
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_HaQkeCwD5QskzJzFixCBacZ4', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-596c9200-771f-436d-8576-72fcb81620f1-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_HaQkeCwD5QskzJzFixCBacZ4'}])]}}\n",
       "------\n",
       "{'input': 'what is the value of magic_function(3)?', 'output': 'Agent stopped due to max iterations.'}\n"
      ]
@@ -970,7 +926,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 19,
    "id": "e9eb55f4-a321-4bac-b52d-9e43b411cf92",
    "metadata": {},
    "outputs": [
@@ -978,7 +934,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_WoOB8juagB08xrP38twYlYKR', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-73dee47e-30ab-42c9-bb0c-6f227cac96cd-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_WoOB8juagB08xrP38twYlYKR', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69})]}}\n",
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_4agJXUHtmHrOOMogjF6ZuzAv', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a1c77db7-405f-43d9-8d57-751f2ca1a58c-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_4agJXUHtmHrOOMogjF6ZuzAv'}])]}}\n",
       "------\n",
       "Task Cancelled.\n"
      ]
@@ -1012,14 +968,12 @@
    "source": [
     "## `early_stopping_method`\n",
     "\n",
-    "### In LangChain\n",
-    "\n",
     "With LangChain's [AgentExecutor](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.iter), you could configure an [early_stopping_method](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.early_stopping_method) to either return a string saying \"Agent stopped due to iteration limit or time limit.\" (`\"force\"`) or prompt the LLM a final time to respond (`\"generate\"`)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 20,
    "id": "3f6e2cf2",
    "metadata": {},
    "outputs": [
@@ -1074,14 +1028,14 @@
    "id": "706e05c4",
    "metadata": {},
    "source": [
-    "### In LangGraph\n",
+    "#### In LangGraph\n",
     "\n",
     "In LangGraph, you can explicitly handle the response behavior outside the agent, since the full state can be accessed."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 21,
    "id": "73cabbc4",
    "metadata": {},
    "outputs": [
@@ -1089,10 +1043,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "content='what is the value of magic_function(3)?' id='4fa7fbe5-758c-47a3-9268-717665d10680'\n",
-      "content='' additional_kwargs={'tool_calls': [{'id': 'call_ujE0IQBbIQnxcF9gsZXQfdhF', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-65d689aa-baee-4342-a5d2-048feefab418-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_ujE0IQBbIQnxcF9gsZXQfdhF', 'type': 'tool_call'}] usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}\n",
-      "content='Sorry there was an error, please try again.' name='magic_function' id='ef8ddf1d-9ad7-4ac0-b784-b673c4d94bbd' tool_call_id='call_ujE0IQBbIQnxcF9gsZXQfdhF'\n",
-      "content='It seems there was an issue with the previous attempt. Let me try that again.' additional_kwargs={'tool_calls': [{'id': 'call_GcsAfCFUHJ50BN2IOWnwTbQ7', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 32, 'prompt_tokens': 87, 'total_tokens': 119}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-54527c4b-8ff0-4ee8-8abf-224886bd222e-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_GcsAfCFUHJ50BN2IOWnwTbQ7', 'type': 'tool_call'}] usage_metadata={'input_tokens': 87, 'output_tokens': 32, 'total_tokens': 119}\n",
+      "('human', 'what is the value of magic_function(3)?')\n",
+      "content='' additional_kwargs={'tool_calls': [{'id': 'call_bTURmOn9C8zslmn0kMFeykIn', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-0844a504-7e6b-4ea6-a069-7017e38121ee-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_bTURmOn9C8zslmn0kMFeykIn'}]\n",
+      "content='Sorry there was an error, please try again.' name='magic_function' id='00d5386f-eb23-4628-9a29-d9ce6a7098cc' tool_call_id='call_bTURmOn9C8zslmn0kMFeykIn'\n",
+      "content='' additional_kwargs={'tool_calls': [{'id': 'call_JYqvvvWmXow2u012DuPoDHFV', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 96, 'total_tokens': 110}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-b73b1b1c-c829-4348-98cd-60b315c85448-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_JYqvvvWmXow2u012DuPoDHFV'}]\n",
       "{'input': 'what is the value of magic_function(3)?', 'output': 'Agent stopped due to max iterations.'}\n"
      ]
     }
@@ -1123,8 +1077,6 @@
    "source": [
     "## `trim_intermediate_steps`\n",
     "\n",
-    "### In LangChain\n",
-    "\n",
     "With LangChain's [AgentExecutor](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor), you could trim the intermediate steps of long-running agents using [trim_intermediate_steps](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.trim_intermediate_steps), which is either an integer (indicating the agent should keep the last N steps) or a custom function.\n",
     "\n",
     "For instance, we could trim the value so the agent only sees the most recent intermediate step."
@@ -1132,7 +1084,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 22,
    "id": "b94bb169",
    "metadata": {},
    "outputs": [
@@ -1228,14 +1180,14 @@
    "id": "3d450c5a",
    "metadata": {},
    "source": [
-    "### In LangGraph\n",
+    "#### In LangGraph\n",
     "\n",
-    "We can use the [`state_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) just as before when passing in [prompt templates](#prompt-templates)."
+    "We can use the [`messages_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) just as before when passing in [prompt templates](#prompt-templates)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 23,
    "id": "b309ba9a",
    "metadata": {},
    "outputs": [
@@ -1260,9 +1212,9 @@
     }
    ],
    "source": [
+    "from langchain_core.messages import AnyMessage\n",
     "from langgraph.errors import GraphRecursionError\n",
     "from langgraph.prebuilt import create_react_agent\n",
-    "from langgraph.prebuilt.chat_agent_executor import AgentState\n",
     "\n",
     "magic_step_num = 1\n",
     "\n",
@@ -1279,12 +1231,12 @@
     "tools = [magic_function]\n",
     "\n",
     "\n",
-    "def _modify_state_messages(state: AgentState):\n",
+    "def _modify_messages(messages: list[AnyMessage]):\n",
     "    # Give the agent amnesia, only keeping the original user query\n",
-    "    return [(\"system\", \"You are a helpful assistant\"), state[\"messages\"][0]]\n",
+    "    return [(\"system\", \"You are a helpful assistant\"), messages[0]]\n",
     "\n",
     "\n",
-    "app = create_react_agent(model, tools, state_modifier=_modify_state_messages)\n",
+    "app = create_react_agent(model, tools, messages_modifier=_modify_messages)\n",
     "\n",
     "try:\n",
     "    for step in app.stream({\"messages\": [(\"human\", query)]}, stream_mode=\"updates\"):\n",
@@ -1322,7 +1274,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.11.2"
   }
  },
  "nbformat": 4,

docs/docs/how_to/migrate_chains.ipynb

@@ -1,811 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "f331037f-be3f-4782-856f-d55dab952488",
-   "metadata": {},
-   "source": [
-    "# How to migrate chains to LCEL\n",
-    "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language](/docs/concepts#langchain-expression-language-lcel)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "LCEL is designed to streamline the process of building useful apps with LLMs and combining related components. It does this by providing:\n",
-    "\n",
-    "1. **A unified interface**: Every LCEL object implements the `Runnable` interface, which defines a common set of invocation methods (`invoke`, `batch`, `stream`, `ainvoke`, ...). This makes it possible to also automatically and consistently support useful operations like streaming of intermediate steps and batching, since every chain composed of LCEL objects is itself an LCEL object.\n",
-    "2. **Composition primitives**: LCEL provides a number of primitives that make it easy to compose chains, parallelize components, add fallbacks, dynamically configure chain internals, and more.\n",
-    "\n",
-    "LangChain maintains a number of legacy abstractions. Many of these can be reimplemented via short combinations of LCEL primitives. Doing so confers some general advantages:\n",
-    "\n",
-    "- The resulting chains typically implement the full `Runnable` interface, including streaming and asynchronous support where appropriate;\n",
-    "- The chains may be more easily extended or modified;\n",
-    "- The parameters of the chain are typically surfaced for easier customization (e.g., prompts) over previous versions, which tended to be subclasses and had opaque parameters and internals.\n",
-    "\n",
-    "The LCEL implementations can be slightly more verbose, but there are significant benefits in transparency and customizability.\n",
-    "\n",
-    "In this guide we review LCEL implementations of common legacy abstractions. Where appropriate, we link out to separate guides with more detail."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b99b47ec",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install --upgrade --quiet langchain-community langchain langchain-openai faiss-cpu"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "717c8673",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e3621b62-a037-42b8-8faa-59575608bb8b",
-   "metadata": {},
-   "source": [
-    "## `LLMChain`\n",
-    "<span data-heading-keywords=\"llmchain\"></span>\n",
-    "\n",
-    "[`LLMChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.llm.LLMChain.html) combined a prompt template, LLM, and output parser into a class.\n",
-    "\n",
-    "Some advantages of switching to the LCEL implementation are:\n",
-    "\n",
-    "- Clarity around contents and parameters. The legacy `LLMChain` contains a default output parser and other options.\n",
-    "- Easier streaming. `LLMChain` only supports streaming via callbacks.\n",
-    "- Easier access to raw message outputs if desired. `LLMChain` only exposes these via a parameter or via callback.\n",
-    "\n",
-    "import { ColumnContainer, Column } from \"@theme/Columns\";\n",
-    "\n",
-    "<ColumnContainer>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "e628905c-430e-4e4a-9d7c-c91d2f42052e",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'adjective': 'funny',\n",
-       " 'text': \"Why couldn't the bicycle find its way home?\\n\\nBecause it lost its bearings!\"}"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import LLMChain\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [(\"user\", \"Tell me a {adjective} joke\")],\n",
-    ")\n",
-    "\n",
-    "chain = LLMChain(llm=ChatOpenAI(), prompt=prompt)\n",
-    "\n",
-    "chain({\"adjective\": \"funny\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cdc3b527-c09e-4c77-9711-c3cc4506cd95",
-   "metadata": {},
-   "source": [
-    "\n",
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "0d2a7cf8-1bc7-405c-bb0d-f2ab2ba3b6ab",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Why couldn't the bicycle stand up by itself?\\n\\nBecause it was two tired!\""
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [(\"user\", \"Tell me a {adjective} joke\")],\n",
-    ")\n",
-    "\n",
-    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
-    "\n",
-    "chain.invoke({\"adjective\": \"funny\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3c0b0513-77b8-4371-a20e-3e487cec7e7f",
-   "metadata": {},
-   "source": [
-    "\n",
-    "</Column>\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "Note that `LLMChain` by default returns a `dict` containing both the input and the output. If this behavior is desired, we can replicate it using another LCEL primitive, [`RunnablePassthrough`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.passthrough.RunnablePassthrough.html):"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "529206c5-abbe-4213-9e6c-3b8586c8000d",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'adjective': 'funny',\n",
-       " 'text': \"Why couldn't the bicycle stand up by itself?\\n\\nBecause it was two tired!\"}"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "\n",
-    "outer_chain = RunnablePassthrough().assign(text=chain)\n",
-    "\n",
-    "outer_chain.invoke({\"adjective\": \"funny\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "29d2e26c-2854-4971-9c2b-613450993921",
-   "metadata": {},
-   "source": [
-    "See [this tutorial](/docs/tutorials/llm_chain) for more detail on building with prompt templates, LLMs, and output parsers."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "00df631d-5121-4918-94aa-b88acce9b769",
-   "metadata": {},
-   "source": [
-    "## `ConversationChain`\n",
-    "<span data-heading-keywords=\"conversationchain\"></span>\n",
-    "\n",
-    "[`ConversationChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.conversation.base.ConversationChain.html) incorporates a memory of previous messages to sustain a stateful conversation.\n",
-    "\n",
-    "Some advantages of switching to the LCEL implementation are:\n",
-    "\n",
-    "- Innate support for threads/separate sessions. To make this work with `ConversationChain`, you'd need to instantiate a separate memory class outside the chain.\n",
-    "- More explicit parameters. `ConversationChain` contains a hidden default prompt, which can cause confusion.\n",
-    "- Streaming support. `ConversationChain` only supports streaming via callbacks.\n",
-    "\n",
-    "`RunnableWithMessageHistory` implements sessions via configuration parameters. It should be instantiated with a callable that returns a [chat message history](https://api.python.langchain.com/en/latest/chat_history/langchain_core.chat_history.BaseChatMessageHistory.html). By default, it expects this function to take a single argument `session_id`.\n",
-    "\n",
-    "<ColumnContainer>\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "4f2cc6dc-d70a-4c13-9258-452f14290da6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'input': 'how are you?',\n",
-       " 'history': '',\n",
-       " 'response': \"Arrr, I be doin' well, me matey! Just sailin' the high seas in search of treasure and adventure. How can I assist ye today?\"}"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import ConversationChain\n",
-    "from langchain.memory import ConversationBufferMemory\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "template = \"\"\"\n",
-    "You are a pirate. Answer the following questions as best you can.\n",
-    "Chat history: {history}\n",
-    "Question: {input}\n",
-    "\"\"\"\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "\n",
-    "memory = ConversationBufferMemory()\n",
-    "\n",
-    "chain = ConversationChain(\n",
-    "    llm=ChatOpenAI(),\n",
-    "    memory=memory,\n",
-    "    prompt=prompt,\n",
-    ")\n",
-    "\n",
-    "chain({\"input\": \"how are you?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f8e36b0e-c7dc-4130-a51b-189d4b756c7f",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "173e1a9c-2a18-4669-b0de-136f39197786",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Arrr, I be doin' well, me heartie! Just sailin' the high seas in search of treasure and adventure. How be ye?\""
-      ]
-     },
-     "execution_count": 1,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.chat_history import InMemoryChatMessageHistory\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", \"You are a pirate. Answer the following questions as best you can.\"),\n",
-    "        (\"placeholder\", \"{chat_history}\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "history = InMemoryChatMessageHistory()\n",
-    "\n",
-    "\n",
-    "def get_history():\n",
-    "    return history\n",
-    "\n",
-    "\n",
-    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
-    "\n",
-    "wrapped_chain = RunnableWithMessageHistory(\n",
-    "    chain,\n",
-    "    get_history,\n",
-    "    history_messages_key=\"chat_history\",\n",
-    ")\n",
-    "\n",
-    "wrapped_chain.invoke({\"input\": \"how are you?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6b386ce6-895e-442c-88f3-7bec0ab9f401",
-   "metadata": {},
-   "source": [
-    "\n",
-    "</Column>\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "The above example uses the same `history` for all sessions. The example below shows how to use a different chat history for each session."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "4e05994f-1fbc-4699-bf2e-62cb0e4deeb8",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Ahoy matey! What can this old pirate do for ye today?'"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.chat_history import BaseChatMessageHistory\n",
-    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
-    "\n",
-    "store = {}\n",
-    "\n",
-    "\n",
-    "def get_session_history(session_id: str) -> BaseChatMessageHistory:\n",
-    "    if session_id not in store:\n",
-    "        store[session_id] = InMemoryChatMessageHistory()\n",
-    "    return store[session_id]\n",
-    "\n",
-    "\n",
-    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
-    "\n",
-    "wrapped_chain = RunnableWithMessageHistory(\n",
-    "    chain,\n",
-    "    get_session_history,\n",
-    "    history_messages_key=\"chat_history\",\n",
-    ")\n",
-    "\n",
-    "wrapped_chain.invoke(\n",
-    "    {\"input\": \"Hello!\"},\n",
-    "    config={\"configurable\": {\"session_id\": \"abc123\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c36ebecb",
-   "metadata": {},
-   "source": [
-    "See [this tutorial](/docs/tutorials/chatbot) for a more end-to-end guide on building with [`RunnableWithMessageHistory`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html).\n",
-    "\n",
-    "## `RetrievalQA`\n",
-    "<span data-heading-keywords=\"retrievalqa\"></span>\n",
-    "\n",
-    "The [`RetrievalQA`](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval_qa.base.RetrievalQA.html) chain performed natural-language question answering over a data source using retrieval-augmented generation.\n",
-    "\n",
-    "Some advantages of switching to the LCEL implementation are:\n",
-    "\n",
-    "- Easier customizability. Details such as the prompt and how documents are formatted are only configurable via specific parameters in the `RetrievalQA` chain.\n",
-    "- More easily return source documents.\n",
-    "- Support for runnable methods like streaming and async operations.\n",
-    "\n",
-    "Now let's look at them side-by-side. We'll use the same ingestion code to load a [blog post by Lilian Weng](https://lilianweng.github.io/posts/2023-06-23-agent/) on autonomous agents into a local vector store:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "1efbe16e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load docs\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
-    "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_openai.chat_models import ChatOpenAI\n",
-    "from langchain_openai.embeddings import OpenAIEmbeddings\n",
-    "\n",
-    "loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n",
-    "data = loader.load()\n",
-    "\n",
-    "# Split\n",
-    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
-    "all_splits = text_splitter.split_documents(data)\n",
-    "\n",
-    "# Store splits\n",
-    "vectorstore = FAISS.from_documents(documents=all_splits, embedding=OpenAIEmbeddings())\n",
-    "\n",
-    "# LLM\n",
-    "llm = ChatOpenAI()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c7e16438",
-   "metadata": {},
-   "source": [
-    "<ColumnContainer>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "43bf55a0",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'query': 'What are autonomous agents?',\n",
-       " 'result': 'Autonomous agents are LLM-empowered agents that handle autonomous design, planning, and performance of complex tasks, such as scientific experiments. These agents can browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other LLMs. They are capable of reasoning and planning ahead for complicated tasks by breaking them down into smaller steps.'}"
-      ]
-     },
-     "execution_count": 22,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.chains import RetrievalQA\n",
-    "\n",
-    "# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt\n",
-    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
-    "\n",
-    "qa_chain = RetrievalQA.from_llm(\n",
-    "    llm, retriever=vectorstore.as_retriever(), prompt=prompt\n",
-    ")\n",
-    "\n",
-    "qa_chain(\"What are autonomous agents?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "081948e5",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "9efcc931",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Autonomous agents are agents that can handle autonomous design, planning, and performance of complex tasks, such as scientific experiments. They can browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other language model models. These agents use reasoning steps to develop solutions to specific tasks, like creating a novel anticancer drug.'"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "\n",
-    "# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt\n",
-    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
-    "\n",
-    "\n",
-    "def format_docs(docs):\n",
-    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
-    "\n",
-    "\n",
-    "qa_chain = (\n",
-    "    {\n",
-    "        \"context\": vectorstore.as_retriever() | format_docs,\n",
-    "        \"question\": RunnablePassthrough(),\n",
-    "    }\n",
-    "    | prompt\n",
-    "    | llm\n",
-    "    | StrOutputParser()\n",
-    ")\n",
-    "\n",
-    "qa_chain.invoke(\"What are autonomous agents?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d6f44fe8",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "The LCEL implementation exposes the internals of what's happening around retrieving, formatting documents, and passing them through a prompt to the LLM, but it is more verbose. You can customize and wrap this composition logic in a helper function, or use the higher-level [`create_retrieval_chain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html) and [`create_stuff_documents_chain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.combine_documents.stuff.create_stuff_documents_chain.html) helper method:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "5fe42761",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'input': 'What are autonomous agents?',\n",
-       " 'context': [Document(page_content='Boiko et al. (2023) also looked into LLM-empowered agents for scientific discovery, to handle autonomous design, planning, and performance of complex scientific experiments. This agent can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs and leverage other LLMs.\\nFor example, when requested to \"develop a novel anticancer drug\", the model came up with the following reasoning steps:', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Weng, Lilian. (Jun 2023). “LLM-powered Autonomous Agents”. Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content=\"LLM Powered Autonomous Agents | Lil'Log\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nLil'Log\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nPosts\\n\\n\\n\\n\\nArchive\\n\\n\\n\\n\\nSearch\\n\\n\\n\\n\\nTags\\n\\n\\n\\n\\nFAQ\\n\\n\\n\\n\\nemojisearch.app\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n      LLM Powered Autonomous Agents\\n    \\nDate: June 23, 2023  |  Estimated Reading Time: 31 min  |  Author: Lilian Weng\\n\\n\\n \\n\\n\\nTable of Contents\\n\\n\\n\\nAgent System Overview\\n\\nComponent One: Planning\\n\\nTask Decomposition\\n\\nSelf-Reflection\\n\\n\\nComponent Two: Memory\\n\\nTypes of Memory\\n\\nMaximum Inner Product Search (MIPS)\", metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'})],\n",
-       " 'answer': 'Autonomous agents are entities that can operate independently, making decisions and taking actions without direct human intervention. These agents can perform tasks such as planning, executing complex experiments, and leveraging various tools and resources to achieve objectives. In the context provided, LLM-powered autonomous agents are specifically designed for scientific discovery, capable of handling tasks like designing novel anticancer drugs through reasoning steps.'}"
-      ]
-     },
-     "execution_count": 20,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.chains import create_retrieval_chain\n",
-    "from langchain.chains.combine_documents import create_stuff_documents_chain\n",
-    "\n",
-    "# See full prompt at https://smith.langchain.com/hub/langchain-ai/retrieval-qa-chat\n",
-    "retrieval_qa_chat_prompt = hub.pull(\"langchain-ai/retrieval-qa-chat\")\n",
-    "\n",
-    "combine_docs_chain = create_stuff_documents_chain(llm, retrieval_qa_chat_prompt)\n",
-    "rag_chain = create_retrieval_chain(vectorstore.as_retriever(), combine_docs_chain)\n",
-    "\n",
-    "rag_chain.invoke({\"input\": \"What are autonomous agents?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2772f4e9",
-   "metadata": {},
-   "source": [
-    "## `ConversationalRetrievalChain`\n",
-    "<span data-heading-keywords=\"conversationalretrievalchain\"></span>\n",
-    "\n",
-    "The [`ConversationalRetrievalChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.conversational_retrieval.base.ConversationalRetrievalChain.html) was an all-in one way that combined retrieval-augmented generation with chat history, allowing you to \"chat with\" your documents.\n",
-    "\n",
-    "Advantages of switching to the LCEL implementation are similar to the `RetrievalQA` section above:\n",
-    "\n",
-    "- Clearer internals. The `ConversationalRetrievalChain` chain hides an entire question rephrasing step which dereferences the initial query against the chat history.\n",
-    "  - This means the class contains two sets of configurable prompts, LLMs, etc.\n",
-    "- More easily return source documents.\n",
-    "- Support for runnable methods like streaming and async operations.\n",
-    "\n",
-    "Here are side-by-side implementations with custom prompts. We'll reuse the loaded documents and vector store from the previous section:"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8bc06416",
-   "metadata": {},
-   "source": [
-    "<ColumnContainer>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "id": "54eb9576",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'question': 'What are autonomous agents?',\n",
-       " 'chat_history': '',\n",
-       " 'answer': 'Autonomous agents are powered by Large Language Models (LLMs) to handle tasks like scientific discovery and complex experiments autonomously. These agents can browse the internet, read documentation, execute code, and leverage other LLMs to perform tasks. They can reason and plan ahead to decompose complicated tasks into manageable steps.'}"
-      ]
-     },
-     "execution_count": 31,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import ConversationalRetrievalChain\n",
-    "\n",
-    "condense_question_template = \"\"\"\n",
-    "Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.\n",
-    "\n",
-    "Chat History:\n",
-    "{chat_history}\n",
-    "Follow Up Input: {question}\n",
-    "Standalone question:\"\"\"\n",
-    "\n",
-    "condense_question_prompt = ChatPromptTemplate.from_template(condense_question_template)\n",
-    "\n",
-    "qa_template = \"\"\"\n",
-    "You are an assistant for question-answering tasks.\n",
-    "Use the following pieces of retrieved context to answer\n",
-    "the question. If you don't know the answer, say that you\n",
-    "don't know. Use three sentences maximum and keep the\n",
-    "answer concise.\n",
-    "\n",
-    "Chat History:\n",
-    "{chat_history}\n",
-    "\n",
-    "Other context:\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "\n",
-    "qa_prompt = ChatPromptTemplate.from_template(qa_template)\n",
-    "\n",
-    "convo_qa_chain = ConversationalRetrievalChain.from_llm(\n",
-    "    llm,\n",
-    "    vectorstore.as_retriever(),\n",
-    "    condense_question_prompt=condense_question_prompt,\n",
-    "    combine_docs_chain_kwargs={\n",
-    "        \"prompt\": qa_prompt,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "convo_qa_chain(\n",
-    "    {\n",
-    "        \"question\": \"What are autonomous agents?\",\n",
-    "        \"chat_history\": \"\",\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "43a8a23c",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "c884b138",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'input': 'What are autonomous agents?',\n",
-       " 'chat_history': [],\n",
-       " 'context': [Document(page_content='Boiko et al. (2023) also looked into LLM-empowered agents for scientific discovery, to handle autonomous design, planning, and performance of complex scientific experiments. This agent can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs and leverage other LLMs.\\nFor example, when requested to \"develop a novel anticancer drug\", the model came up with the following reasoning steps:', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Weng, Lilian. (Jun 2023). “LLM-powered Autonomous Agents”. Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Or\\n@article{weng2023agent,\\n  title   = \"LLM-powered Autonomous Agents\",\\n  author  = \"Weng, Lilian\",\\n  journal = \"lilianweng.github.io\",\\n  year    = \"2023\",\\n  month   = \"Jun\",\\n  url     = \"https://lilianweng.github.io/posts/2023-06-23-agent/\"\\n}\\nReferences#\\n[1] Wei et al. “Chain of thought prompting elicits reasoning in large language models.” NeurIPS 2022\\n[2] Yao et al. “Tree of Thoughts: Dliberate Problem Solving with Large Language Models.” arXiv preprint arXiv:2305.10601 (2023).', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'})],\n",
-       " 'answer': 'Autonomous agents are entities capable of acting independently, making decisions, and performing tasks without direct human intervention. These agents can interact with their environment, perceive information, and take actions based on their goals or objectives. They often use artificial intelligence techniques to navigate and accomplish tasks in complex or dynamic environments.'}"
-      ]
-     },
-     "execution_count": 25,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import create_history_aware_retriever, create_retrieval_chain\n",
-    "\n",
-    "condense_question_system_template = (\n",
-    "    \"Given a chat history and the latest user question \"\n",
-    "    \"which might reference context in the chat history, \"\n",
-    "    \"formulate a standalone question which can be understood \"\n",
-    "    \"without the chat history. Do NOT answer the question, \"\n",
-    "    \"just reformulate it if needed and otherwise return it as is.\"\n",
-    ")\n",
-    "\n",
-    "condense_question_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", condense_question_system_template),\n",
-    "        (\"placeholder\", \"{chat_history}\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "history_aware_retriever = create_history_aware_retriever(\n",
-    "    llm, vectorstore.as_retriever(), condense_question_prompt\n",
-    ")\n",
-    "\n",
-    "system_prompt = (\n",
-    "    \"You are an assistant for question-answering tasks. \"\n",
-    "    \"Use the following pieces of retrieved context to answer \"\n",
-    "    \"the question. If you don't know the answer, say that you \"\n",
-    "    \"don't know. Use three sentences maximum and keep the \"\n",
-    "    \"answer concise.\"\n",
-    "    \"\\n\\n\"\n",
-    "    \"{context}\"\n",
-    ")\n",
-    "\n",
-    "qa_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", system_prompt),\n",
-    "        (\"placeholder\", \"{chat_history}\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "qa_chain = create_stuff_documents_chain(llm, qa_prompt)\n",
-    "\n",
-    "convo_qa_chain = create_retrieval_chain(history_aware_retriever, qa_chain)\n",
-    "\n",
-    "convo_qa_chain.invoke(\n",
-    "    {\n",
-    "        \"input\": \"What are autonomous agents?\",\n",
-    "        \"chat_history\": [],\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b2717810",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "## Next steps\n",
-    "\n",
-    "You've now seen how to migrate existing usage of some legacy chains to LCEL.\n",
-    "\n",
-    "Next, check out the [LCEL conceptual docs](/docs/concepts/#langchain-expression-language-lcel) for more background information."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/how_to/pydantic_compatibility.md

@@ -1,97 +1,27 @@
 # How to use LangChain with different Pydantic versions
 
-- Pydantic v2 was released in June, 2023 (https://docs.pydantic.dev/2.0/blog/pydantic-v2-final/).
-- v2 contains has a number of breaking changes (https://docs.pydantic.dev/2.0/migration/).
-- Pydantic 1 End of Life was in June 2024. LangChain will be dropping support for Pydantic 1 in the near future,
-and likely migrating internally to Pydantic 2. The timeline is tentatively September. This change will be accompanied by a minor version bump in the main langchain packages to version 0.3.x.
+- Pydantic v2 was released in June, 2023 (https://docs.pydantic.dev/2.0/blog/pydantic-v2-final/)
+- v2 contains has a number of breaking changes (https://docs.pydantic.dev/2.0/migration/)
+- Pydantic v2 and v1 are under the same package name, so both versions cannot be installed at the same time
 
-As of `langchain>=0.0.267`, LangChain allows users to install either Pydantic V1 or V2.
+## LangChain Pydantic migration plan
 
-Internally, LangChain continues to use the [Pydantic V1](https://docs.pydantic.dev/latest/migration/#continue-using-pydantic-v1-features) via
-the v1 namespace of Pydantic 2.
+As of `langchain>=0.0.267`, LangChain will allow users to install either Pydantic V1 or V2. 
+   * Internally LangChain will continue to [use V1](https://docs.pydantic.dev/latest/migration/#continue-using-pydantic-v1-features).
+   * During this time, users can pin their pydantic version to v1 to avoid breaking changes, or start a partial
+   migration using pydantic v2 throughout their code, but avoiding mixing v1 and v2 code for LangChain (see below).
 
-Because Pydantic does not support mixing .v1 and .v2 objects, users should be aware of a number of issues
-when using LangChain with Pydantic.
-
-## 1. Passing Pydantic objects to LangChain APIs
-
-Most LangChain APIs that accept Pydantic objects have been updated to accept both Pydantic v1 and v2 objects.
-
-* Pydantic v1 objects correspond to subclasses of `pydantic.BaseModel` if `pydantic 1` is installed or subclasses of `pydantic.v1.BaseModel` if `pydantic 2` is installed.
-* Pydantic v2 objects correspond to subclasses of `pydantic.BaseModel` if `pydantic 2` is installed.
-
-
-| API                                    | Pydantic 1 | Pydantic 2                                                     |
-|----------------------------------------|------------|----------------------------------------------------------------|
-| `BaseChatModel.bind_tools`             | Yes        | langchain-core>=0.2.23, appropriate version of partner package |
-| `BaseChatModel.with_structured_output` | Yes        | langchain-core>=0.2.23, appropriate version of partner package |
-| `Tool.from_function`                   | Yes        | langchain-core>=0.2.23                                         |
-| `StructuredTool.from_function`         | Yes        | langchain-core>=0.2.23                                         |
-
-
-Partner packages that accept pydantic v2 objects via `bind_tools` or `with_structured_output` APIs:
-
-| Package Name        | pydantic v1 | pydantic v2 |
-|---------------------|-------------|-------------|
-| langchain-mistralai | Yes         | >=0.1.11    |
-| langchain-anthropic | Yes         | >=0.1.21    |
-| langchain-robocorp  | Yes         | >=0.0.10    |
-| langchain-openai    | Yes         | >=0.1.19    |
-| langchain-fireworks | Yes         | >=0.1.5     |
-
-Additional partner packages will be updated to accept Pydantic v2 objects in the future.
-
-If you are still seeing issues with these APIs or other APIs that accept Pydantic objects, please open an issue, and we'll
-address it.
-
-Example:
-
-Prior to `langchain-core<0.2.23`, use Pydantic v1 objects when passing to LangChain APIs.
-
-
-```python
-from langchain_openai import ChatOpenAI
-from pydantic.v1 import BaseModel # <-- Note v1 namespace
-
-class Person(BaseModel):
-    """Personal information"""
-    name: str
-    
-model = ChatOpenAI()
-model = model.with_structured_output(Person)
-
-model.invoke('Bob is a person.')
-```
-
-After `langchain-core>=0.2.23`, use either Pydantic v1 or v2 objects when passing to LangChain APIs.
-
-```python
-from langchain_openai import ChatOpenAI
-from pydantic import BaseModel
-
-class Person(BaseModel):
-    """Personal information"""
-    name: str
-    
-    
-model = ChatOpenAI()
-model = model.with_structured_output(Person)
-
-model.invoke('Bob is a person.')
-```
-
-## 2. Sub-classing LangChain models
-
-Because LangChain internally uses Pydantic v1, if you are sub-classing LangChain models, you should use Pydantic v1
-primitives.
+User can either pin to pydantic v1, and upgrade their code in one go once LangChain has migrated to v2 internally, or they can start a partial migration to v2, but must avoid mixing v1 and v2 code for LangChain.
 
+Below are two examples of showing how to avoid mixing pydantic v1 and v2 code in
+the case of inheritance and in the case of passing objects to LangChain.
 
 **Example 1: Extending via inheritance**
 
 **YES** 
 
 ```python
-from pydantic.v1 import validator
+from pydantic.v1 import root_validator, validator
 from langchain_core.tools import BaseTool
 
 class CustomTool(BaseTool): # BaseTool is v1 code
@@ -140,33 +70,38 @@ CustomTool(
 )
 ```
 
+**Example 2: Passing objects to LangChain**
 
-## 3. Disable run-time validation for LangChain objects used inside Pydantic v2 models
-
-e.g.,
+**YES**
 
 ```python
-from typing import Annotated
+from langchain_core.tools import Tool
+from pydantic.v1 import BaseModel, Field # <-- Uses v1 namespace
 
-from langchain_openai import ChatOpenAI # <-- ChatOpenAI uses pydantic v1
-from pydantic import BaseModel, SkipValidation
+class CalculatorInput(BaseModel):
+    question: str = Field()
 
-
-class Foo(BaseModel): # <-- BaseModel is from Pydantic v2
-    model: Annotated[ChatOpenAI, SkipValidation()]
-
-Foo(model=ChatOpenAI(api_key="hello"))
+Tool.from_function( # <-- tool uses v1 namespace
+    func=lambda question: 'hello',
+    name="Calculator",
+    description="useful for when you need to answer questions about math",
+    args_schema=CalculatorInput
+)
 ```
 
-## 4: LangServe cannot generate OpenAPI docs if running Pydantic 2
+**NO**
 
-If you are using Pydantic 2, you will not be able to generate OpenAPI docs using LangServe.
+```python
+from langchain_core.tools import Tool
+from pydantic import BaseModel, Field # <-- Uses v2 namespace
 
-If you need OpenAPI docs, your options are to either install Pydantic 1:
+class CalculatorInput(BaseModel):
+    question: str = Field()
 
-`pip install pydantic==1.10.17`
-
-or else to use the `APIHandler` object in LangChain to manually create the
-routes for your API.
-
-See: https://python.langchain.com/v0.2/docs/langserve/#pydantic
+Tool.from_function( # <-- tool uses v1 namespace
+    func=lambda question: 'hello',
+    name="Calculator",
+    description="useful for when you need to answer questions about math",
+    args_schema=CalculatorInput
+)
+```

docs/docs/how_to/runnable_runtime_secrets.ipynb

@@ -1,78 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "6fcd2994-0092-4fa3-9bb1-c9c84babadc5",
-   "metadata": {},
-   "source": [
-    "# How to pass runtime secrets to runnables\n",
-    "\n",
-    ":::info Requires `langchain-core >= 0.2.22`\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "We can pass in secrets to our runnables at runtime using the `RunnableConfig`. Specifically we can pass in secrets with a `__` prefix to the `configurable` field. This will ensure that these secrets aren't traced as part of the invocation:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "92e42e91-c277-49de-aa7a-dfb5c993c817",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "7"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.runnables import RunnableConfig\n",
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def foo(x: int, config: RunnableConfig) -> int:\n",
-    "    \"\"\"Sum x and a secret int\"\"\"\n",
-    "    return x + config[\"configurable\"][\"__top_secret_int\"]\n",
-    "\n",
-    "\n",
-    "foo.invoke({\"x\": 5}, {\"configurable\": {\"__top_secret_int\": 2, \"traced_key\": \"bar\"}})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ae3a4fb9-2ce7-46b2-b654-35dff0ae7197",
-   "metadata": {},
-   "source": [
-    "Looking at the LangSmith trace for this run, we can see that \"traced_key\" was recorded (as part of Metadata) while our secret int was not: https://smith.langchain.com/public/aa7e3289-49ca-422d-a408-f6b927210170/r"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "poetry-venv-311",
-   "language": "python",
-   "name": "poetry-venv-311"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/how_to/streaming.ipynb

@@ -452,7 +452,7 @@
    "source": [
     "#### Generator Functions\n",
     "\n",
-    "Let's fix the streaming using a generator function that can operate on the **input stream**.\n",
+    "Le'ts fix the streaming using a generator function that can operate on the **input stream**.\n",
     "\n",
     ":::{.callout-tip}\n",
     "A generator function (a function that uses `yield`) allows writing code that operates on **input streams**\n",

docs/docs/how_to/structured_output.ipynb

@@ -58,7 +58,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "6d55008f",
    "metadata": {},
    "outputs": [],
@@ -81,17 +81,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 38,
    "id": "070bf702",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Joke(setup='Why was the cat sitting on the computer?', punchline='Because it wanted to keep an eye on the mouse!', rating=8)"
+       "Joke(setup='Why was the cat sitting on the computer?', punchline='To keep an eye on the mouse!', rating=None)"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 38,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -514,49 +514,12 @@
     ")"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "91e95aa2",
-   "metadata": {},
-   "source": [
-    "### (Advanced) Raw outputs\n",
-    "\n",
-    "LLMs aren't perfect at generating structured output, especially as schemas become complex. You can avoid raising exceptions and handle the raw output yourself by passing `include_raw=True`. This changes the output format to contain the raw message output, the `parsed` value (if successful), and any resulting errors:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "10ed2842",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_ASK4EmZeZ69Fi3p554Mb4rWy', 'function': {'arguments': '{\"setup\":\"Why was the cat sitting on the computer?\",\"punchline\":\"Because it wanted to keep an eye on the mouse!\"}', 'name': 'Joke'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 36, 'prompt_tokens': 107, 'total_tokens': 143}, 'model_name': 'gpt-4-0125-preview', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-6491d35b-9164-4656-b75c-d7882cfb76cb-0', tool_calls=[{'name': 'Joke', 'args': {'setup': 'Why was the cat sitting on the computer?', 'punchline': 'Because it wanted to keep an eye on the mouse!'}, 'id': 'call_ASK4EmZeZ69Fi3p554Mb4rWy'}], usage_metadata={'input_tokens': 107, 'output_tokens': 36, 'total_tokens': 143}),\n",
-       " 'parsed': Joke(setup='Why was the cat sitting on the computer?', punchline='Because it wanted to keep an eye on the mouse!', rating=None),\n",
-       " 'parsing_error': None}"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "structured_llm = llm.with_structured_output(Joke, include_raw=True)\n",
-    "\n",
-    "structured_llm.invoke(\n",
-    "    \"Tell me a joke about cats, respond in JSON with `setup` and `punchline` keys\"\n",
-    ")"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "5e92a98a",
    "metadata": {},
    "source": [
-    "## Prompting and parsing model outputs directly\n",
+    "## Prompting and parsing model directly\n",
     "\n",
     "Not all models support `.with_structured_output()`, since not all models have tool calling or JSON mode support. For such models you'll need to directly prompt the model to use a specific format, and use an output parser to extract the structured response from the raw model output.\n",
     "\n",
@@ -824,9 +787,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "poetry-venv-2",
    "language": "python",
-   "name": "python3"
+   "name": "poetry-venv-2"
   },
   "language_info": {
    "codemirror_mode": {
@@ -838,7 +801,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/how_to/tool_artifacts.ipynb

@@ -1,396 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "503e36ae-ca62-4f8a-880c-4fe78ff5df93",
-   "metadata": {},
-   "source": [
-    "# How to return artifacts from a tool\n",
-    "\n",
-    ":::info Prerequisites\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "\n",
-    "- [ToolMessage](/docs/concepts/#toolmessage)\n",
-    "- [Tools](/docs/concepts/#tools)\n",
-    "- [Function/tool calling](/docs/concepts/#functiontool-calling)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Tools are utilities that can be called by a model, and whose outputs are designed to be fed back to a model. Sometimes, however, there are artifacts of a tool's execution that we want to make accessible to downstream components in our chain or agent, but that we don't want to expose to the model itself. For example if a tool returns a custom object, a dataframe or an image, we may want to pass some metadata about this output to the model without passing the actual output to the model. At the same time, we may want to be able to access this full output elsewhere, for example in downstream tools.\n",
-    "\n",
-    "The Tool and [ToolMessage](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolMessage.html) interfaces make it possible to distinguish between the parts of the tool output meant for the model (this is the ToolMessage.content) and those parts which are meant for use outside the model (ToolMessage.artifact).\n",
-    "\n",
-    ":::info Requires ``langchain-core >= 0.2.19``\n",
-    "\n",
-    "This functionality was added in ``langchain-core == 0.2.19``. Please make sure your package is up to date.\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "## Defining the tool\n",
-    "\n",
-    "If we want our tool to distinguish between message content and other artifacts, we need to specify `response_format=\"content_and_artifact\"` when defining our tool and make sure that we return a tuple of (content, artifact):"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "762b9199-885f-4946-9c98-cc54d72b0d76",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU \"langchain-core>=0.2.19\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "b9eb179d-1f41-4748-9866-b3d3e8c73cd0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import random\n",
-    "from typing import List, Tuple\n",
-    "\n",
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool(response_format=\"content_and_artifact\")\n",
-    "def generate_random_ints(min: int, max: int, size: int) -> Tuple[str, List[int]]:\n",
-    "    \"\"\"Generate size random ints in the range [min, max].\"\"\"\n",
-    "    array = [random.randint(min, max) for _ in range(size)]\n",
-    "    content = f\"Successfully generated array of {size} random ints in [{min}, {max}].\"\n",
-    "    return content, array"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0ab05d25-af4a-4e5a-afe2-f090416d7ee7",
-   "metadata": {},
-   "source": [
-    "## Invoking the tool with ToolCall\n",
-    "\n",
-    "If we directly invoke our tool with just the tool arguments, you'll notice that we only get back the content part of the Tool output:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "5e7d5e77-3102-4a59-8ade-e4e699dd1817",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Successfully generated array of 10 random ints in [0, 9].'"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Failed to batch ingest runs: LangSmithRateLimitError('Rate limit exceeded for https://api.smith.langchain.com/runs/batch. HTTPError(\\'429 Client Error: Too Many Requests for url: https://api.smith.langchain.com/runs/batch\\', \\'{\"detail\":\"Monthly unique traces usage limit exceeded\"}\\')')\n"
-     ]
-    }
-   ],
-   "source": [
-    "generate_random_ints.invoke({\"min\": 0, \"max\": 9, \"size\": 10})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "30db7228-f04c-489e-afda-9a572eaa90a1",
-   "metadata": {},
-   "source": [
-    "In order to get back both the content and the artifact, we need to invoke our model with a ToolCall (which is just a dictionary with \"name\", \"args\", \"id\" and \"type\" keys), which has additional info needed to generate a ToolMessage like the tool call ID:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "da1d939d-a900-4b01-92aa-d19011a6b034",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "ToolMessage(content='Successfully generated array of 10 random ints in [0, 9].', name='generate_random_ints', tool_call_id='123', artifact=[2, 8, 0, 6, 0, 0, 1, 5, 0, 0])"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "generate_random_ints.invoke(\n",
-    "    {\n",
-    "        \"name\": \"generate_random_ints\",\n",
-    "        \"args\": {\"min\": 0, \"max\": 9, \"size\": 10},\n",
-    "        \"id\": \"123\",  # required\n",
-    "        \"type\": \"tool_call\",  # required\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a3cfc03d-020b-42c7-b0f8-c824af19e45e",
-   "metadata": {},
-   "source": [
-    "## Using with a model\n",
-    "\n",
-    "With a [tool-calling model](/docs/how_to/tool_calling/), we can easily use a model to call our Tool and generate ToolMessages:\n",
-    "\n",
-    "```{=mdx}\n",
-    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
-    "\n",
-    "<ChatModelTabs\n",
-    "  customVarName=\"llm\"\n",
-    "/>\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "74de0286-b003-4b48-9cdd-ecab435515ca",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# | echo: false\n",
-    "# | output: false\n",
-    "\n",
-    "from langchain_anthropic import ChatAnthropic\n",
-    "\n",
-    "llm = ChatAnthropic(model=\"claude-3-5-sonnet-20240620\", temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "8a67424b-d19c-43df-ac7b-690bca42146c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[{'name': 'generate_random_ints',\n",
-       "  'args': {'min': 1, 'max': 24, 'size': 6},\n",
-       "  'id': 'toolu_01EtALY3Wz1DVYhv1TLvZGvE',\n",
-       "  'type': 'tool_call'}]"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_with_tools = llm.bind_tools([generate_random_ints])\n",
-    "\n",
-    "ai_msg = llm_with_tools.invoke(\"generate 6 positive ints less than 25\")\n",
-    "ai_msg.tool_calls"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "00c4e906-3ca8-41e8-a0be-65cb0db7d574",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "ToolMessage(content='Successfully generated array of 6 random ints in [1, 24].', name='generate_random_ints', tool_call_id='toolu_01EtALY3Wz1DVYhv1TLvZGvE', artifact=[2, 20, 23, 8, 1, 15])"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "generate_random_ints.invoke(ai_msg.tool_calls[0])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ddef2690-70de-4542-ab20-2337f77f3e46",
-   "metadata": {},
-   "source": [
-    "If we just pass in the tool call args, we'll only get back the content:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "f4a6c9a6-0ffc-4b0e-a59f-f3c3d69d824d",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Successfully generated array of 6 random ints in [1, 24].'"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "generate_random_ints.invoke(ai_msg.tool_calls[0][\"args\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "98d6443b-ff41-4d91-8523-b6274fc74ee5",
-   "metadata": {},
-   "source": [
-    "If we wanted to declaratively create a chain, we could do this:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "eb55ec23-95a4-464e-b886-d9679bf3aaa2",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[ToolMessage(content='Successfully generated array of 1 random ints in [1, 5].', name='generate_random_ints', tool_call_id='toolu_01FwYhnkwDPJPbKdGq4ng6uD', artifact=[5])]"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from operator import attrgetter\n",
-    "\n",
-    "chain = llm_with_tools | attrgetter(\"tool_calls\") | generate_random_ints.map()\n",
-    "\n",
-    "chain.invoke(\"give me a random number between 1 and 5\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4df46be2-babb-4bfe-a641-91cd3d03ffaf",
-   "metadata": {},
-   "source": [
-    "## Creating from BaseTool class\n",
-    "\n",
-    "If you want to create a BaseTool object directly, instead of decorating a function with `@tool`, you can do so like this:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "9a9129e1-6aee-4a10-ad57-62ef3bf0276c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.tools import BaseTool\n",
-    "\n",
-    "\n",
-    "class GenerateRandomFloats(BaseTool):\n",
-    "    name: str = \"generate_random_floats\"\n",
-    "    description: str = \"Generate size random floats in the range [min, max].\"\n",
-    "    response_format: str = \"content_and_artifact\"\n",
-    "\n",
-    "    ndigits: int = 2\n",
-    "\n",
-    "    def _run(self, min: float, max: float, size: int) -> Tuple[str, List[float]]:\n",
-    "        range_ = max - min\n",
-    "        array = [\n",
-    "            round(min + (range_ * random.random()), ndigits=self.ndigits)\n",
-    "            for _ in range(size)\n",
-    "        ]\n",
-    "        content = f\"Generated {size} floats in [{min}, {max}], rounded to {self.ndigits} decimals.\"\n",
-    "        return content, array\n",
-    "\n",
-    "    # Optionally define an equivalent async method\n",
-    "\n",
-    "    # async def _arun(self, min: float, max: float, size: int) -> Tuple[str, List[float]]:\n",
-    "    #     ..."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "d7322619-f420-4b29-8ee5-023e693d0179",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Generated 3 floats in [0.1, 3.3333], rounded to 4 decimals.'"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "rand_gen = GenerateRandomFloats(ndigits=4)\n",
-    "rand_gen.invoke({\"min\": 0.1, \"max\": 3.3333, \"size\": 3})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "0892f277-23a6-4bb8-a0e9-59f533ac9750",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "ToolMessage(content='Generated 3 floats in [0.1, 3.3333], rounded to 4 decimals.', name='generate_random_floats', tool_call_id='123', artifact=[1.5789, 2.464, 2.2719])"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "rand_gen.invoke(\n",
-    "    {\n",
-    "        \"name\": \"generate_random_floats\",\n",
-    "        \"args\": {\"min\": 0.1, \"max\": 3.3333, \"size\": 3},\n",
-    "        \"id\": \"123\",\n",
-    "        \"type\": \"tool_call\",\n",
-    "    }\n",
-    ")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "poetry-venv-311",
-   "language": "python",
-   "name": "poetry-venv-311"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/how_to/tool_calling.ipynb

@@ -17,41 +17,62 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# How to use chat models to call tools\n",
+    "# How to use a model to call tools\n",
     "\n",
     ":::info Prerequisites\n",
     "\n",
     "This guide assumes familiarity with the following concepts:\n",
-    "\n",
     "- [Chat models](/docs/concepts/#chat-models)\n",
     "- [LangChain Tools](/docs/concepts/#tools)\n",
-    "- [Tool calling](/docs/concepts/#functiontool-calling)\n",
     "- [Output parsers](/docs/concepts/#output-parsers)\n",
     "\n",
     ":::\n",
     "\n",
-    "[Tool calling](/docs/concepts/#functiontool-calling) allows a chat model to respond to a given prompt by \"calling a tool\".\n",
+    ":::info Tool calling vs function calling\n",
     "\n",
-    "Remember, while the name \"tool calling\" implies that the model is directly performing some action, this is actually not the case! The model only generates the arguments to a tool, and actually running the tool (or not) is up to the user.\n",
-    "\n",
-    "Tool calling is a general technique that generates structured output from a model, and you can use it even when you don't intend to invoke any tools. An example use-case of that is [extraction from unstructured text](/docs/tutorials/extraction/).\n",
-    "\n",
-    "![Diagram of calling a tool](/img/tool_call.png)\n",
-    "\n",
-    "If you want to see how to use the model-generated tool call to actually run a tool function [check out this guide](/docs/how_to/tool_results_pass_to_model/).\n",
-    "\n",
-    ":::note Supported models\n",
-    "\n",
-    "Tool calling is not universal, but is supported by many popular LLM providers, including [Anthropic](/docs/integrations/chat/anthropic/), \n",
-    "[Cohere](/docs/integrations/chat/cohere/), [Google](/docs/integrations/chat/google_vertex_ai_palm/), \n",
-    "[Mistral](/docs/integrations/chat/mistralai/), [OpenAI](/docs/integrations/chat/openai/), and even for locally-running models via [Ollama](/docs/integrations/chat/ollama/).\n",
-    "\n",
-    "You can find a [list of all models that support tool calling here](/docs/integrations/chat/).\n",
+    "We use the term tool calling interchangeably with function calling. Although\n",
+    "function calling is sometimes meant to refer to invocations of a single function,\n",
+    "we treat all models as though they can return multiple tool or function calls in \n",
+    "each message.\n",
     "\n",
     ":::\n",
     "\n",
-    "LangChain implements standard interfaces for defining tools, passing them to LLMs, and representing tool calls.\n",
-    "This guide will cover how to bind tools to an LLM, then invoke the LLM to generate these arguments."
+    ":::info Supported models\n",
+    "\n",
+    "You can find a [list of all models that support tool calling](/docs/integrations/chat/).\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "Tool calling allows a chat model to respond to a given prompt by \"calling a tool\".\n",
+    "While the name implies that the model is performing \n",
+    "some action, this is actually not the case! The model generates the \n",
+    "arguments to a tool, and actually running the tool (or not) is up to the user.\n",
+    "For example, if you want to [extract output matching some schema](/docs/how_to/structured_output/) \n",
+    "from unstructured text, you could give the model an \"extraction\" tool that takes \n",
+    "parameters matching the desired schema, then treat the generated output as your final \n",
+    "result.\n",
+    "\n",
+    ":::note\n",
+    "\n",
+    "If you only need formatted values, try the [.with_structured_output()](/docs/how_to/structured_output/#the-with_structured_output-method) chat model method as a simpler entrypoint.\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "However, tool calling goes beyond [structured output](/docs/how_to/structured_output/)\n",
+    "since you can pass responses from called tools back to the model to create longer interactions.\n",
+    "For instance, given a search engine tool, an LLM might handle a \n",
+    "query by first issuing a call to the search engine with arguments. The system calling the LLM can \n",
+    "receive the tool call, execute it, and return the output to the LLM to inform its \n",
+    "response. LangChain includes a suite of [built-in tools](/docs/integrations/tools/) \n",
+    "and supports several methods for defining your own [custom tools](/docs/how_to/custom_tools). \n",
+    "\n",
+    "Tool calling is not universal, but many popular LLM providers, including [Anthropic](https://www.anthropic.com/), \n",
+    "[Cohere](https://cohere.com/), [Google](https://cloud.google.com/vertex-ai), \n",
+    "[Mistral](https://mistral.ai/), [OpenAI](https://openai.com/), and others, \n",
+    "support variants of a tool calling feature.\n",
+    "\n",
+    "LangChain implements standard interfaces for defining tools, passing them to LLMs, \n",
+    "and representing tool calls. This guide and the other How-to pages in the Tool section will show you how to use tools with LangChain."
    ]
   },
   {
@@ -61,11 +82,12 @@
     "## Passing tools to chat models\n",
     "\n",
     "Chat models that support tool calling features implement a `.bind_tools` method, which \n",
-    "receives a list of functions, Pydantic models, or LangChain [tool objects](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html#langchain_core.tools.BaseTool) \n",
+    "receives a list of LangChain [tool objects](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html#langchain_core.tools.BaseTool) \n",
     "and binds them to the chat model in its expected format. Subsequent invocations of the \n",
     "chat model will include tool schemas in its calls to the LLM.\n",
     "\n",
-    "For example, below we implement simple tools for arithmetic:"
+    "For example, we can define the schema for custom tools using the `@tool` decorator \n",
+    "on Python functions:"
    ]
   },
   {
@@ -74,11 +96,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
     "def add(a: int, b: int) -> int:\n",
     "    \"\"\"Adds a and b.\"\"\"\n",
     "    return a + b\n",
     "\n",
     "\n",
+    "@tool\n",
     "def multiply(a: int, b: int) -> int:\n",
     "    \"\"\"Multiplies a and b.\"\"\"\n",
     "    return a * b\n",
@@ -91,9 +118,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "LangChain also implements a `@tool` decorator that allows for further control of the tool schema, such as tool names and argument descriptions. See the how-to guide [here](/docs/how_to/custom_tools/#creating-tools-from-functions) for details.\n",
-    "\n",
-    "We can also define the schemas without the accompanying functions using [Pydantic](https://docs.pydantic.dev):"
+    "Or below, we define the schema using [Pydantic](https://docs.pydantic.dev):"
    ]
   },
   {
@@ -128,8 +153,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "To actually bind those schemas to a chat model, we'll use the `.bind_tools()` method. This handles converting\n",
-    "the `Add` and `Multiply` schemas to the proper format for the model. The tool schema will then be passed it in each time the model is invoked.\n",
+    "We can bind them to chat models as follows:\n",
     "\n",
     "```{=mdx}\n",
     "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
@@ -138,7 +162,11 @@
     "  customVarName=\"llm\"\n",
     "  fireworksParams={`model=\"accounts/fireworks/models/firefunction-v1\", temperature=0`}\n",
     "/>\n",
-    "```"
+    "```\n",
+    "\n",
+    "We'll use the `.bind_tools()` method to handle converting\n",
+    "`Multiply` to the proper format for the model, then and bind it (i.e.,\n",
+    "passing it in each time the model is invoked)."
    ]
   },
   {
@@ -159,7 +187,7 @@
     "\n",
     "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
     "\n",
-    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)"
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
    ]
   },
   {
@@ -170,7 +198,7 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_wLTBasMppAwpdiA5CD92l9x7', 'function': {'arguments': '{\"a\":3,\"b\":12}', 'name': 'Multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 89, 'total_tokens': 107}, 'model_name': 'gpt-4o-mini-2024-07-18', 'system_fingerprint': 'fp_0f03d4f0ee', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-d3f36cca-f225-416f-ac16-0217046f0b38-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_wLTBasMppAwpdiA5CD92l9x7', 'type': 'tool_call'}], usage_metadata={'input_tokens': 89, 'output_tokens': 18, 'total_tokens': 107})"
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_g4RuAijtDcSeM96jXyCuiLSN', 'function': {'arguments': '{\"a\":3,\"b\":12}', 'name': 'Multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 95, 'total_tokens': 113}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-5157d15a-7e0e-4ab1-af48-3d98010cd152-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_g4RuAijtDcSeM96jXyCuiLSN'}], usage_metadata={'input_tokens': 95, 'output_tokens': 18, 'total_tokens': 113})"
       ]
      },
      "execution_count": 4,
@@ -190,7 +218,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "As we can see our LLM generated arguments to a tool! You can look at the docs for [bind_tools()](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.BaseChatOpenAI.html#langchain_openai.chat_models.base.BaseChatOpenAI.bind_tools) to learn about all the ways to customize how your LLM selects tools, as well as [this guide on how to force the LLM to call a tool](/docs/how_to/tool_choice/) rather than letting it decide."
+    "As we can see, even though the prompt didn't really suggest a tool call, our LLM made one since it was forced to do so. You can look at the docs for [bind_tools()](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.BaseChatOpenAI.html#langchain_openai.chat_models.base.BaseChatOpenAI.bind_tools) to learn about all the ways to customize how your LLM selects tools."
    ]
   },
   {
@@ -222,12 +250,10 @@
       "text/plain": [
        "[{'name': 'Multiply',\n",
        "  'args': {'a': 3, 'b': 12},\n",
-       "  'id': 'call_uqJsNrDJ8ZZnFa1BHHYAllEv',\n",
-       "  'type': 'tool_call'},\n",
+       "  'id': 'call_TnadLbWJu9HwDULRb51RNSMw'},\n",
        " {'name': 'Add',\n",
        "  'args': {'a': 11, 'b': 49},\n",
-       "  'id': 'call_ud1uHAaYsdpWuxugwoJ63BDs',\n",
-       "  'type': 'tool_call'}]"
+       "  'id': 'call_Q9vt1up05sOQScXvUYWzSpCg'}]"
       ]
      },
      "execution_count": 5,
@@ -286,17 +312,17 @@
    "source": [
     "## Next steps\n",
     "\n",
-    "Now you've learned how to bind tool schemas to a chat model and have the model call the tool.\n",
-    "\n",
-    "Next, check out this guide on actually using the tool by invoking the function and passing the results back to the model:\n",
+    "Now you've learned how to bind tool schemas to a chat model and to call those tools. Next, you can learn more about how to use tools:\n",
     "\n",
+    "- Few shot promting [with tools](/docs/how_to/tools_few_shot/)\n",
+    "- Stream [tool calls](/docs/how_to/tool_streaming/)\n",
+    "- Bind [model-specific tools](/docs/how_to/tools_model_specific/)\n",
+    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)\n",
     "- Pass [tool results back to model](/docs/how_to/tool_results_pass_to_model)\n",
     "\n",
     "You can also check out some more specific uses of tool calling:\n",
     "\n",
-    "- Few shot prompting [with tools](/docs/how_to/tools_few_shot/)\n",
-    "- Stream [tool calls](/docs/how_to/tool_streaming/)\n",
-    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)\n",
+    "- Building [tool-using chains and agents](/docs/how_to#tools)\n",
     "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
    ]
   }

docs/docs/how_to/tool_calling_parallel.ipynb

@@ -4,13 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# How to disable parallel tool calling\n",
-    "\n",
-    ":::info OpenAI-specific\n",
-    "\n",
-    "This API is currently only supported by OpenAI.\n",
-    "\n",
-    ":::\n",
+    "### Disabling parallel tool calling (OpenAI only)\n",
     "\n",
     "OpenAI tool calling performs tool calling in parallel by default. That means that if we ask a question like \"What is the weather in Tokyo, New York, and Chicago?\" and we have a tool for getting the weather, it will call the tool 3 times in parallel. We can force it to call only a single tool once by using the ``parallel_tool_call`` parameter."
    ]
@@ -105,24 +99,10 @@
   }
  ],
  "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
   "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "name": "python"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 2
 }

docs/docs/how_to/tool_choice.ipynb

@@ -4,15 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# How to force models to call a tool\n",
-    "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [Chat models](/docs/concepts/#chat-models)\n",
-    "- [LangChain Tools](/docs/concepts/#tools)\n",
-    "- [How to use a model to call tools](/docs/how_to/tool_calling)\n",
-    ":::\n",
+    "# How to force tool calling behavior\n",
     "\n",
     "In order to force our LLM to spelect a specific tool, we can use the `tool_choice` parameter to ensure certain behavior. First, let's define our model and tools:"
    ]
@@ -125,24 +117,10 @@
   }
  ],
  "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
   "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "name": "python"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 2
 }

docs/docs/how_to/tool_configure.ipynb

@@ -1,132 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to access the RunnableConfig from a tool\n",
-    "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "\n",
-    "- [LangChain Tools](/docs/concepts/#tools)\n",
-    "- [Custom tools](/docs/how_to/custom_tools)\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language-lcel)\n",
-    "- [Configuring runnable behavior](/docs/how_to/configure/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "If you have a tool  that call chat models, retrievers, or other runnables, you may want to access internal events from those runnables or configure them with additional properties. This guide shows you how to manually pass parameters properly so that you can do this using the `astream_events()` method.\n",
-    "\n",
-    "Tools are runnables, and you can treat them the same way as any other runnable at the interface level - you can call `invoke()`, `batch()`, and `stream()` on them as normal. However, when writing custom tools, you may want to invoke other runnables like chat models or retrievers. In order to properly trace and configure those sub-invocations, you'll need to manually access and pass in the tool's current [`RunnableConfig`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.config.RunnableConfig.html) object. This guide show you some examples of how to do that.\n",
-    "\n",
-    ":::caution Compatibility\n",
-    "\n",
-    "This guide requires `langchain-core>=0.2.16`.\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "## Inferring by parameter type\n",
-    "\n",
-    "To access reference the active config object from your custom tool, you'll need to add a parameter to your tool's signature typed as `RunnableConfig`. When you invoke your tool, LangChain will inspect your tool's signature, look for a parameter typed as `RunnableConfig`, and if it exists, populate that parameter with the correct value.\n",
-    "\n",
-    "**Note:** The actual name of the parameter doesn't matter, only the typing.\n",
-    "\n",
-    "To illustrate this, define a custom tool that takes a two parameters - one typed as a string, the other typed as `RunnableConfig`:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain_core"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.runnables import RunnableConfig\n",
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "async def reverse_tool(text: str, special_config_param: RunnableConfig) -> str:\n",
-    "    \"\"\"A test tool that combines input text with a configurable parameter.\"\"\"\n",
-    "    return (text + special_config_param[\"configurable\"][\"additional_field\"])[::-1]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Then, if we invoke the tool with a `config` containing a `configurable` field, we can see that `additional_field` is passed through correctly:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'321cba'"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "await reverse_tool.ainvoke(\n",
-    "    {\"text\": \"abc\"}, config={\"configurable\": {\"additional_field\": \"123\"}}\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You've now seen how to configure and stream events from within a tool. Next, check out the following guides for more on using tools:\n",
-    "\n",
-    "- [Stream events from child runs within a custom tool](/docs/how_to/tool_stream_events/)\n",
-    "- Pass [tool results back to a model](/docs/how_to/tool_results_pass_to_model)\n",
-    "\n",
-    "You can also check out some more specific uses of tool calling:\n",
-    "\n",
-    "- Building [tool-using chains and agents](/docs/how_to#tools)\n",
-    "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

docs/docs/how_to/tool_results_pass_to_model.ipynb

@@ -4,63 +4,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# How to pass tool outputs to chat models\n",
+    "# How to pass tool outputs to the model\n",
     "\n",
-    ":::info Prerequisites\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "\n",
-    "- [LangChain Tools](/docs/concepts/#tools)\n",
-    "- [Function/tool calling](/docs/concepts/#functiontool-calling)\n",
-    "- [Using chat models to call tools](/docs/how_to/tool_calling)\n",
-    "- [Defining custom tools](/docs/how_to/custom_tools/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Some models are capable of [**tool calling**](/docs/concepts/#functiontool-calling) - generating arguments that conform to a specific user-provided schema. This guide will demonstrate how to use those tool cals to actually call a function and properly pass the results back to the model.\n",
-    "\n",
-    "![Diagram of a tool call invocation](/img/tool_invocation.png)\n",
-    "\n",
-    "![Diagram of a tool call result](/img/tool_results.png)\n",
-    "\n",
-    "First, let's define our tools and our model:"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "```{=mdx}\n",
-    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
-    "\n",
-    "<ChatModelTabs\n",
-    "  customVarName=\"llm\"\n",
-    "  fireworksParams={`model=\"accounts/fireworks/models/firefunction-v1\", temperature=0`}\n",
-    "/>\n",
-    "```"
+    "If we're using the model-generated tool invocations to actually call tools and want to pass the tool results back to the model, we can do so using `ToolMessage`s. First, let's define our tools and our model."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# | output: false\n",
-    "# | echo: false\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
-    "\n",
-    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -79,8 +30,23 @@
     "    return a * b\n",
     "\n",
     "\n",
-    "tools = [add, multiply]\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
     "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
     "llm_with_tools = llm.bind_tools(tools)"
    ]
   },
@@ -88,102 +54,55 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Now, let's get the model to call a tool. We'll add it to a list of messages that we'll treat as conversation history:"
+    "Now we can use ``ToolMessage`` to pass back the output of the tool calls to the model."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[{'name': 'multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_GPGPE943GORirhIAYnWv00rK', 'type': 'tool_call'}, {'name': 'add', 'args': {'a': 11, 'b': 49}, 'id': 'call_dm8o64ZrY3WFZHAvCh1bEJ6i', 'type': 'tool_call'}]\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "query = \"What is 3 * 12? Also, what is 11 + 49?\"\n",
-    "\n",
-    "messages = [HumanMessage(query)]\n",
-    "\n",
-    "ai_msg = llm_with_tools.invoke(messages)\n",
-    "\n",
-    "print(ai_msg.tool_calls)\n",
-    "\n",
-    "messages.append(ai_msg)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Next let's invoke the tool functions using the args the model populated!\n",
-    "\n",
-    "Conveniently, if we invoke a LangChain `Tool` with a `ToolCall`, we'll automatically get back a `ToolMessage` that can be fed back to the model:\n",
-    "\n",
-    ":::caution Compatibility\n",
-    "\n",
-    "This functionality was added in `langchain-core == 0.2.19`. Please make sure your package is up to date.\n",
-    "\n",
-    "If you are on earlier versions of `langchain-core`, you will need to extract the `args` field from the tool and construct a `ToolMessage` manually.\n",
-    "\n",
-    ":::"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
        "[HumanMessage(content='What is 3 * 12? Also, what is 11 + 49?'),\n",
-       " AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_loT2pliJwJe3p7nkgXYF48A1', 'function': {'arguments': '{\"a\": 3, \"b\": 12}', 'name': 'multiply'}, 'type': 'function'}, {'id': 'call_bG9tYZCXOeYDZf3W46TceoV4', 'function': {'arguments': '{\"a\": 11, \"b\": 49}', 'name': 'add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 50, 'prompt_tokens': 87, 'total_tokens': 137}, 'model_name': 'gpt-4o-mini-2024-07-18', 'system_fingerprint': 'fp_661538dc1f', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-e3db3c46-bf9e-478e-abc1-dc9a264f4afe-0', tool_calls=[{'name': 'multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_loT2pliJwJe3p7nkgXYF48A1', 'type': 'tool_call'}, {'name': 'add', 'args': {'a': 11, 'b': 49}, 'id': 'call_bG9tYZCXOeYDZf3W46TceoV4', 'type': 'tool_call'}], usage_metadata={'input_tokens': 87, 'output_tokens': 50, 'total_tokens': 137}),\n",
-       " ToolMessage(content='36', name='multiply', tool_call_id='call_loT2pliJwJe3p7nkgXYF48A1'),\n",
-       " ToolMessage(content='60', name='add', tool_call_id='call_bG9tYZCXOeYDZf3W46TceoV4')]"
+       " AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_svc2GLSxNFALbaCAbSjMI9J8', 'function': {'arguments': '{\"a\": 3, \"b\": 12}', 'name': 'Multiply'}, 'type': 'function'}, {'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh', 'function': {'arguments': '{\"a\": 11, \"b\": 49}', 'name': 'Add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 50, 'prompt_tokens': 105, 'total_tokens': 155}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a79ad1dd-95f1-4a46-b688-4c83f327a7b3-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_svc2GLSxNFALbaCAbSjMI9J8'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh'}]),\n",
+       " ToolMessage(content='36', tool_call_id='call_svc2GLSxNFALbaCAbSjMI9J8'),\n",
+       " ToolMessage(content='60', tool_call_id='call_r8jxte3zW6h3MEGV3zH2qzFh')]"
       ]
      },
-     "execution_count": 4,
      "metadata": {},
-     "output_type": "execute_result"
+     "output_type": "display_data"
     }
    ],
    "source": [
+    "from langchain_core.messages import HumanMessage, ToolMessage\n",
+    "\n",
+    "query = \"What is 3 * 12? Also, what is 11 + 49?\"\n",
+    "\n",
+    "messages = [HumanMessage(query)]\n",
+    "ai_msg = llm_with_tools.invoke(messages)\n",
+    "messages.append(ai_msg)\n",
     "for tool_call in ai_msg.tool_calls:\n",
     "    selected_tool = {\"add\": add, \"multiply\": multiply}[tool_call[\"name\"].lower()]\n",
-    "    tool_msg = selected_tool.invoke(tool_call)\n",
-    "    messages.append(tool_msg)\n",
-    "\n",
+    "    tool_output = selected_tool.invoke(tool_call[\"args\"])\n",
+    "    messages.append(ToolMessage(tool_output, tool_call_id=tool_call[\"id\"]))\n",
     "messages"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And finally, we'll invoke the model with the tool results. The model will use this information to generate a final answer to our original query:"
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='The result of \\\\(3 \\\\times 12\\\\) is 36, and the result of \\\\(11 + 49\\\\) is 60.', response_metadata={'token_usage': {'completion_tokens': 31, 'prompt_tokens': 153, 'total_tokens': 184}, 'model_name': 'gpt-4o-mini-2024-07-18', 'system_fingerprint': 'fp_661538dc1f', 'finish_reason': 'stop', 'logprobs': None}, id='run-87d1ef0a-1223-4bb3-9310-7b591789323d-0', usage_metadata={'input_tokens': 153, 'output_tokens': 31, 'total_tokens': 184})"
+       "AIMessage(content='3 * 12 is 36 and 11 + 49 is 60.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 171, 'total_tokens': 189}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'stop', 'logprobs': None}, id='run-20b52149-e00d-48ea-97cf-f8de7a255f8c-0')"
       ]
      },
-     "execution_count": 5,
      "metadata": {},
-     "output_type": "execute_result"
+     "output_type": "display_data"
     }
    ],
    "source": [
@@ -194,39 +113,15 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Note that each `ToolMessage` must include a `tool_call_id` that matches an `id` in the original tool calls that the model generates. This helps the model match tool responses with tool calls.\n",
-    "\n",
-    "Tool calling agents, like those in [LangGraph](https://langchain-ai.github.io/langgraph/tutorials/introduction/), use this basic flow to answer queries and solve tasks.\n",
-    "\n",
-    "## Related\n",
-    "\n",
-    "- [LangGraph quickstart](https://langchain-ai.github.io/langgraph/tutorials/introduction/)\n",
-    "- Few shot prompting [with tools](/docs/how_to/tools_few_shot/)\n",
-    "- Stream [tool calls](/docs/how_to/tool_streaming/)\n",
-    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)\n",
-    "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
+    "Note that we pass back the same `id` in the `ToolMessage` as the what we receive from the model in order to help the model match tool responses with tool calls."
    ]
   }
  ],
  "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
   "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "name": "python"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 2
 }

docs/docs/how_to/tool_runtime.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# How to pass run time values to tools\n",
+    "# How to pass run time values to a tool\n",
     "\n",
     ":::info Prerequisites\n",
     "\n",
@@ -12,28 +12,29 @@
     "- [Chat models](/docs/concepts/#chat-models)\n",
     "- [LangChain Tools](/docs/concepts/#tools)\n",
     "- [How to create tools](/docs/how_to/custom_tools)\n",
-    "- [How to use a model to call tools](/docs/how_to/tool_calling)\n",
+    "- [How to use a model to call tools](https://python.langchain.com/v0.2/docs/how_to/tool_calling)\n",
     ":::\n",
     "\n",
-    ":::info Using with LangGraph\n",
+    ":::{.callout-info} Supported models\n",
+    "\n",
+    "This how-to guide uses models with native tool calling capability.\n",
+    "You can find a [list of all models that support tool calling](/docs/integrations/chat/).\n",
+    "\n",
+    ":::\n",
+    "\n",
+    ":::{.callout-info} Using with LangGraph\n",
     "\n",
     "If you're using LangGraph, please refer to [this how-to guide](https://langchain-ai.github.io/langgraph/how-tos/pass-run-time-values-to-tools/)\n",
     "which shows how to create an agent that keeps track of a given user's favorite pets.\n",
     ":::\n",
     "\n",
-    ":::caution Added in `langchain-core==0.2.21`\n",
-    "\n",
-    "Must have `langchain-core>=0.2.21` to use this functionality.\n",
-    "\n",
-    ":::\n",
-    "\n",
     "You may need to bind values to a tool that are only known at runtime. For example, the tool logic may require using the ID of the user who made the request.\n",
     "\n",
     "Most of the time, such values should not be controlled by the LLM. In fact, allowing the LLM to control the user ID may lead to a security risk.\n",
     "\n",
     "Instead, the LLM should only control the parameters of the tool that are meant to be controlled by the LLM, while other parameters (such as user ID) should be fixed by the application logic.\n",
     "\n",
-    "This how-to guide shows you how to prevent the model from generating certain tool arguments and injecting them in directly at runtime."
+    "This how-to guide shows a simple design pattern that creates the tool dynamically at run time and binds to them appropriate values."
    ]
   },
   {
@@ -56,12 +57,23 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpython -m pip install --upgrade pip\u001b[0m\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
     "# | output: false\n",
     "# | echo: false\n",
     "\n",
-    "# %pip install -qU langchain langchain_openai\n",
+    "%pip install -qU langchain langchain_openai\n",
     "\n",
     "import os\n",
     "from getpass import getpass\n",
@@ -78,9 +90,10 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Hiding arguments from the model\n",
+    "# Passing request time information\n",
     "\n",
-    "We can use the InjectedToolArg annotation to mark certain parameters of our Tool, like `user_id` as being injected at runtime, meaning they shouldn't be generated by the model"
+    "The idea is to create the tool dynamically at request time, and bind to it the appropriate information. For example,\n",
+    "this information may be the user ID as resolved from the request itself."
    ]
   },
   {
@@ -91,88 +104,46 @@
    "source": [
     "from typing import List\n",
     "\n",
-    "from langchain_core.tools import InjectedToolArg, tool\n",
-    "from typing_extensions import Annotated\n",
-    "\n",
-    "user_to_pets = {}\n",
-    "\n",
-    "\n",
-    "@tool(parse_docstring=True)\n",
-    "def update_favorite_pets(\n",
-    "    pets: List[str], user_id: Annotated[str, InjectedToolArg]\n",
-    ") -> None:\n",
-    "    \"\"\"Add the list of favorite pets.\n",
-    "\n",
-    "    Args:\n",
-    "        pets: List of favorite pets to set.\n",
-    "        user_id: User's ID.\n",
-    "    \"\"\"\n",
-    "    user_to_pets[user_id] = pets\n",
-    "\n",
-    "\n",
-    "@tool(parse_docstring=True)\n",
-    "def delete_favorite_pets(user_id: Annotated[str, InjectedToolArg]) -> None:\n",
-    "    \"\"\"Delete the list of favorite pets.\n",
-    "\n",
-    "    Args:\n",
-    "        user_id: User's ID.\n",
-    "    \"\"\"\n",
-    "    if user_id in user_to_pets:\n",
-    "        del user_to_pets[user_id]\n",
-    "\n",
-    "\n",
-    "@tool(parse_docstring=True)\n",
-    "def list_favorite_pets(user_id: Annotated[str, InjectedToolArg]) -> None:\n",
-    "    \"\"\"List favorite pets if any.\n",
-    "\n",
-    "    Args:\n",
-    "        user_id: User's ID.\n",
-    "    \"\"\"\n",
-    "    return user_to_pets.get(user_id, [])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "If we look at the input schemas for these tools, we'll see that user_id is still listed:"
+    "from langchain_core.output_parsers import JsonOutputParser\n",
+    "from langchain_core.tools import BaseTool, tool"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'title': 'update_favorite_petsSchema',\n",
-       " 'description': 'Add the list of favorite pets.',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'pets': {'title': 'Pets',\n",
-       "   'description': 'List of favorite pets to set.',\n",
-       "   'type': 'array',\n",
-       "   'items': {'type': 'string'}},\n",
-       "  'user_id': {'title': 'User Id',\n",
-       "   'description': \"User's ID.\",\n",
-       "   'type': 'string'}},\n",
-       " 'required': ['pets', 'user_id']}"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "update_favorite_pets.get_input_schema().schema()"
+    "user_to_pets = {}\n",
+    "\n",
+    "\n",
+    "def generate_tools_for_user(user_id: str) -> List[BaseTool]:\n",
+    "    \"\"\"Generate a set of tools that have a user id associated with them.\"\"\"\n",
+    "\n",
+    "    @tool\n",
+    "    def update_favorite_pets(pets: List[str]) -> None:\n",
+    "        \"\"\"Add the list of favorite pets.\"\"\"\n",
+    "        user_to_pets[user_id] = pets\n",
+    "\n",
+    "    @tool\n",
+    "    def delete_favorite_pets() -> None:\n",
+    "        \"\"\"Delete the list of favorite pets.\"\"\"\n",
+    "        if user_id in user_to_pets:\n",
+    "            del user_to_pets[user_id]\n",
+    "\n",
+    "    @tool\n",
+    "    def list_favorite_pets() -> None:\n",
+    "        \"\"\"List favorite pets if any.\"\"\"\n",
+    "        return user_to_pets.get(user_id, [])\n",
+    "\n",
+    "    return [update_favorite_pets, delete_favorite_pets, list_favorite_pets]"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "But if we look at the tool call schema, which is what is passed to the model for tool-calling, user_id has been removed:"
+    "Verify that the tools work correctly"
    ]
   },
   {
@@ -181,60 +152,46 @@
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "{'title': 'update_favorite_pets',\n",
-       " 'description': 'Add the list of favorite pets.',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'pets': {'title': 'Pets',\n",
-       "   'description': 'List of favorite pets to set.',\n",
-       "   'type': 'array',\n",
-       "   'items': {'type': 'string'}}},\n",
-       " 'required': ['pets']}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'eugene': ['cat', 'dog']}\n",
+      "['cat', 'dog']\n"
+     ]
     }
    ],
    "source": [
-    "update_favorite_pets.tool_call_schema.schema()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "So when we invoke our tool, we need to pass in user_id:"
+    "update_pets, delete_pets, list_pets = generate_tools_for_user(\"eugene\")\n",
+    "update_pets.invoke({\"pets\": [\"cat\", \"dog\"]})\n",
+    "print(user_to_pets)\n",
+    "print(list_pets.invoke({}))"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'123': ['lizard', 'dog']}\n",
-      "['lizard', 'dog']\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "user_id = \"123\"\n",
-    "update_favorite_pets.invoke({\"pets\": [\"lizard\", \"dog\"], \"user_id\": user_id})\n",
-    "print(user_to_pets)\n",
-    "print(list_favorite_pets.invoke({\"user_id\": user_id}))"
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "\n",
+    "def handle_run_time_request(user_id: str, query: str):\n",
+    "    \"\"\"Handle run time request.\"\"\"\n",
+    "    tools = generate_tools_for_user(user_id)\n",
+    "    llm_with_tools = llm.bind_tools(tools)\n",
+    "    prompt = ChatPromptTemplate.from_messages(\n",
+    "        [(\"system\", \"You are a helpful assistant.\")],\n",
+    "    )\n",
+    "    chain = prompt | llm_with_tools\n",
+    "    return llm_with_tools.invoke(query)"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "But when the model calls the tool, no user_id argument will be generated:"
+    "This code will allow the LLM to invoke the tools, but the LLM is **unaware** of the fact that a **user ID** even exists!"
    ]
   },
   {
@@ -247,8 +204,7 @@
       "text/plain": [
        "[{'name': 'update_favorite_pets',\n",
        "  'args': {'pets': ['cats', 'parrots']},\n",
-       "  'id': 'call_W3cn4lZmJlyk8PCrKN4PRwqB',\n",
-       "  'type': 'tool_call'}]"
+       "  'id': 'call_jJvjPXsNbFO5MMgW0q84iqCN'}]"
       ]
      },
      "execution_count": 6,
@@ -257,349 +213,30 @@
     }
    ],
    "source": [
-    "tools = [\n",
-    "    update_favorite_pets,\n",
-    "    delete_favorite_pets,\n",
-    "    list_favorite_pets,\n",
-    "]\n",
-    "llm_with_tools = llm.bind_tools(tools)\n",
-    "ai_msg = llm_with_tools.invoke(\"my favorite animals are cats and parrots\")\n",
-    "ai_msg.tool_calls"
+    "ai_message = handle_run_time_request(\n",
+    "    \"eugene\", \"my favorite animals are cats and parrots.\"\n",
+    ")\n",
+    "ai_message.tool_calls"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Injecting arguments at runtime"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "If we want to actually execute our tools using the model-generated tool call, we'll need to inject the user_id ourselves:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[{'name': 'update_favorite_pets',\n",
-       "  'args': {'pets': ['cats', 'parrots'], 'user_id': '123'},\n",
-       "  'id': 'call_W3cn4lZmJlyk8PCrKN4PRwqB',\n",
-       "  'type': 'tool_call'}]"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from copy import deepcopy\n",
+    ":::{.callout-important}\n",
     "\n",
-    "from langchain_core.runnables import chain\n",
+    "Chat models only output requests to invoke tools, they don't actually invoke the underlying tools.\n",
     "\n",
-    "\n",
-    "@chain\n",
-    "def inject_user_id(ai_msg):\n",
-    "    tool_calls = []\n",
-    "    for tool_call in ai_msg.tool_calls:\n",
-    "        tool_call_copy = deepcopy(tool_call)\n",
-    "        tool_call_copy[\"args\"][\"user_id\"] = user_id\n",
-    "        tool_calls.append(tool_call_copy)\n",
-    "    return tool_calls\n",
-    "\n",
-    "\n",
-    "inject_user_id.invoke(ai_msg)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And now we can chain together our model, injection code, and the actual tools to create a tool-executing chain:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[ToolMessage(content='null', name='update_favorite_pets', tool_call_id='call_HUyF6AihqANzEYxQnTUKxkXj')]"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "tool_map = {tool.name: tool for tool in tools}\n",
-    "\n",
-    "\n",
-    "@chain\n",
-    "def tool_router(tool_call):\n",
-    "    return tool_map[tool_call[\"name\"]]\n",
-    "\n",
-    "\n",
-    "chain = llm_with_tools | inject_user_id | tool_router.map()\n",
-    "chain.invoke(\"my favorite animals are cats and parrots\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Looking at the user_to_pets dict, we can see that it's been updated to include cats and parrots:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'123': ['cats', 'parrots']}"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "user_to_pets"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Other ways of annotating args\n",
-    "\n",
-    "Here are a few other ways of annotating our tool args:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'title': 'UpdateFavoritePetsSchema',\n",
-       " 'description': 'Update list of favorite pets',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'pets': {'title': 'Pets',\n",
-       "   'description': 'List of favorite pets to set.',\n",
-       "   'type': 'array',\n",
-       "   'items': {'type': 'string'}},\n",
-       "  'user_id': {'title': 'User Id',\n",
-       "   'description': \"User's ID.\",\n",
-       "   'type': 'string'}},\n",
-       " 'required': ['pets', 'user_id']}"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "from langchain_core.tools import BaseTool\n",
-    "\n",
-    "\n",
-    "class UpdateFavoritePetsSchema(BaseModel):\n",
-    "    \"\"\"Update list of favorite pets\"\"\"\n",
-    "\n",
-    "    pets: List[str] = Field(..., description=\"List of favorite pets to set.\")\n",
-    "    user_id: Annotated[str, InjectedToolArg] = Field(..., description=\"User's ID.\")\n",
-    "\n",
-    "\n",
-    "@tool(args_schema=UpdateFavoritePetsSchema)\n",
-    "def update_favorite_pets(pets, user_id):\n",
-    "    user_to_pets[user_id] = pets\n",
-    "\n",
-    "\n",
-    "update_favorite_pets.get_input_schema().schema()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'title': 'update_favorite_pets',\n",
-       " 'description': 'Update list of favorite pets',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'pets': {'title': 'Pets',\n",
-       "   'description': 'List of favorite pets to set.',\n",
-       "   'type': 'array',\n",
-       "   'items': {'type': 'string'}}},\n",
-       " 'required': ['pets']}"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "update_favorite_pets.tool_call_schema.schema()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'title': 'UpdateFavoritePetsSchema',\n",
-       " 'description': 'Update list of favorite pets',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'pets': {'title': 'Pets',\n",
-       "   'description': 'List of favorite pets to set.',\n",
-       "   'type': 'array',\n",
-       "   'items': {'type': 'string'}},\n",
-       "  'user_id': {'title': 'User Id',\n",
-       "   'description': \"User's ID.\",\n",
-       "   'type': 'string'}},\n",
-       " 'required': ['pets', 'user_id']}"
-      ]
-     },
-     "execution_count": 22,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from typing import Optional, Type\n",
-    "\n",
-    "\n",
-    "class UpdateFavoritePets(BaseTool):\n",
-    "    name: str = \"update_favorite_pets\"\n",
-    "    description: str = \"Update list of favorite pets\"\n",
-    "    args_schema: Optional[Type[BaseModel]] = UpdateFavoritePetsSchema\n",
-    "\n",
-    "    def _run(self, pets, user_id):\n",
-    "        user_to_pets[user_id] = pets\n",
-    "\n",
-    "\n",
-    "UpdateFavoritePets().get_input_schema().schema()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'title': 'update_favorite_pets',\n",
-       " 'description': 'Update list of favorite pets',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'pets': {'title': 'Pets',\n",
-       "   'description': 'List of favorite pets to set.',\n",
-       "   'type': 'array',\n",
-       "   'items': {'type': 'string'}}},\n",
-       " 'required': ['pets']}"
-      ]
-     },
-     "execution_count": 23,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "UpdateFavoritePets().tool_call_schema.schema()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'title': 'update_favorite_petsSchema',\n",
-       " 'description': 'Use the tool.\\n\\nAdd run_manager: Optional[CallbackManagerForToolRun] = None\\nto child implementations to enable tracing.',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'pets': {'title': 'Pets',\n",
-       "   'type': 'array',\n",
-       "   'items': {'type': 'string'}},\n",
-       "  'user_id': {'title': 'User Id', 'type': 'string'}},\n",
-       " 'required': ['pets', 'user_id']}"
-      ]
-     },
-     "execution_count": 24,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "class UpdateFavoritePets2(BaseTool):\n",
-    "    name: str = \"update_favorite_pets\"\n",
-    "    description: str = \"Update list of favorite pets\"\n",
-    "\n",
-    "    def _run(self, pets: List[str], user_id: Annotated[str, InjectedToolArg]) -> None:\n",
-    "        user_to_pets[user_id] = pets\n",
-    "\n",
-    "\n",
-    "UpdateFavoritePets2().get_input_schema().schema()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'title': 'update_favorite_pets',\n",
-       " 'description': 'Update list of favorite pets',\n",
-       " 'type': 'object',\n",
-       " 'properties': {'pets': {'title': 'Pets',\n",
-       "   'type': 'array',\n",
-       "   'items': {'type': 'string'}}},\n",
-       " 'required': ['pets']}"
-      ]
-     },
-     "execution_count": 26,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "UpdateFavoritePets2().tool_call_schema.schema()"
+    "To see how to invoke the tools, please refer to [how to use a model to call tools](https://python.langchain.com/v0.2/docs/how_to/tool_calling).\n",
+    ":::"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv-311",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "poetry-venv-311"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -611,7 +248,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/tool_stream_events.ipynb

@@ -1,302 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to stream events from a tool\n",
-    "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Tools](/docs/concepts/#tools)\n",
-    "- [Custom tools](/docs/how_to/custom_tools)\n",
-    "- [Using stream events](/docs/how_to/streaming/#using-stream-events)\n",
-    "- [Accessing RunnableConfig within a custom tool](/docs/how_to/tool_configure/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "If you have tools that call chat models, retrievers, or other runnables, you may want to access internal events from those runnables or configure them with additional properties. This guide shows you how to manually pass parameters properly so that you can do this using the `astream_events()` method.\n",
-    "\n",
-    ":::caution Compatibility\n",
-    "\n",
-    "LangChain cannot automatically propagate configuration, including callbacks necessary for `astream_events()`, to child runnables if you are running `async` code in `python<=3.10`. This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
-    "\n",
-    "If you are running python<=3.10, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
-    "\n",
-    "If you are running python>=3.11, the `RunnableConfig` will automatically propagate to child runnables in async environment. However, it is still a good idea to propagate the `RunnableConfig` manually if your code may run in older Python versions.\n",
-    "\n",
-    "This guide also requires `langchain-core>=0.2.16`.\n",
-    ":::\n",
-    "\n",
-    "Say you have a custom tool that calls a chain that condenses its input by prompting a chat model to return only 10 words, then reversing the output. First, define it in a naive way:\n",
-    "\n",
-    "```{=mdx}\n",
-    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
-    "\n",
-    "<ChatModelTabs customVarName=\"model\" />\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# | output: false\n",
-    "# | echo: false\n",
-    "\n",
-    "%pip install -qU langchain langchain_anthropic langchain_core\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "from langchain_anthropic import ChatAnthropic\n",
-    "\n",
-    "if \"ANTHROPIC_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"ANTHROPIC_API_KEY\"] = getpass()\n",
-    "\n",
-    "model = ChatAnthropic(model=\"claude-3-5-sonnet-20240620\", temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "async def special_summarization_tool(long_text: str) -> str:\n",
-    "    \"\"\"A tool that summarizes input text using advanced techniques.\"\"\"\n",
-    "    prompt = ChatPromptTemplate.from_template(\n",
-    "        \"You are an expert writer. Summarize the following text in 10 words or less:\\n\\n{long_text}\"\n",
-    "    )\n",
-    "\n",
-    "    def reverse(x: str):\n",
-    "        return x[::-1]\n",
-    "\n",
-    "    chain = prompt | model | StrOutputParser() | reverse\n",
-    "    summary = await chain.ainvoke({\"long_text\": long_text})\n",
-    "    return summary"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Invoking the tool directly works just fine:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'.yad noitaudarg rof tiftuo sesoohc yrraB ;scisyhp seifed eeB'"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "LONG_TEXT = \"\"\"\n",
-    "NARRATOR:\n",
-    "(Black screen with text; The sound of buzzing bees can be heard)\n",
-    "According to all known laws of aviation, there is no way a bee should be able to fly. Its wings are too small to get its fat little body off the ground. The bee, of course, flies anyway because bees don't care what humans think is impossible.\n",
-    "BARRY BENSON:\n",
-    "(Barry is picking out a shirt)\n",
-    "Yellow, black. Yellow, black. Yellow, black. Yellow, black. Ooh, black and yellow! Let's shake it up a little.\n",
-    "JANET BENSON:\n",
-    "Barry! Breakfast is ready!\n",
-    "BARRY:\n",
-    "Coming! Hang on a second.\n",
-    "\"\"\"\n",
-    "\n",
-    "await special_summarization_tool.ainvoke({\"long_text\": LONG_TEXT})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "But if you wanted to access the raw output from the chat model rather than the full tool, you might try to use the [`astream_events()`](/docs/how_to/streaming/#using-stream-events) method and look for an `on_chat_model_end` event. Here's what happens:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "stream = special_summarization_tool.astream_events(\n",
-    "    {\"long_text\": LONG_TEXT}, version=\"v2\"\n",
-    ")\n",
-    "\n",
-    "async for event in stream:\n",
-    "    if event[\"event\"] == \"on_chat_model_end\":\n",
-    "        # Never triggers in python<=3.10!\n",
-    "        print(event)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You'll notice (unless you're running through this guide in `python>=3.11`) that there are no chat model events emitted from the child run!\n",
-    "\n",
-    "This is because the example above does not pass the tool's config object into the internal chain. To fix this, redefine your tool to take a special parameter typed as `RunnableConfig` (see [this guide](/docs/how_to/tool_configure) for more details). You'll also need to pass that parameter through into the internal chain when executing it:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.runnables import RunnableConfig\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "async def special_summarization_tool_with_config(\n",
-    "    long_text: str, config: RunnableConfig\n",
-    ") -> str:\n",
-    "    \"\"\"A tool that summarizes input text using advanced techniques.\"\"\"\n",
-    "    prompt = ChatPromptTemplate.from_template(\n",
-    "        \"You are an expert writer. Summarize the following text in 10 words or less:\\n\\n{long_text}\"\n",
-    "    )\n",
-    "\n",
-    "    def reverse(x: str):\n",
-    "        return x[::-1]\n",
-    "\n",
-    "    chain = prompt | model | StrOutputParser() | reverse\n",
-    "    # Pass the \"config\" object as an argument to any executed runnables\n",
-    "    summary = await chain.ainvoke({\"long_text\": long_text}, config=config)\n",
-    "    return summary"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And now try the same `astream_events()` call as before with your new tool:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'event': 'on_chat_model_end', 'data': {'output': AIMessage(content='Bee defies physics; Barry chooses outfit for graduation day.', response_metadata={'stop_reason': 'end_turn', 'stop_sequence': None}, id='run-d23abc80-0dce-4f74-9d7b-fb98ca4f2a9e', usage_metadata={'input_tokens': 182, 'output_tokens': 16, 'total_tokens': 198}), 'input': {'messages': [[HumanMessage(content=\"You are an expert writer. Summarize the following text in 10 words or less:\\n\\n\\nNARRATOR:\\n(Black screen with text; The sound of buzzing bees can be heard)\\nAccording to all known laws of aviation, there is no way a bee should be able to fly. Its wings are too small to get its fat little body off the ground. The bee, of course, flies anyway because bees don't care what humans think is impossible.\\nBARRY BENSON:\\n(Barry is picking out a shirt)\\nYellow, black. Yellow, black. Yellow, black. Yellow, black. Ooh, black and yellow! Let's shake it up a little.\\nJANET BENSON:\\nBarry! Breakfast is ready!\\nBARRY:\\nComing! Hang on a second.\\n\")]]}}, 'run_id': 'd23abc80-0dce-4f74-9d7b-fb98ca4f2a9e', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['f25c41fe-8972-4893-bc40-cecf3922c1fa']}\n"
-     ]
-    }
-   ],
-   "source": [
-    "stream = special_summarization_tool_with_config.astream_events(\n",
-    "    {\"long_text\": LONG_TEXT}, version=\"v2\"\n",
-    ")\n",
-    "\n",
-    "async for event in stream:\n",
-    "    if event[\"event\"] == \"on_chat_model_end\":\n",
-    "        print(event)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Awesome! This time there's an event emitted.\n",
-    "\n",
-    "For streaming, `astream_events()` automatically calls internal runnables in a chain with streaming enabled if possible, so if you wanted to a stream of tokens as they are generated from the chat model, you could simply filter to look for `on_chat_model_stream` events with no other changes:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42', usage_metadata={'input_tokens': 182, 'output_tokens': 0, 'total_tokens': 182})}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='Bee', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' def', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='ies physics', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=';', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' Barry', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' cho', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='oses outfit', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' for', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' graduation', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' day', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='.', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='', response_metadata={'stop_reason': 'end_turn', 'stop_sequence': None}, id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42', usage_metadata={'input_tokens': 0, 'output_tokens': 16, 'total_tokens': 16})}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n"
-     ]
-    }
-   ],
-   "source": [
-    "stream = special_summarization_tool_with_config.astream_events(\n",
-    "    {\"long_text\": LONG_TEXT}, version=\"v2\"\n",
-    ")\n",
-    "\n",
-    "async for event in stream:\n",
-    "    if event[\"event\"] == \"on_chat_model_stream\":\n",
-    "        print(event)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You've now seen how to stream events from within a tool. Next, check out the following guides for more on using tools:\n",
-    "\n",
-    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)\n",
-    "- Pass [tool results back to a model](/docs/how_to/tool_results_pass_to_model)\n",
-    "- [Dispatch custom callback events](/docs/how_to/callbacks_custom_events)\n",
-    "\n",
-    "You can also check out some more specific uses of tool calling:\n",
-    "\n",
-    "- Building [tool-using chains and agents](/docs/how_to#tools)\n",
-    "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

docs/docs/how_to/tools_builtin.ipynb

@@ -228,7 +228,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/tools_chain.ipynb

@@ -419,13 +419,13 @@
       "Invoking: `exponentiate` with `{'base': 405, 'exponent': 2}`\n",
       "\n",
       "\n",
-      "\u001b[0m\u001b[38;5;200m\u001b[1;3m13286025\u001b[0m\u001b[32;1m\u001b[1;3mThe result of taking 3 to the fifth power is 243. \n",
+      "\u001b[0m\u001b[38;5;200m\u001b[1;3m164025\u001b[0m\u001b[32;1m\u001b[1;3mThe result of taking 3 to the fifth power is 243. \n",
       "\n",
       "The sum of twelve and three is 15. \n",
       "\n",
       "Multiplying 243 by 15 gives 3645. \n",
       "\n",
-      "Finally, squaring 3645 gives 13286025.\u001b[0m\n",
+      "Finally, squaring 3645 gives 164025.\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -434,7 +434,7 @@
      "data": {
       "text/plain": [
        "{'input': 'Take 3 to the fifth power and multiply that by the sum of twelve and three, then square the whole result',\n",
-       " 'output': 'The result of taking 3 to the fifth power is 243. \\n\\nThe sum of twelve and three is 15. \\n\\nMultiplying 243 by 15 gives 3645. \\n\\nFinally, squaring 3645 gives 13286025.'}"
+       " 'output': 'The result of taking 3 to the fifth power is 243. \\n\\nThe sum of twelve and three is 15. \\n\\nMultiplying 243 by 15 gives 3645. \\n\\nFinally, squaring 3645 gives 164025.'}"
       ]
      },
      "execution_count": 18,

docs/docs/how_to/tools_error.ipynb

@@ -7,18 +7,9 @@
    "source": [
     "# How to handle tool errors\n",
     "\n",
-    ":::info Prerequisites\n",
+    "Using a model to invoke a tool has some obvious potential failure modes. Firstly, the model needs to return a output that can be parsed at all. Secondly, the model needs to return tool arguments that are valid.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [Chat models](/docs/concepts/#chat-models)\n",
-    "- [LangChain Tools](/docs/concepts/#tools)\n",
-    "- [How to use a model to call tools](/docs/how_to/tool_calling)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Calling tools with an LLM is generally more reliable than pure prompting, but it isn't perfect. The model may try to call a tool that doesn't exist or fail to return arguments that match the requested schema. Strategies like keeping schemas simple, reducing the number of tools you pass at once, and having good names and descriptions can help mitigate this risk, but aren't foolproof.\n",
-    "\n",
-    "This guide covers some ways to build error handling into your chains to mitigate these failure modes."
+    "We can build error handling into our chains to mitigate these failure modes."
    ]
   },
   {
@@ -51,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "08785b6d-722d-4620-b6ec-36deb3842c69",
    "metadata": {},
    "outputs": [],
@@ -81,7 +72,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "id": "86258950-5e61-4340-81b9-84a5d26e8773",
    "metadata": {},
    "outputs": [],
@@ -91,14 +82,12 @@
     "\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass()\n",
-    "\n",
     "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "id": "1d20604e-c4d1-4d21-841b-23e4f61aec36",
    "metadata": {},
    "outputs": [],
@@ -110,13 +99,28 @@
     "@tool\n",
     "def complex_tool(int_arg: int, float_arg: float, dict_arg: dict) -> int:\n",
     "    \"\"\"Do something complex with a complex tool.\"\"\"\n",
-    "    return int_arg * float_arg\n",
-    "\n",
-    "\n",
+    "    return int_arg * float_arg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "553c2c13-28c8-4451-8a3a-6c31d52dc31d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "llm_with_tools = llm.bind_tools(\n",
     "    [complex_tool],\n",
-    ")\n",
-    "\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "802b2eca-9f79-4d6c-8257-85139ca5c752",
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "# Define chain\n",
     "chain = llm_with_tools | (lambda msg: msg.tool_calls[0][\"args\"]) | complex_tool"
    ]
@@ -131,7 +135,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 12,
    "id": "d354664c-ac44-4967-a35f-8912b3ad9477",
    "metadata": {},
    "outputs": [
@@ -142,14 +146,14 @@
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mValidationError\u001b[0m                           Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[6], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mchain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      2\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43muse complex tool. the args are 5, 2.1, empty dictionary. don\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mt forget dict_arg\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m      3\u001b[0m \u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/langchain_core/runnables/base.py:2572\u001b[0m, in \u001b[0;36mRunnableSequence.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m   2570\u001b[0m             \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m step\u001b[38;5;241m.\u001b[39minvoke(\u001b[38;5;28minput\u001b[39m, config, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m   2571\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 2572\u001b[0m             \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[43mstep\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2573\u001b[0m \u001b[38;5;66;03m# finish the root run\u001b[39;00m\n\u001b[1;32m   2574\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
-      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/langchain_core/tools.py:380\u001b[0m, in \u001b[0;36mBaseTool.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    373\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m    374\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    375\u001b[0m     \u001b[38;5;28minput\u001b[39m: Union[\u001b[38;5;28mstr\u001b[39m, Dict],\n\u001b[1;32m    376\u001b[0m     config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    377\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m    378\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n\u001b[1;32m    379\u001b[0m     config \u001b[38;5;241m=\u001b[39m ensure_config(config)\n\u001b[0;32m--> 380\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    381\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    382\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcallbacks\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    383\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtags\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    384\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmetadata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    385\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrun_name\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    386\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpop\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrun_id\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    387\u001b[0m \u001b[43m        \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    388\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    389\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/langchain_core/tools.py:537\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, config, **kwargs)\u001b[0m\n\u001b[1;32m    535\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ValidationError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    536\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_validation_error:\n\u001b[0;32m--> 537\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    538\u001b[0m     \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_validation_error, \u001b[38;5;28mbool\u001b[39m):\n\u001b[1;32m    539\u001b[0m         observation \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTool input validation error\u001b[39m\u001b[38;5;124m\"\u001b[39m\n",
-      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/langchain_core/tools.py:526\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, config, **kwargs)\u001b[0m\n\u001b[1;32m    524\u001b[0m context \u001b[38;5;241m=\u001b[39m copy_context()\n\u001b[1;32m    525\u001b[0m context\u001b[38;5;241m.\u001b[39mrun(_set_config_context, child_config)\n\u001b[0;32m--> 526\u001b[0m parsed_input \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_parse_input\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtool_input\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    527\u001b[0m tool_args, tool_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_to_args_and_kwargs(parsed_input)\n\u001b[1;32m    528\u001b[0m observation \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    529\u001b[0m     context\u001b[38;5;241m.\u001b[39mrun(\n\u001b[1;32m    530\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run, \u001b[38;5;241m*\u001b[39mtool_args, run_manager\u001b[38;5;241m=\u001b[39mrun_manager, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mtool_kwargs\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    533\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m context\u001b[38;5;241m.\u001b[39mrun(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run, \u001b[38;5;241m*\u001b[39mtool_args, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mtool_kwargs)\n\u001b[1;32m    534\u001b[0m )\n",
-      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/langchain_core/tools.py:424\u001b[0m, in \u001b[0;36mBaseTool._parse_input\u001b[0;34m(self, tool_input)\u001b[0m\n\u001b[1;32m    422\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    423\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m input_args \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 424\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[43minput_args\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse_obj\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtool_input\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    425\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[1;32m    426\u001b[0m             k: \u001b[38;5;28mgetattr\u001b[39m(result, k)\n\u001b[1;32m    427\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m k, v \u001b[38;5;129;01min\u001b[39;00m result\u001b[38;5;241m.\u001b[39mdict()\u001b[38;5;241m.\u001b[39mitems()\n\u001b[1;32m    428\u001b[0m             \u001b[38;5;28;01mif\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m tool_input\n\u001b[1;32m    429\u001b[0m         }\n\u001b[1;32m    430\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m tool_input\n",
-      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/pydantic/main.py:526\u001b[0m, in \u001b[0;36mpydantic.main.BaseModel.parse_obj\u001b[0;34m()\u001b[0m\n",
-      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/pydantic/main.py:341\u001b[0m, in \u001b[0;36mpydantic.main.BaseModel.__init__\u001b[0;34m()\u001b[0m\n",
+      "Cell \u001b[0;32mIn[12], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mchain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      2\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43muse complex tool. the args are 5, 2.1, empty dictionary. don\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mt forget dict_arg\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m      3\u001b[0m \u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/langchain/libs/core/langchain_core/runnables/base.py:2499\u001b[0m, in \u001b[0;36mRunnableSequence.invoke\u001b[0;34m(self, input, config)\u001b[0m\n\u001b[1;32m   2497\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   2498\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m i, step \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msteps):\n\u001b[0;32m-> 2499\u001b[0m         \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[43mstep\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   2500\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2501\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;66;43;03m# mark each step as a child run\u001b[39;49;00m\n\u001b[1;32m   2502\u001b[0m \u001b[43m            \u001b[49m\u001b[43mpatch_config\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   2503\u001b[0m \u001b[43m                \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseq:step:\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mi\u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2504\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2505\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2506\u001b[0m \u001b[38;5;66;03m# finish the root run\u001b[39;00m\n\u001b[1;32m   2507\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
+      "File \u001b[0;32m~/langchain/libs/core/langchain_core/tools.py:241\u001b[0m, in \u001b[0;36mBaseTool.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    234\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m    235\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    236\u001b[0m     \u001b[38;5;28minput\u001b[39m: Union[\u001b[38;5;28mstr\u001b[39m, Dict],\n\u001b[1;32m    237\u001b[0m     config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    238\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m    239\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n\u001b[1;32m    240\u001b[0m     config \u001b[38;5;241m=\u001b[39m ensure_config(config)\n\u001b[0;32m--> 241\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    242\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    243\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcallbacks\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    244\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtags\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    245\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmetadata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    246\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrun_name\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    247\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpop\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrun_id\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    248\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    249\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/langchain/libs/core/langchain_core/tools.py:387\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m    385\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ValidationError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    386\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_validation_error:\n\u001b[0;32m--> 387\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    388\u001b[0m     \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_validation_error, \u001b[38;5;28mbool\u001b[39m):\n\u001b[1;32m    389\u001b[0m         observation \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTool input validation error\u001b[39m\u001b[38;5;124m\"\u001b[39m\n",
+      "File \u001b[0;32m~/langchain/libs/core/langchain_core/tools.py:378\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m    364\u001b[0m run_manager \u001b[38;5;241m=\u001b[39m callback_manager\u001b[38;5;241m.\u001b[39mon_tool_start(\n\u001b[1;32m    365\u001b[0m     {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mname, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdescription\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdescription},\n\u001b[1;32m    366\u001b[0m     tool_input \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(tool_input, \u001b[38;5;28mstr\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mstr\u001b[39m(tool_input),\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    375\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m    376\u001b[0m )\n\u001b[1;32m    377\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 378\u001b[0m     parsed_input \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_parse_input\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtool_input\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    379\u001b[0m     tool_args, tool_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_to_args_and_kwargs(parsed_input)\n\u001b[1;32m    380\u001b[0m     observation \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    381\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run(\u001b[38;5;241m*\u001b[39mtool_args, run_manager\u001b[38;5;241m=\u001b[39mrun_manager, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mtool_kwargs)\n\u001b[1;32m    382\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    383\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run(\u001b[38;5;241m*\u001b[39mtool_args, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mtool_kwargs)\n\u001b[1;32m    384\u001b[0m     )\n",
+      "File \u001b[0;32m~/langchain/libs/core/langchain_core/tools.py:283\u001b[0m, in \u001b[0;36mBaseTool._parse_input\u001b[0;34m(self, tool_input)\u001b[0m\n\u001b[1;32m    281\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    282\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m input_args \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 283\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[43minput_args\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse_obj\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtool_input\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    284\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[1;32m    285\u001b[0m             k: \u001b[38;5;28mgetattr\u001b[39m(result, k)\n\u001b[1;32m    286\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m k, v \u001b[38;5;129;01min\u001b[39;00m result\u001b[38;5;241m.\u001b[39mdict()\u001b[38;5;241m.\u001b[39mitems()\n\u001b[1;32m    287\u001b[0m             \u001b[38;5;28;01mif\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m tool_input\n\u001b[1;32m    288\u001b[0m         }\n\u001b[1;32m    289\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m tool_input\n",
+      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/pydantic/v1/main.py:526\u001b[0m, in \u001b[0;36mBaseModel.parse_obj\u001b[0;34m(cls, obj)\u001b[0m\n\u001b[1;32m    524\u001b[0m         exc \u001b[38;5;241m=\u001b[39m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m expected dict not \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mobj\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m    525\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m ValidationError([ErrorWrapper(exc, loc\u001b[38;5;241m=\u001b[39mROOT_KEY)], \u001b[38;5;28mcls\u001b[39m) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[0;32m--> 526\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mobj\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/pydantic/v1/main.py:341\u001b[0m, in \u001b[0;36mBaseModel.__init__\u001b[0;34m(__pydantic_self__, **data)\u001b[0m\n\u001b[1;32m    339\u001b[0m values, fields_set, validation_error \u001b[38;5;241m=\u001b[39m validate_model(__pydantic_self__\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m, data)\n\u001b[1;32m    340\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m validation_error:\n\u001b[0;32m--> 341\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m validation_error\n\u001b[1;32m    342\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    343\u001b[0m     object_setattr(__pydantic_self__, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m__dict__\u001b[39m\u001b[38;5;124m'\u001b[39m, values)\n",
       "\u001b[0;31mValidationError\u001b[0m: 1 validation error for complex_toolSchema\ndict_arg\n  field required (type=value_error.missing)"
      ]
     }
@@ -172,26 +176,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 6,
    "id": "8fedb550-683d-45ae-8876-ae7acb332019",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Calling tool with arguments:\n",
-      "\n",
-      "{'int_arg': 5, 'float_arg': 2.1}\n",
-      "\n",
-      "raised the following error:\n",
-      "\n",
-      "<class 'pydantic.error_wrappers.ValidationError'>: 1 validation error for complex_toolSchema\n",
-      "dict_arg\n",
-      "  field required (type=value_error.missing)\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from typing import Any\n",
     "\n",
@@ -205,8 +193,32 @@
     "        return f\"Calling tool with arguments:\\n\\n{tool_args}\\n\\nraised the following error:\\n\\n{type(e)}: {e}\"\n",
     "\n",
     "\n",
-    "chain = llm_with_tools | (lambda msg: msg.tool_calls[0][\"args\"]) | try_except_tool\n",
-    "\n",
+    "chain = llm_with_tools | (lambda msg: msg.tool_calls[0][\"args\"]) | try_except_tool"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "71a2c98d-c0be-4c0a-bb3d-41ad4596526c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Calling tool with arguments:\n",
+      "\n",
+      "{'int_arg': 5, 'float_arg': 2.1}\n",
+      "\n",
+      "raised the following error:\n",
+      "\n",
+      "<class 'pydantic.v1.error_wrappers.ValidationError'>: 1 validation error for complex_toolSchema\n",
+      "dict_arg\n",
+      "  field required (type=value_error.missing)\n"
+     ]
+    }
+   ],
+   "source": [
     "print(\n",
     "    chain.invoke(\n",
     "        \"use complex tool. the args are 5, 2.1, empty dictionary. don't forget dict_arg\"\n",
@@ -226,7 +238,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 17,
    "id": "02cc4223-35fa-4240-976a-012299ca703c",
    "metadata": {},
    "outputs": [
@@ -236,22 +248,19 @@
        "10.5"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "chain = llm_with_tools | (lambda msg: msg.tool_calls[0][\"args\"]) | complex_tool\n",
-    "\n",
     "better_model = ChatOpenAI(model=\"gpt-4-1106-preview\", temperature=0).bind_tools(\n",
     "    [complex_tool], tool_choice=\"complex_tool\"\n",
     ")\n",
-    "\n",
     "better_chain = better_model | (lambda msg: msg.tool_calls[0][\"args\"]) | complex_tool\n",
     "\n",
     "chain_with_fallback = chain.with_fallbacks([better_chain])\n",
-    "\n",
     "chain_with_fallback.invoke(\n",
     "    \"use complex tool. the args are 5, 2.1, empty dictionary. don't forget dict_arg\"\n",
     ")"
@@ -262,7 +271,7 @@
    "id": "412f8c4e-cc83-4d87-84a1-5ba2f8edb1e9",
    "metadata": {},
    "source": [
-    "Looking at the [LangSmith trace](https://smith.langchain.com/public/00e91fc2-e1a4-4b0f-a82e-e6b3119d196c/r) for this chain run, we can see that the first chain call fails as expected and it's the fallback that succeeds."
+    "Looking at the [Langsmith trace](https://smith.langchain.com/public/00e91fc2-e1a4-4b0f-a82e-e6b3119d196c/r) for this chain run, we can see that the first chain call fails as expected and it's the fallback that succeeds."
    ]
   },
   {
@@ -277,13 +286,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 13,
    "id": "b5659956-9454-468a-9753-a3ff9052b8f5",
    "metadata": {},
    "outputs": [],
    "source": [
+    "import json\n",
+    "from typing import Any\n",
+    "\n",
     "from langchain_core.messages import AIMessage, HumanMessage, ToolCall, ToolMessage\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
     "\n",
     "\n",
     "class CustomToolException(Exception):\n",
@@ -323,7 +336,7 @@
     "# affect the prompt at all, but gives us the option to insert an arbitrary list of Messages\n",
     "# into the prompt if needed. We'll use this on retries to insert the error message.\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [(\"human\", \"{input}\"), (\"placeholder\", \"{last_output}\")]\n",
+    "    [(\"human\", \"{input}\"), MessagesPlaceholder(\"last_output\", optional=True)]\n",
     ")\n",
     "chain = prompt | llm_with_tools | tool_custom_exception\n",
     "\n",
@@ -335,7 +348,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 14,
    "id": "4c45f5bd-cbb4-47d5-b4b6-aec50673c750",
    "metadata": {},
    "outputs": [
@@ -345,7 +358,7 @@
        "10.5"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -365,24 +378,6 @@
    "source": [
     "And our chain succeeds! Looking at the [LangSmith trace](https://smith.langchain.com/public/c11e804c-e14f-4059-bd09-64766f999c14/r), we can see that indeed our initial chain still fails, and it's only on retrying that the chain succeeds."
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6b97af9f",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "Now you've seen some strategies how to handle tool calling errors. Next, you can learn more about how to use tools:\n",
-    "\n",
-    "- Few shot prompting [with tools](/docs/how_to/tools_few_shot/)\n",
-    "- Stream [tool calls](/docs/how_to/tool_streaming/)\n",
-    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)\n",
-    "\n",
-    "You can also check out some more specific uses of tool calling:\n",
-    "\n",
-    "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
-   ]
   }
  ],
  "metadata": {
@@ -401,7 +396,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/bedrock.ipynb

@@ -2,125 +2,86 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
+   "id": "fbc66410",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
-    "sidebar_label: AWS Bedrock\n",
+    "sidebar_label: Bedrock\n",
     "---"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "e49f1e0d",
+   "id": "bf733a38-db84-4363-89e2-de6735c37230",
    "metadata": {},
    "source": [
     "# ChatBedrock\n",
     "\n",
-    "This doc will help you get started with AWS Bedrock [chat models](/docs/concepts/#chat-models). Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon via a single API, along with a broad set of capabilities you need to build generative AI applications with security, privacy, and responsible AI. Using Amazon Bedrock, you can easily experiment with and evaluate top FMs for your use case, privately customize them with your data using techniques such as fine-tuning and Retrieval Augmented Generation (RAG), and build agents that execute tasks using your enterprise systems and data sources. Since Amazon Bedrock is serverless, you don't have to manage any infrastructure, and you can securely integrate and deploy generative AI capabilities into your applications using the AWS services you are already familiar with.\n",
-    "\n",
-    "For more information on which models are accessible via Bedrock, head to the [AWS docs](https://docs.aws.amazon.com/bedrock/latest/userguide/models-features.html).\n",
-    "\n",
-    "For detailed documentation of all ChatBedrock features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_aws.chat_models.bedrock.ChatBedrock.html).\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/bedrock) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatBedrock](https://api.python.langchain.com/en/latest/chat_models/langchain_aws.chat_models.bedrock.ChatBedrock.html) | [langchain-aws](https://api.python.langchain.com/en/latest/aws_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-aws?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-aws?style=flat-square&label=%20) |\n",
-    "\n",
-    "### Model features\n",
-    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
-    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | \n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "To access Bedrock models you'll need to create an AWS account, set up the Bedrock API service, get an access key ID and secret key, and install the `langchain-aws` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Head to the [AWS docs](https://docs.aws.amazon.com/bedrock/latest/userguide/setting-up.html) to sign up to AWS and setup your credentials. You'll also need to turn on model access for your account, which you can do by following [these instructions](https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
-   "metadata": {},
-   "source": [
-    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+    ">[Amazon Bedrock](https://aws.amazon.com/bedrock/) is a fully managed service that offers a choice of \n",
+    "> high-performing foundation models (FMs) from leading AI companies like `AI21 Labs`, `Anthropic`, `Cohere`, \n",
+    "> `Meta`, `Stability AI`, and `Amazon` via a single API, along with a broad set of capabilities you need to \n",
+    "> build generative AI applications with security, privacy, and responsible AI. Using `Amazon Bedrock`, \n",
+    "> you can easily experiment with and evaluate top FMs for your use case, privately customize them with \n",
+    "> your data using techniques such as fine-tuning and `Retrieval Augmented Generation` (`RAG`), and build \n",
+    "> agents that execute tasks using your enterprise systems and data sources. Since `Amazon Bedrock` is \n",
+    "> serverless, you don't have to manage any infrastructure, and you can securely integrate and deploy \n",
+    "> generative AI capabilities into your applications using the AWS services you are already familiar with."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "execution_count": 2,
+   "id": "d51edc81",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
-   "metadata": {},
-   "source": [
-    "### Installation\n",
-    "\n",
-    "The LangChain Bedrock integration lives in the `langchain-aws` package:"
+    "%pip install --upgrade --quiet langchain-aws"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-aws"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
-   "metadata": {},
-   "source": [
-    "## Instantiation\n",
-    "\n",
-    "Now we can instantiate our model object and generate chat completions:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
+   "execution_count": 1,
+   "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from langchain_aws import ChatBedrock\n",
-    "\n",
-    "llm = ChatBedrock(\n",
+    "from langchain_core.messages import HumanMessage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat = ChatBedrock(\n",
     "    model_id=\"anthropic.claude-3-sonnet-20240229-v1:0\",\n",
-    "    model_kwargs=dict(temperature=0),\n",
-    "    # other params...\n",
+    "    model_kwargs={\"temperature\": 0.1},\n",
     ")"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "2b4f3e15",
-   "metadata": {},
-   "source": [
-    "## Invocation"
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "62e0dbc3",
+   "execution_count": 12,
+   "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
    "metadata": {
     "tags": []
    },
@@ -128,30 +89,38 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Voici la traduction en français :\\n\\nJ'aime la programmation.\", additional_kwargs={'usage': {'prompt_tokens': 29, 'completion_tokens': 21, 'total_tokens': 50}, 'stop_reason': 'end_turn', 'model_id': 'anthropic.claude-3-sonnet-20240229-v1:0'}, response_metadata={'usage': {'prompt_tokens': 29, 'completion_tokens': 21, 'total_tokens': 50}, 'stop_reason': 'end_turn', 'model_id': 'anthropic.claude-3-sonnet-20240229-v1:0'}, id='run-fdb07dc3-ff72-430d-b22b-e7824b15c766-0', usage_metadata={'input_tokens': 29, 'output_tokens': 21, 'total_tokens': 50})"
+       "AIMessage(content=\"Voici la traduction en français :\\n\\nJ'aime la programmation.\", additional_kwargs={'usage': {'prompt_tokens': 20, 'completion_tokens': 21, 'total_tokens': 41}}, response_metadata={'model_id': 'anthropic.claude-3-sonnet-20240229-v1:0', 'usage': {'prompt_tokens': 20, 'completion_tokens': 21, 'total_tokens': 41}}, id='run-994f0362-0e50-4524-afad-3c4f5bb11328-0')"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "messages = [\n",
-    "    (\n",
-    "        \"system\",\n",
-    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
-    "    ),\n",
-    "    (\"human\", \"I love programming.\"),\n",
+    "    HumanMessage(\n",
+    "        content=\"Translate this sentence from English to French. I love programming.\"\n",
+    "    )\n",
     "]\n",
-    "ai_msg = llm.invoke(messages)\n",
-    "ai_msg"
+    "chat.invoke(messages)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "a4a4f4d4",
+   "metadata": {},
+   "source": [
+    "### Streaming\n",
+    "\n",
+    "To stream responses, you can use the runnable `.stream()` method."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+   "execution_count": 14,
+   "id": "d9e52838",
    "metadata": {},
    "outputs": [
     {
@@ -160,124 +129,84 @@
      "text": [
       "Voici la traduction en français :\n",
       "\n",
-      "J'aime la programmation.\n"
+      "J'aime la programmation."
      ]
     }
    ],
    "source": [
-    "print(ai_msg.content)"
+    "for chunk in chat.stream(messages):\n",
+    "    print(chunk.content, end=\"\", flush=True)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
+   "id": "c36575b3",
    "metadata": {},
    "source": [
-    "## Chaining\n",
+    "### LLM Caching with OpenSearch Semantic Cache\n",
     "\n",
-    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
+    "Use OpenSearch as a semantic cache to cache prompts and responses and evaluate hits based on semantic similarity.\n",
+    "\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "execution_count": null,
+   "id": "375d4e56",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ich liebe Programmieren.', additional_kwargs={'usage': {'prompt_tokens': 23, 'completion_tokens': 11, 'total_tokens': 34}, 'stop_reason': 'end_turn', 'model_id': 'anthropic.claude-3-sonnet-20240229-v1:0'}, response_metadata={'usage': {'prompt_tokens': 23, 'completion_tokens': 11, 'total_tokens': 34}, 'stop_reason': 'end_turn', 'model_id': 'anthropic.claude-3-sonnet-20240229-v1:0'}, id='run-5ad005ce-9f31-4670-baa0-9373d418698a-0', usage_metadata={'input_tokens': 23, 'output_tokens': 11, 'total_tokens': 34})"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain.globals import set_llm_cache\n",
+    "from langchain_aws import BedrockEmbeddings, ChatBedrock\n",
+    "from langchain_community.cache import OpenSearchSemanticCache\n",
+    "from langchain_core.messages import HumanMessage\n",
     "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
-    "        ),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
+    "bedrock_embeddings = BedrockEmbeddings(\n",
+    "    model_id=\"amazon.titan-embed-text-v1\", region_name=\"us-east-1\"\n",
     ")\n",
     "\n",
-    "chain = prompt | llm\n",
-    "chain.invoke(\n",
-    "    {\n",
-    "        \"input_language\": \"English\",\n",
-    "        \"output_language\": \"German\",\n",
-    "        \"input\": \"I love programming.\",\n",
-    "    }\n",
+    "chat = ChatBedrock(\n",
+    "    model_id=\"anthropic.claude-3-haiku-20240307-v1:0\", model_kwargs={\"temperature\": 0.5}\n",
+    ")\n",
+    "\n",
+    "# Enable LLM cache. Make sure OpenSearch is set up and running. Update URL accordingly.\n",
+    "set_llm_cache(\n",
+    "    OpenSearchSemanticCache(\n",
+    "        opensearch_url=\"http://localhost:9200\", embedding=bedrock_embeddings\n",
+    "    )\n",
     ")"
    ]
   },
   {
-   "cell_type": "markdown",
-   "id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bb5d25bb",
    "metadata": {},
+   "outputs": [],
    "source": [
-    "## ***Beta***: Bedrock Converse API\n",
+    "%%time\n",
+    "# The first time, it is not yet in cache, so it should take longer\n",
+    "messages = [HumanMessage(content=\"tell me about Amazon Bedrock\")]\n",
+    "response_text = chat.invoke(messages)\n",
     "\n",
-    "AWS has recently recently the Bedrock Converse API which provides a unified conversational interface for Bedrock models. This API does not yet support custom models. You can see a list of all [models that are supported here](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html). To improve reliability the ChatBedrock integration will switch to using the Bedrock Converse API as soon as it has feature parity with the existing Bedrock API. Until then a separate [ChatBedrockConverse](https://api.python.langchain.com/en/latest/chat_models/langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse.html#langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse) integration has been released in beta for users who do not need to use custom models.\n",
-    "\n",
-    "You can use it like so:"
+    "print(response_text)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "ae728e59-94d4-40cf-9d24-25ad8723fc59",
+   "execution_count": null,
+   "id": "6cfb3086",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/bagatur/langchain/libs/core/langchain_core/_api/beta_decorator.py:87: LangChainBetaWarning: The class `ChatBedrockConverse` is in beta. It is actively being worked on, so the API may change.\n",
-      "  warn_beta(\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Voici la traduction en français :\\n\\nJ'aime la programmation.\", response_metadata={'ResponseMetadata': {'RequestId': '122fb1c8-c3c5-4b06-941e-c95d210bfbc7', 'HTTPStatusCode': 200, 'HTTPHeaders': {'date': 'Mon, 01 Jul 2024 21:48:25 GMT', 'content-type': 'application/json', 'content-length': '243', 'connection': 'keep-alive', 'x-amzn-requestid': '122fb1c8-c3c5-4b06-941e-c95d210bfbc7'}, 'RetryAttempts': 0}, 'stopReason': 'end_turn', 'metrics': {'latencyMs': 830}}, id='run-0e3df22f-fcd8-4fbb-a4fb-565227e7e430-0', usage_metadata={'input_tokens': 29, 'output_tokens': 21, 'total_tokens': 50})"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "from langchain_aws import ChatBedrockConverse\n",
+    "%%time\n",
+    "# The second time, while not a direct hit, the question is semantically similar to the original question,\n",
+    "# so it uses the cached result!\n",
     "\n",
-    "llm = ChatBedrockConverse(\n",
-    "    model=\"anthropic.claude-3-sonnet-20240229-v1:0\",\n",
-    "    temperature=0,\n",
-    "    max_tokens=None,\n",
-    "    # other params...\n",
-    ")\n",
+    "messages = [HumanMessage(content=\"what is amazon bedrock\")]\n",
+    "response_text = chat.invoke(messages)\n",
     "\n",
-    "llm.invoke(messages)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all ChatBedrock features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_aws.chat_models.bedrock.ChatBedrock.html\n",
-    "\n",
-    "For detailed documentation of all ChatBedrockConverse features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse.html"
+    "print(response_text)"
    ]
   }
  ],
@@ -297,7 +226,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/cohere.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "afaf8039",
+   "id": "53fbf15f",
    "metadata": {},
    "source": [
     "---\n",
@@ -12,129 +12,103 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e49f1e0d",
+   "id": "bf733a38-db84-4363-89e2-de6735c37230",
    "metadata": {},
    "source": [
-    "# ChatCohere\n",
+    "# Cohere\n",
     "\n",
-    "This doc will help you get started with Cohere [chat models](/docs/concepts/#chat-models). For detailed documentation of all ChatCohere features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_cohere.chat_models.ChatCohere.html).\n",
-    "\n",
-    "For an overview of all Cohere models head to the [Cohere docs](https://docs.cohere.com/docs/models).\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/cohere) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatCohere](https://api.python.langchain.com/en/latest/chat_models/langchain_cohere.chat_models.ChatCohere.html) | [langchain-cohere](https://api.python.langchain.com/en/latest/cohere_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-cohere?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-cohere?style=flat-square&label=%20) |\n",
-    "\n",
-    "### Model features\n",
-    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
-    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | \n",
+    "This notebook covers how to get started with [Cohere chat models](https://cohere.com/chat).\n",
     "\n",
+    "Head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.cohere.ChatCohere.html) for detailed documentation of all attributes and methods."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3607d67e-e56c-4102-bbba-df2edc0e109e",
+   "metadata": {},
+   "source": [
     "## Setup\n",
     "\n",
-    "To access Cohere models you'll need to create a Cohere account, get an API key, and install the `langchain-cohere` integration package.\n",
+    "The integration lives in the `langchain-cohere` package. We can install these with:\n",
     "\n",
-    "### Credentials\n",
+    "```bash\n",
+    "pip install -U langchain-cohere\n",
+    "```\n",
     "\n",
-    "Head to https://dashboard.cohere.com/welcome/login to sign up to Cohere and generate an API key. Once you've done this set the COHERE_API_KEY environment variable:"
+    "We'll also need to get a [Cohere API key](https://cohere.com/) and set the `COHERE_API_KEY` environment variable:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+   "execution_count": 11,
+   "id": "2108b517-1e8d-473d-92fa-4f930e8072a7",
    "metadata": {},
    "outputs": [],
    "source": [
     "import getpass\n",
     "import os\n",
     "\n",
-    "os.environ[\"COHERE_API_KEY\"] = getpass.getpass(\"Enter your Cohere API key: \")"
+    "os.environ[\"COHERE_API_KEY\"] = getpass.getpass()"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+   "id": "cf690fbb",
    "metadata": {},
    "source": [
-    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+    "It's also helpful (but not needed) to set up [LangSmith](https://smith.langchain.com/) for best-in-class observability"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "execution_count": 12,
+   "id": "7f11de02",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "id": "4c26754b-b3c9-4d93-8f36-43049bd943bf",
    "metadata": {},
    "source": [
-    "### Installation\n",
+    "## Usage\n",
     "\n",
-    "The LangChain Cohere integration lives in the `langchain-cohere` package:"
+    "ChatCohere supports all [ChatModel](/docs/how_to#chat-models) functionality:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-cohere"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
-   "metadata": {},
-   "source": [
-    "## Instantiation\n",
-    "\n",
-    "Now we can instantiate our model object and generate chat completions:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
+   "execution_count": 13,
+   "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from langchain_cohere import ChatCohere\n",
-    "\n",
-    "llm = ChatCohere(\n",
-    "    model=\"command-r-plus\",\n",
-    "    temperature=0,\n",
-    "    max_tokens=None,\n",
-    "    timeout=None,\n",
-    "    max_retries=2,\n",
-    "    # other params...\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2b4f3e15",
-   "metadata": {},
-   "source": [
-    "## Invocation"
+    "from langchain_core.messages import HumanMessage"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "id": "62e0dbc3",
+   "execution_count": 14,
+   "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat = ChatCohere(model=\"command\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
    "metadata": {
     "tags": []
    },
@@ -142,110 +116,134 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"J'adore programmer.\", additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'd84f80f3-4611-46e6-aed0-9d8665a20a11', 'token_count': {'input_tokens': 89, 'output_tokens': 5}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'd84f80f3-4611-46e6-aed0-9d8665a20a11', 'token_count': {'input_tokens': 89, 'output_tokens': 5}}, id='run-514ab516-ed7e-48ac-b132-2598fb80ebef-0')"
+       "AIMessage(content='4 && 5 \\n6 || 7 \\n\\nWould you like to play a game of odds and evens?', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '2076b614-52b3-4082-a259-cc92cd3d9fea', 'token_count': {'prompt_tokens': 68, 'response_tokens': 23, 'total_tokens': 91, 'billed_tokens': 77}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '2076b614-52b3-4082-a259-cc92cd3d9fea', 'token_count': {'prompt_tokens': 68, 'response_tokens': 23, 'total_tokens': 91, 'billed_tokens': 77}}, id='run-3475e0c8-c89b-4937-9300-e07d652455e1-0')"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "messages = [\n",
-    "    (\n",
-    "        \"system\",\n",
-    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
-    "    ),\n",
-    "    (\"human\", \"I love programming.\"),\n",
-    "]\n",
-    "ai_msg = llm.invoke(messages)\n",
-    "ai_msg"
+    "messages = [HumanMessage(content=\"1\"), HumanMessage(content=\"2 3\")]\n",
+    "chat.invoke(messages)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
-   "metadata": {},
+   "execution_count": 16,
+   "id": "c5fac0e9-05a4-4fc1-a3b3-e5bbb24b971b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='4 && 5', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'f0708a92-f874-46ee-9b93-334d616ad92e', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'f0708a92-f874-46ee-9b93-334d616ad92e', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, id='run-1635e63e-2994-4e7f-986e-152ddfc95777-0')"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await chat.ainvoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "025be980-e50d-4a68-93dc-c9c7b500ce34",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "J'adore programmer.\n"
+      "4 && 5"
      ]
     }
    ],
    "source": [
-    "print(ai_msg.content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
-   "metadata": {},
-   "source": [
-    "## Chaining\n",
-    "\n",
-    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
+    "for chunk in chat.stream(messages):\n",
+    "    print(chunk.content, end=\"\", flush=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "execution_count": 18,
+   "id": "064288e4-f184-4496-9427-bcf148fa055e",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Ich liebe Programmierung.', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '053bebde-4e1d-4d06-8ee6-3446e7afa25e', 'token_count': {'input_tokens': 84, 'output_tokens': 6}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '053bebde-4e1d-4d06-8ee6-3446e7afa25e', 'token_count': {'input_tokens': 84, 'output_tokens': 6}}, id='run-53700708-b7fb-417b-af36-1a6fcde38e7d-0')"
+       "[AIMessage(content='4 && 5', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, id='run-8d6fade2-1b39-4e31-ab23-4be622dd0027-0')]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
-    "        ),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "chain = prompt | llm\n",
-    "chain.invoke(\n",
-    "    {\n",
-    "        \"input_language\": \"English\",\n",
-    "        \"output_language\": \"German\",\n",
-    "        \"input\": \"I love programming.\",\n",
-    "    }\n",
-    ")"
+    "chat.batch([messages])"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "id": "f1c56460",
    "metadata": {},
    "source": [
-    "## API reference\n",
+    "## Chaining\n",
     "\n",
-    "For detailed documentation of all ChatCohere features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_cohere.chat_models.ChatCohere.html"
+    "You can also easily combine with a prompt template for easy structuring of user input. We can do this using [LCEL](/docs/concepts#langchain-expression-language-lcel)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "0851b103",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
+    "chain = prompt | chat"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "ae950c0f-1691-47f1-b609-273033cae707",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='What color socks do bears wear?\\n\\nThey don’t wear socks, they have bear feet. \\n\\nHope you laughed! If not, maybe this will help: laughter is the best medicine, and a good sense of humor is infectious!', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6edccf44-9bc8-4139-b30e-13b368f3563c', 'token_count': {'prompt_tokens': 68, 'response_tokens': 51, 'total_tokens': 119, 'billed_tokens': 108}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6edccf44-9bc8-4139-b30e-13b368f3563c', 'token_count': {'prompt_tokens': 68, 'response_tokens': 51, 'total_tokens': 119, 'billed_tokens': 108}}, id='run-ef7f9789-0d4d-43bf-a4f7-f2a0e27a5320-0')"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"topic\": \"bears\"})"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv-2",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "poetry-venv-2"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -257,7 +255,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.7"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/fireworks.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "afaf8039",
+   "id": "529aeba9",
    "metadata": {},
    "source": [
     "---\n",
@@ -11,236 +11,190 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
-   "id": "e49f1e0d",
+   "id": "642fd21c-600a-47a1-be96-6e1438b421a9",
    "metadata": {},
    "source": [
     "# ChatFireworks\n",
     "\n",
-    "This doc help you get started with Fireworks AI [chat models](/docs/concepts/#chat-models). For detailed documentation of all ChatFireworks features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_fireworks.chat_models.ChatFireworks.html).\n",
+    ">[Fireworks](https://app.fireworks.ai/) accelerates product development on generative AI by creating an innovative AI experiment and production platform. \n",
     "\n",
-    "Fireworks AI is an AI inference platform to run and customize models. For a list of all models served by Fireworks see the [Fireworks docs](https://fireworks.ai/models).\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/fireworks) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatFireworks](https://api.python.langchain.com/en/latest/chat_models/langchain_fireworks.chat_models.ChatFireworks.html) | [langchain-fireworks](https://api.python.langchain.com/en/latest/fireworks_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-fireworks?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-fireworks?style=flat-square&label=%20) |\n",
-    "\n",
-    "### Model features\n",
-    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
-    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | \n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "To access Fireworks models you'll need to create a Fireworks account, get an API key, and install the `langchain-fireworks` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Head to (ttps://fireworks.ai/login to sign up to Fireworks and generate an API key. Once you've done this set the FIREWORKS_API_KEY environment variable:"
+    "This example goes over how to use LangChain to interact with `ChatFireworks` models."
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "4a7c795e",
+   "metadata": {},
+   "source": [
+    "%pip install langchain-fireworks"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+   "execution_count": 1,
+   "id": "d00d850917865298",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import HumanMessage, SystemMessage\n",
+    "from langchain_fireworks import ChatFireworks"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f28ebf8b-f14f-46c7-9962-8b8dc42e31be",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "\n",
+    "1. Make sure the `langchain-fireworks` package is installed in your environment.\n",
+    "2. Sign in to [Fireworks AI](http://fireworks.ai) for the an API Key to access our models, and make sure it is set as the `FIREWORKS_API_KEY` environment variable.\n",
+    "3. Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-7b-chat. See the full, most up-to-date model list on [app.fireworks.ai](https://app.fireworks.ai)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "d096fb14-8acc-4047-9cd0-c842430c3a1d",
    "metadata": {},
    "outputs": [],
    "source": [
     "import getpass\n",
     "import os\n",
     "\n",
-    "os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Enter your Fireworks API key: \")"
+    "if \"FIREWORKS_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")\n",
+    "\n",
+    "# Initialize a Fireworks chat model\n",
+    "chat = ChatFireworks(model=\"accounts/fireworks/models/mixtral-8x7b-instruct\")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+   "id": "d8f13144-37cf-47a5-b5a0-e3cdf76d9a72",
    "metadata": {},
    "source": [
-    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
-   "metadata": {},
-   "source": [
-    "### Installation\n",
+    "# Calling the Model Directly\n",
     "\n",
-    "The LangChain Fireworks integration lives in the `langchain-fireworks` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-fireworks"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
-   "metadata": {},
-   "source": [
-    "## Instantiation\n",
-    "\n",
-    "Now we can instantiate our model object and generate chat completions:\n",
-    "\n",
-    "- TODO: Update model instantiation with relevant params."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_fireworks import ChatFireworks\n",
-    "\n",
-    "llm = ChatFireworks(\n",
-    "    model=\"accounts/fireworks/models/llama-v3-70b-instruct\",\n",
-    "    temperature=0,\n",
-    "    max_tokens=None,\n",
-    "    timeout=None,\n",
-    "    max_retries=2,\n",
-    "    # other params...\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2b4f3e15",
-   "metadata": {},
-   "source": [
-    "## Invocation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'prompt_tokens': 35, 'total_tokens': 44, 'completion_tokens': 9}, 'model_name': 'accounts/fireworks/models/llama-v3-70b-instruct', 'system_fingerprint': '', 'finish_reason': 'stop', 'logprobs': None}, id='run-df28e69a-ff30-457e-a743-06eb14d01cb0-0', usage_metadata={'input_tokens': 35, 'output_tokens': 9, 'total_tokens': 44})"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "messages = [\n",
-    "    (\n",
-    "        \"system\",\n",
-    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
-    "    ),\n",
-    "    (\"human\", \"I love programming.\"),\n",
-    "]\n",
-    "ai_msg = llm.invoke(messages)\n",
-    "ai_msg"
+    "You can call the model directly with a system and human message to get answers."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+   "id": "72340871-ae2f-415f-b399-0777d32dc379",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Hello! I'm an AI language model, a helpful assistant designed to chat and assist you with any questions or information you might need. I'm here to make your experience as smooth and enjoyable as possible. How can I assist you today?\")"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# ChatFireworks Wrapper\n",
+    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
+    "human_message = HumanMessage(content=\"Who are you?\")\n",
+    "\n",
+    "chat.invoke([system_message, human_message])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "68c6b1fa-2ff7-4a63-8d88-3cec302180b8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"I'm an AI and do not have the ability to experience the weather firsthand. However,\")"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Setting additional parameters: temperature, max_tokens, top_p\n",
+    "chat = ChatFireworks(\n",
+    "    model=\"accounts/fireworks/models/mixtral-8x7b-instruct\",\n",
+    "    temperature=1,\n",
+    "    max_tokens=20,\n",
+    ")\n",
+    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
+    "human_message = HumanMessage(content=\"How's the weather today?\")\n",
+    "chat.invoke([system_message, human_message])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8c44cb36",
+   "metadata": {},
+   "source": [
+    "# Tool Calling\n",
+    "\n",
+    "Fireworks offers the `FireFunction-v2` tool calling model. You can use it for structured output and function calling use cases:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "ee2db682",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "J'adore la programmation.\n"
+      "{'function': {'arguments': '{\"name\": \"Erick\", \"age\": 27}',\n",
+      "              'name': 'ExtractFields'},\n",
+      " 'id': 'call_J0WYP2TLenaFw3UeVU0UnWqx',\n",
+      " 'index': 0,\n",
+      " 'type': 'function'}\n"
      ]
     }
    ],
    "source": [
-    "print(ai_msg.content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
-   "metadata": {},
-   "source": [
-    "## Chaining\n",
+    "from pprint import pprint\n",
     "\n",
-    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
+    "from langchain_core.pydantic_v1 import BaseModel\n",
+    "\n",
+    "\n",
+    "class ExtractFields(BaseModel):\n",
+    "    name: str\n",
+    "    age: int\n",
+    "\n",
+    "\n",
+    "chat = ChatFireworks(\n",
+    "    model=\"accounts/fireworks/models/firefunction-v2\",\n",
+    ").bind_tools([ExtractFields])\n",
+    "\n",
+    "result = chat.invoke(\"I am a 27 year old named Erick\")\n",
+    "\n",
+    "pprint(result.additional_kwargs[\"tool_calls\"][0])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "execution_count": null,
+   "id": "2321a4e6",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ich liebe das Programmieren.', response_metadata={'token_usage': {'prompt_tokens': 30, 'total_tokens': 37, 'completion_tokens': 7}, 'model_name': 'accounts/fireworks/models/llama-v3-70b-instruct', 'system_fingerprint': '', 'finish_reason': 'stop', 'logprobs': None}, id='run-ff3f91ad-ed81-4acf-9f59-7490dc8d8f48-0', usage_metadata={'input_tokens': 30, 'output_tokens': 7, 'total_tokens': 37})"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
-    "        ),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "chain = prompt | llm\n",
-    "chain.invoke(\n",
-    "    {\n",
-    "        \"input_language\": \"English\",\n",
-    "        \"output_language\": \"German\",\n",
-    "        \"input\": \"I love programming.\",\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all ChatFireworks features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_fireworks.chat_models.ChatFireworks.html"
-   ]
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -259,7 +213,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/groq.ipynb

@@ -2,259 +2,298 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
     "sidebar_label: Groq\n",
+    "keywords: [chatgroq]\n",
     "---"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "e49f1e0d",
    "metadata": {},
    "source": [
-    "# ChatGroq\n",
+    "# Groq\n",
     "\n",
-    "This will help you getting started with Groq [chat models](../../concepts.mdx#chat-models). For detailed documentation of all ChatGroq features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_groq.chat_models.ChatGroq.html). For a list of all Groq models, visit this [link](https://console.groq.com/docs/models).\n",
+    "LangChain supports integration with [Groq](https://groq.com/) chat models. Groq specializes in fast AI inference.\n",
     "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/groq) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatGroq](https://api.python.langchain.com/en/latest/chat_models/langchain_groq.chat_models.ChatGroq.html) | [langchain-groq](https://api.python.langchain.com/en/latest/groq_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-groq?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-groq?style=flat-square&label=%20) |\n",
-    "\n",
-    "### Model features\n",
-    "| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
-    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | \n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "To access Groq models you'll need to create a Groq account, get an API key, and install the `langchain-groq` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Head to the [Groq console](https://console.groq.com/keys) to sign up to Groq and generate an API key. Once you've done this set the GROQ_API_KEY environment variable:"
+    "To get started, you'll first need to install the langchain-groq package:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"GROQ_API_KEY\"] = getpass.getpass(\"Enter your Groq API key: \")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
-   "metadata": {},
-   "source": [
-    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
-   "metadata": {},
-   "source": [
-    "### Installation\n",
-    "\n",
-    "The LangChain Groq integration lives in the `langchain-groq` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.1.2\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
    "source": [
     "%pip install -qU langchain-groq"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
    "metadata": {},
    "source": [
-    "## Instantiation\n",
+    "Request an [API key](https://wow.groq.com) and set it as an environment variable:\n",
     "\n",
-    "Now we can instantiate our model object and generate chat completions:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_groq import ChatGroq\n",
+    "```bash\n",
+    "export GROQ_API_KEY=<YOUR API KEY>\n",
+    "```\n",
     "\n",
-    "llm = ChatGroq(\n",
-    "    model=\"mixtral-8x7b-32768\",\n",
-    "    temperature=0,\n",
-    "    max_tokens=None,\n",
-    "    timeout=None,\n",
-    "    max_retries=2,\n",
-    "    # other params...\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2b4f3e15",
-   "metadata": {},
-   "source": [
-    "## Invocation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='I enjoy programming. (The French translation is: \"J\\'aime programmer.\")\\n\\nNote: I chose to translate \"I love programming\" as \"J\\'aime programmer\" instead of \"Je suis amoureux de programmer\" because the latter has a romantic connotation that is not present in the original English sentence.', response_metadata={'token_usage': {'completion_tokens': 73, 'prompt_tokens': 31, 'total_tokens': 104, 'completion_time': 0.1140625, 'prompt_time': 0.003352463, 'queue_time': None, 'total_time': 0.117414963}, 'model_name': 'mixtral-8x7b-32768', 'system_fingerprint': 'fp_c5f20b5bb1', 'finish_reason': 'stop', 'logprobs': None}, id='run-64433c19-eadf-42fc-801e-3071e3c40160-0', usage_metadata={'input_tokens': 31, 'output_tokens': 73, 'total_tokens': 104})"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "messages = [\n",
-    "    (\n",
-    "        \"system\",\n",
-    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
-    "    ),\n",
-    "    (\"human\", \"I love programming.\"),\n",
-    "]\n",
-    "ai_msg = llm.invoke(messages)\n",
-    "ai_msg"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "I enjoy programming. (The French translation is: \"J'aime programmer.\")\n",
-      "\n",
-      "Note: I chose to translate \"I love programming\" as \"J'aime programmer\" instead of \"Je suis amoureux de programmer\" because the latter has a romantic connotation that is not present in the original English sentence.\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(ai_msg.content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
-   "metadata": {},
-   "source": [
-    "## Chaining\n",
+    "Alternatively, you may configure the API key when you initialize ChatGroq.\n",
     "\n",
-    "We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so:"
+    "Here's an example of it in action:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='That\\'s great! I can help you translate English phrases related to programming into German.\\n\\n\"I love programming\" can be translated as \"Ich liebe Programmieren\" in German.\\n\\nHere are some more programming-related phrases translated into German:\\n\\n* \"Programming language\" = \"Programmiersprache\"\\n* \"Code\" = \"Code\"\\n* \"Variable\" = \"Variable\"\\n* \"Function\" = \"Funktion\"\\n* \"Array\" = \"Array\"\\n* \"Object-oriented programming\" = \"Objektorientierte Programmierung\"\\n* \"Algorithm\" = \"Algorithmus\"\\n* \"Data structure\" = \"Datenstruktur\"\\n* \"Debugging\" = \"Fehlersuche\"\\n* \"Compile\" = \"Kompilieren\"\\n* \"Link\" = \"Verknüpfen\"\\n* \"Run\" = \"Ausführen\"\\n* \"Test\" = \"Testen\"\\n* \"Deploy\" = \"Bereitstellen\"\\n* \"Version control\" = \"Versionskontrolle\"\\n* \"Open source\" = \"Open Source\"\\n* \"Software development\" = \"Softwareentwicklung\"\\n* \"Agile methodology\" = \"Agile Methodik\"\\n* \"DevOps\" = \"DevOps\"\\n* \"Cloud computing\" = \"Cloud Computing\"\\n\\nI hope this helps! Let me know if you have any other questions or if you need further translations.', response_metadata={'token_usage': {'completion_tokens': 331, 'prompt_tokens': 25, 'total_tokens': 356, 'completion_time': 0.520006542, 'prompt_time': 0.00250165, 'queue_time': None, 'total_time': 0.522508192}, 'model_name': 'mixtral-8x7b-32768', 'system_fingerprint': 'fp_c5f20b5bb1', 'finish_reason': 'stop', 'logprobs': None}, id='run-74207fb7-85d3-417d-b2b9-621116b75d41-0', usage_metadata={'input_tokens': 25, 'output_tokens': 331, 'total_tokens': 356})"
+       "AIMessage(content=\"Low latency is crucial for Large Language Models (LLMs) because it directly impacts the user experience, model performance, and overall efficiency. Here are some reasons why low latency is essential for LLMs:\\n\\n1. **Real-time Interaction**: LLMs are often used in applications that require real-time interaction, such as chatbots, virtual assistants, and language translation. Low latency ensures that the model responds quickly to user input, providing a seamless and engaging experience.\\n2. **Conversational Flow**: In conversational AI, latency can disrupt the natural flow of conversation. Low latency helps maintain a smooth conversation, allowing users to respond quickly and naturally, without feeling like they're waiting for the model to catch up.\\n3. **Model Performance**: High latency can lead to increased error rates, as the model may struggle to keep up with the input pace. Low latency enables the model to process information more efficiently, resulting in better accuracy and performance.\\n4. **Scalability**: As the number of users and requests increases, low latency becomes even more critical. It allows the model to handle a higher volume of requests without sacrificing performance, making it more scalable and efficient.\\n5. **Resource Utilization**: Low latency can reduce the computational resources required to process requests. By minimizing latency, you can optimize resource allocation, reduce costs, and improve overall system efficiency.\\n6. **User Experience**: High latency can lead to frustration, abandonment, and a poor user experience. Low latency ensures that users receive timely responses, which is essential for building trust and satisfaction.\\n7. **Competitive Advantage**: In applications like customer service or language translation, low latency can be a key differentiator. It can provide a competitive advantage by offering a faster and more responsive experience, setting your application apart from others.\\n8. **Edge Computing**: With the increasing adoption of edge computing, low latency is critical for processing data closer to the user. This reduces latency even further, enabling real-time processing and analysis of data.\\n9. **Real-time Analytics**: Low latency enables real-time analytics and insights, which are essential for applications like sentiment analysis, trend detection, and anomaly detection.\\n10. **Future-Proofing**: As LLMs continue to evolve and become more complex, low latency will become even more critical. By prioritizing low latency now, you'll be better prepared to handle the demands of future LLM applications.\\n\\nIn summary, low latency is vital for LLMs because it ensures a seamless user experience, improves model performance, and enables efficient resource utilization. By prioritizing low latency, you can build more effective, scalable, and efficient LLM applications that meet the demands of real-time interaction and processing.\", response_metadata={'token_usage': {'completion_tokens': 541, 'prompt_tokens': 33, 'total_tokens': 574, 'completion_time': 1.499777658, 'prompt_time': 0.008344704, 'queue_time': None, 'total_time': 1.508122362}, 'model_name': 'llama3-70b-8192', 'system_fingerprint': 'fp_87cbfbbc4d', 'finish_reason': 'stop', 'logprobs': None}, id='run-49dad960-ace8-4cd7-90b3-2db99ecbfa44-0')"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_groq import ChatGroq\n",
     "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
-    "        ),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
+    "chat = ChatGroq(\n",
+    "    temperature=0,\n",
+    "    model=\"llama3-70b-8192\",\n",
+    "    # api_key=\"\" # Optional if not set as an environment variable\n",
     ")\n",
     "\n",
-    "chain = prompt | llm\n",
-    "chain.invoke(\n",
-    "    {\n",
-    "        \"input_language\": \"English\",\n",
-    "        \"output_language\": \"German\",\n",
-    "        \"input\": \"I love programming.\",\n",
-    "    }\n",
-    ")"
+    "system = \"You are a helpful assistant.\"\n",
+    "human = \"{text}\"\n",
+    "prompt = ChatPromptTemplate.from_messages([(\"system\", system), (\"human\", human)])\n",
+    "\n",
+    "chain = prompt | chat\n",
+    "chain.invoke({\"text\": \"Explain the importance of low latency for LLMs.\"})"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
    "metadata": {},
    "source": [
-    "## API reference\n",
+    "You can view the available models [here](https://console.groq.com/docs/models).\n",
     "\n",
-    "For detailed documentation of all ChatGroq features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_groq.chat_models.ChatGroq.html"
+    "## Tool calling\n",
+    "\n",
+    "Groq chat models support [tool calling](/docs/how_to/tool_calling) to generate output matching a specific schema. The model may choose to call multiple tools or the same tool multiple times if appropriate.\n",
+    "\n",
+    "Here's an example:"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'get_current_weather',\n",
+       "  'args': {'location': 'San Francisco', 'unit': 'Celsius'},\n",
+       "  'id': 'call_pydj'},\n",
+       " {'name': 'get_current_weather',\n",
+       "  'args': {'location': 'Tokyo', 'unit': 'Celsius'},\n",
+       "  'id': 'call_jgq3'}]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from typing import Optional\n",
+    "\n",
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def get_current_weather(location: str, unit: Optional[str]):\n",
+    "    \"\"\"Get the current weather in a given location\"\"\"\n",
+    "    return \"Cloudy with a chance of rain.\"\n",
+    "\n",
+    "\n",
+    "tool_model = chat.bind_tools([get_current_weather], tool_choice=\"auto\")\n",
+    "\n",
+    "res = tool_model.invoke(\"What is the weather like in San Francisco and Tokyo?\")\n",
+    "\n",
+    "res.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### `.with_structured_output()`\n",
+    "\n",
+    "You can also use the convenience [`.with_structured_output()`](/docs/how_to/structured_output/#the-with_structured_output-method) method to coerce `ChatGroq` into returning a structured output.\n",
+    "Here is an example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Joke(setup='Why did the cat join a band?', punchline='Because it wanted to be the purr-cussionist!', rating=None)"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class Joke(BaseModel):\n",
+    "    \"\"\"Joke to tell user.\"\"\"\n",
+    "\n",
+    "    setup: str = Field(description=\"The setup of the joke\")\n",
+    "    punchline: str = Field(description=\"The punchline to the joke\")\n",
+    "    rating: Optional[int] = Field(description=\"How funny the joke is, from 1 to 10\")\n",
+    "\n",
+    "\n",
+    "structured_llm = chat.with_structured_output(Joke)\n",
+    "\n",
+    "structured_llm.invoke(\"Tell me a joke about cats\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Behind the scenes, this takes advantage of the above tool calling functionality.\n",
+    "\n",
+    "## Async"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Here is a limerick about the sun:\\n\\nThere once was a sun in the sky,\\nWhose warmth and light caught the eye,\\nIt shone bright and bold,\\nWith a fiery gold,\\nAnd brought life to all, as it flew by.', response_metadata={'token_usage': {'completion_tokens': 51, 'prompt_tokens': 18, 'total_tokens': 69, 'completion_time': 0.144614022, 'prompt_time': 0.00585394, 'queue_time': None, 'total_time': 0.150467962}, 'model_name': 'llama3-70b-8192', 'system_fingerprint': 'fp_2f30b0b571', 'finish_reason': 'stop', 'logprobs': None}, id='run-e42340ba-f0ad-4b54-af61-8308d8ec8256-0')"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chat = ChatGroq(temperature=0, model=\"llama3-70b-8192\")\n",
+    "prompt = ChatPromptTemplate.from_messages([(\"human\", \"Write a Limerick about {topic}\")])\n",
+    "chain = prompt | chat\n",
+    "await chain.ainvoke({\"topic\": \"The Sun\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Streaming"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Silvery glow bright\n",
+      "Luna's gentle light shines down\n",
+      "Midnight's gentle queen"
+     ]
+    }
+   ],
+   "source": [
+    "chat = ChatGroq(temperature=0, model=\"llama3-70b-8192\")\n",
+    "prompt = ChatPromptTemplate.from_messages([(\"human\", \"Write a haiku about {topic}\")])\n",
+    "chain = prompt | chat\n",
+    "for chunk in chain.stream({\"topic\": \"The Moon\"}):\n",
+    "    print(chunk.content, end=\"\", flush=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Passing custom parameters\n",
+    "\n",
+    "You can pass other Groq-specific parameters using the `model_kwargs` argument on initialization. Here's an example of enabling JSON mode:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='{ \"response\": \"That\\'s a tough question! There are eight species of bears found in the world, and each one is unique and amazing in its own way. However, if I had to pick one, I\\'d say the giant panda is a popular favorite among many people. Who can resist those adorable black and white markings?\", \"followup_question\": \"Would you like to know more about the giant panda\\'s habitat and diet?\" }', response_metadata={'token_usage': {'completion_tokens': 89, 'prompt_tokens': 50, 'total_tokens': 139, 'completion_time': 0.249032839, 'prompt_time': 0.011134497, 'queue_time': None, 'total_time': 0.260167336}, 'model_name': 'llama3-70b-8192', 'system_fingerprint': 'fp_2f30b0b571', 'finish_reason': 'stop', 'logprobs': None}, id='run-558ce67e-8c63-43fe-a48f-6ecf181bc922-0')"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chat = ChatGroq(\n",
+    "    model=\"llama3-70b-8192\", model_kwargs={\"response_format\": {\"type\": \"json_object\"}}\n",
+    ")\n",
+    "\n",
+    "system = \"\"\"\n",
+    "You are a helpful assistant.\n",
+    "Always respond with a JSON object with two string keys: \"response\" and \"followup_question\".\n",
+    "\"\"\"\n",
+    "human = \"{question}\"\n",
+    "prompt = ChatPromptTemplate.from_messages([(\"system\", system), (\"human\", human)])\n",
+    "\n",
+    "chain = prompt | chat\n",
+    "\n",
+    "chain.invoke({\"question\": \"what bear is best?\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -268,9 +307,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 5
+ "nbformat_minor": 2
 }

docs/docs/integrations/chat/ibm_watsonx.ipynb

@@ -454,7 +454,7 @@
     "\n",
     "Please note that `ChatWatsonx.bind_tools` is on beta state, so right now we only support `mistralai/mixtral-8x7b-instruct-v01` model.\n",
     "\n",
-    "You should also redefine `max_new_tokens` parameter to get the entire model response. By default `max_new_tokens` is set to 20."
+    "You should also redefine `max_new_tokens` parameter to get the entire model response. By default `max_new_tokens` is set ot 20."
    ]
   },
   {
@@ -577,7 +577,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.1.undefined"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/llamacpp.ipynb

@@ -41,7 +41,7 @@
     "\n",
     "### Installation\n",
     "\n",
-    "The LangChain LlamaCpp integration lives in the `langchain-community` and `llama-cpp-python` packages:"
+    "The LangChain OpenAI integration lives in the `langchain-community` and `llama-cpp-python` packages:"
    ]
   },
   {

docs/docs/integrations/chat/nvidia_ai_endpoints.ipynb

@@ -302,6 +302,9 @@
     "\n",
     "NVIDIA also supports multimodal inputs, meaning you can provide both images and text for the model to reason over. An example model supporting multimodal inputs is `nvidia/neva-22b`.\n",
     "\n",
+    "\n",
+    "These models accept LangChain's standard image formats, and accept `labels`, similar to the Steering LLMs above. In addition to `creativity`, `complexity`, and `verbosity`, these models support a `quality` toggle.\n",
+    "\n",
     "Below is an example use:"
    ]
   },
@@ -444,6 +447,92 @@
     "llm.invoke(f'What\\'s in this image?\\n<img src=\"{base64_with_mime_type}\" />')"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "3e61d868",
+   "metadata": {},
+   "source": [
+    "#### **Advanced Use Case:** Forcing Payload \n",
+    "\n",
+    "You may notice that some newer models may have strong parameter expectations that the LangChain connector may not support by default. For example, we cannot invoke the [Kosmos](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-foundation/models/kosmos-2) model at the time of this notebook's latest release due to the lack of a streaming argument on the server side: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d143e0d6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_nvidia_ai_endpoints import ChatNVIDIA\n",
+    "\n",
+    "kosmos = ChatNVIDIA(model=\"microsoft/kosmos-2\")\n",
+    "\n",
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "# kosmos.invoke(\n",
+    "#     [\n",
+    "#         HumanMessage(\n",
+    "#             content=[\n",
+    "#                 {\"type\": \"text\", \"text\": \"Describe this image:\"},\n",
+    "#                 {\"type\": \"image_url\", \"image_url\": {\"url\": image_url}},\n",
+    "#             ]\n",
+    "#         )\n",
+    "#     ]\n",
+    "# )\n",
+    "\n",
+    "# Exception: [422] Unprocessable Entity\n",
+    "# body -> stream\n",
+    "#   Extra inputs are not permitted (type=extra_forbidden)\n",
+    "# RequestID: 35538c9a-4b45-4616-8b75-7ef816fccf38"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1e230b70",
+   "metadata": {},
+   "source": [
+    "For a simple use case like this, we can actually try to force the payload argument of our underlying client by specifying the `payload_fn` function as follows: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0925b2b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def drop_streaming_key(d):\n",
+    "    \"\"\"Takes in payload dictionary, outputs new payload dictionary\"\"\"\n",
+    "    if \"stream\" in d:\n",
+    "        d.pop(\"stream\")\n",
+    "    return d\n",
+    "\n",
+    "\n",
+    "## Override the payload passthrough. Default is to pass through the payload as is.\n",
+    "kosmos = ChatNVIDIA(model=\"microsoft/kosmos-2\")\n",
+    "kosmos.client.payload_fn = drop_streaming_key\n",
+    "\n",
+    "kosmos.invoke(\n",
+    "    [\n",
+    "        HumanMessage(\n",
+    "            content=[\n",
+    "                {\"type\": \"text\", \"text\": \"Describe this image:\"},\n",
+    "                {\"type\": \"image_url\", \"image_url\": {\"url\": image_url}},\n",
+    "            ]\n",
+    "        )\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fe6e1758",
+   "metadata": {},
+   "source": [
+    "For more advanced or custom use-cases (i.e. supporting the diffusion models), you may be interested in leveraging the `NVEModel` client as a requests backbone. The `NVIDIAEmbeddings` class is a good source of inspiration for this. "
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "137662a6",
@@ -451,7 +540,7 @@
     "id": "137662a6"
    },
    "source": [
-    "## Example usage within a RunnableWithMessageHistory"
+    "## Example usage within a Conversation Chains"
    ]
   },
   {
@@ -461,7 +550,7 @@
     "id": "79efa62d"
    },
    "source": [
-    "Like any other integration, ChatNVIDIA is fine to support chat utilities like RunnableWithMessageHistory which is analogous to using `ConversationChain`. Below, we show the [LangChain RunnableWithMessageHistory](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html) example applied to the `mistralai/mixtral-8x22b-instruct-v0.1` model."
+    "Like any other integration, ChatNVIDIA is fine to support chat utilities like conversation buffers by default. Below, we show the [LangChain ConversationBufferMemory](https://python.langchain.com/docs/modules/memory/types/buffer) example applied to the `mistralai/mixtral-8x22b-instruct-v0.1` model."
    ]
   },
   {
@@ -483,19 +572,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_core.chat_history import InMemoryChatMessageHistory\n",
-    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
-    "\n",
-    "# store is a dictionary that maps session IDs to their corresponding chat histories.\n",
-    "store = {}  # memory is maintained outside the chain\n",
-    "\n",
-    "\n",
-    "# A function that returns the chat history for a given session ID.\n",
-    "def get_session_history(session_id: str) -> InMemoryChatMessageHistory:\n",
-    "    if session_id not in store:\n",
-    "        store[session_id] = InMemoryChatMessageHistory()\n",
-    "    return store[session_id]\n",
-    "\n",
+    "from langchain.chains import ConversationChain\n",
+    "from langchain.memory import ConversationBufferMemory\n",
     "\n",
     "chat = ChatNVIDIA(\n",
     "    model=\"mistralai/mixtral-8x22b-instruct-v0.1\",\n",
@@ -504,18 +582,24 @@
     "    top_p=1.0,\n",
     ")\n",
     "\n",
-    "#  Define a RunnableConfig object, with a `configurable` key. session_id determines thread\n",
-    "config = {\"configurable\": {\"session_id\": \"1\"}}\n",
-    "\n",
-    "conversation = RunnableWithMessageHistory(\n",
-    "    chat,\n",
-    "    get_session_history,\n",
-    ")\n",
-    "\n",
-    "conversation.invoke(\n",
-    "    \"Hi I'm Srijan Dubey.\",  # input or query\n",
-    "    config=config,\n",
-    ")"
+    "conversation = ConversationChain(llm=chat, memory=ConversationBufferMemory())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f644ff28",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 268
+    },
+    "id": "f644ff28",
+    "outputId": "bae354cc-2118-4e01-ce20-a717ac94d27d"
+   },
+   "outputs": [],
+   "source": [
+    "conversation.invoke(\"Hi there!\")[\"response\"]"
    ]
   },
   {
@@ -532,10 +616,9 @@
    },
    "outputs": [],
    "source": [
-    "conversation.invoke(\n",
-    "    \"I'm doing well! Just having a conversation with an AI.\",\n",
-    "    config=config,\n",
-    ")"
+    "conversation.invoke(\"I'm doing well! Just having a conversation with an AI.\")[\n",
+    "    \"response\"\n",
+    "]"
    ]
   },
   {
@@ -552,83 +635,7 @@
    },
    "outputs": [],
    "source": [
-    "conversation.invoke(\n",
-    "    \"Tell me about yourself.\",\n",
-    "    config=config,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f3cbbba0",
-   "metadata": {},
-   "source": [
-    "## Tool calling\n",
-    "\n",
-    "Starting in v0.2, `ChatNVIDIA` supports [bind_tools](https://api.python.langchain.com/en/latest/language_models/langchain_core.language_models.chat_models.BaseChatModel.html#langchain_core.language_models.chat_models.BaseChatModel.bind_tools).\n",
-    "\n",
-    "`ChatNVIDIA` provides integration with the variety of models on [build.nvidia.com](https://build.nvidia.com) as well as local NIMs. Not all these models are trained for tool calling. Be sure to select a model that does have tool calling for your experimention and applications."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6f7b535e",
-   "metadata": {},
-   "source": [
-    "You can get a list of models that are known to support tool calling with,"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e36c8911",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tool_models = [\n",
-    "    model for model in ChatNVIDIA.get_available_models() if model.supports_tools\n",
-    "]\n",
-    "tool_models"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b01d75a7",
-   "metadata": {},
-   "source": [
-    "With a tool capable model,"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bd54f174",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.pydantic_v1 import Field\n",
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def get_current_weather(\n",
-    "    location: str = Field(..., description=\"The location to get the weather for.\"),\n",
-    "):\n",
-    "    \"\"\"Get the current weather for a location.\"\"\"\n",
-    "    ...\n",
-    "\n",
-    "\n",
-    "llm = ChatNVIDIA(model=tool_models[0].id).bind_tools(tools=[get_current_weather])\n",
-    "response = llm.invoke(\"What is the weather in Boston?\")\n",
-    "response.tool_calls"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e08df68c",
-   "metadata": {},
-   "source": [
-    "See [How to use chat models to call tools](https://python.langchain.com/v0.2/docs/how_to/tool_calling/) for additional examples."
+    "conversation.invoke(\"Tell me about yourself.\")[\"response\"]"
    ]
   }
  ],
@@ -651,7 +658,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.10.2"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/oci_generative_ai.ipynb

@@ -33,7 +33,7 @@
     "### Model features\n",
     "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
     "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | \n",
+    "| ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | \n",
     "\n",
     "## Setup\n",
     "\n",

docs/docs/integrations/chat/ollama.ipynb

@@ -2,7 +2,6 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "afaf8039",
    "metadata": {},
    "source": [
     "---\n",
@@ -12,7 +11,6 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e49f1e0d",
    "metadata": {},
    "source": [
     "# ChatOllama\n",
@@ -25,18 +23,6 @@
     "\n",
     "For a complete list of supported models and model variants, see the [Ollama model library](https://github.com/jmorganca/ollama#model-library).\n",
     "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/ollama) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatOllama](https://api.python.langchain.com/en/latest/chat_models/langchain_ollama.chat_models.ChatOllama.html) | [langchain-ollama](https://api.python.langchain.com/en/latest/ollama_api_reference.html) | ✅ | ❌ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ollama?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ollama?style=flat-square&label=%20) |\n",
-    "\n",
-    "### Model features\n",
-    "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
-    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | \n",
-    "\n",
     "## Setup\n",
     "\n",
     "First, follow [these instructions](https://github.com/jmorganca/ollama) to set up and run a local Ollama instance:\n",
@@ -54,285 +40,307 @@
     "* Specify the exact version of the model of interest as such `ollama pull vicuna:13b-v1.5-16k-q4_0` (View the [various tags for the `Vicuna`](https://ollama.ai/library/vicuna/tags) model in this instance)\n",
     "* To view all pulled models, use `ollama list`\n",
     "* To chat directly with a model from the command line, use `ollama run <name-of-model>`\n",
-    "* View the [Ollama documentation](https://github.com/jmorganca/ollama) for more commands. Run `ollama help` in the terminal to see available commands too.\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
-   "metadata": {},
-   "source": [
-    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+    "* View the [Ollama documentation](https://github.com/jmorganca/ollama) for more commands. Run `ollama help` in the terminal to see available commands too.\n",
+    "\n",
+    "## Usage\n",
+    "\n",
+    "You can see a full list of supported parameters on the [API reference page](https://api.python.langchain.com/en/latest/llms/langchain.llms.ollama.Ollama.html).\n",
+    "\n",
+    "If you are using a LLaMA `chat` model (e.g., `ollama pull llama3`) then you can use the `ChatOllama` interface.\n",
+    "\n",
+    "This includes [special tokens](https://huggingface.co/blog/llama2#how-to-prompt-llama-2) for system message and user input.\n",
+    "\n",
+    "## Interacting with Models \n",
+    "\n",
+    "Here are a few ways to interact with pulled local models\n",
+    "\n",
+    "#### In the terminal:\n",
+    "\n",
+    "* All of your local models are automatically served on `localhost:11434`\n",
+    "* Run `ollama run <name-of-model>` to start interacting via the command line directly\n",
+    "\n",
+    "#### Via an API\n",
+    "\n",
+    "Send an `application/json` request to the API endpoint of Ollama to interact.\n",
+    "\n",
+    "```bash\n",
+    "curl http://localhost:11434/api/generate -d '{\n",
+    "  \"model\": \"llama3\",\n",
+    "  \"prompt\":\"Why is the sky blue?\"\n",
+    "}'\n",
+    "```\n",
+    "\n",
+    "See the Ollama [API documentation](https://github.com/jmorganca/ollama/blob/main/docs/api.md) for all endpoints.\n",
+    "\n",
+    "#### Via LangChain\n",
+    "\n",
+    "See a typical basic example of using Ollama via the `ChatOllama` chat model in your LangChain application. \n",
+    "\n",
+    "View the [API Reference for ChatOllama](https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.ollama.ChatOllama.html#langchain_community.chat_models.ollama.ChatOllama) for more."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
-   "metadata": {},
-   "source": [
-    "### Installation\n",
-    "\n",
-    "The LangChain Ollama integration lives in the `langchain-ollama` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-ollama"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
-   "metadata": {},
-   "source": [
-    "## Instantiation\n",
-    "\n",
-    "Now we can instantiate our model object and generate chat completions:\n",
-    "\n",
-    "- TODO: Update model instantiation with relevant params."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_ollama import ChatOllama\n",
-    "\n",
-    "llm = ChatOllama(\n",
-    "    model=\"llama3\",\n",
-    "    temperature=0,\n",
-    "    # other params...\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2b4f3e15",
-   "metadata": {},
-   "source": [
-    "## Invocation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Je adore le programmation.\\n\\n(Note: \"programmation\" is not commonly used in French, but I translated it as \"le programmation\" to maintain the same grammatical structure and meaning as the original English sentence.)', response_metadata={'model': 'llama3', 'created_at': '2024-07-22T17:43:54.731273Z', 'message': {'role': 'assistant', 'content': ''}, 'done_reason': 'stop', 'done': True, 'total_duration': 11094839375, 'load_duration': 10121854667, 'prompt_eval_count': 36, 'prompt_eval_duration': 146569000, 'eval_count': 46, 'eval_duration': 816593000}, id='run-befccbdc-e1f9-42a9-85cf-e69b926d6b8b-0', usage_metadata={'input_tokens': 36, 'output_tokens': 46, 'total_tokens': 82})"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import AIMessage\n",
-    "\n",
-    "messages = [\n",
-    "    (\n",
-    "        \"system\",\n",
-    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
-    "    ),\n",
-    "    (\"human\", \"I love programming.\"),\n",
-    "]\n",
-    "ai_msg = llm.invoke(messages)\n",
-    "ai_msg"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Je adore le programmation.\n",
+      "Why did the astronaut break up with his girlfriend?\n",
       "\n",
-      "(Note: \"programmation\" is not commonly used in French, but I translated it as \"le programmation\" to maintain the same grammatical structure and meaning as the original English sentence.)\n"
+      "Because he needed space!\n"
      ]
     }
    ],
    "source": [
-    "print(ai_msg.content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
-   "metadata": {},
-   "source": [
-    "## Chaining\n",
-    "\n",
-    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ich liebe Programmieren!\\n\\n(Note: \"Ich liebe\" means \"I love\", \"Programmieren\" is the verb for \"programming\")', response_metadata={'model': 'llama3', 'created_at': '2024-07-04T04:22:33.864132Z', 'message': {'role': 'assistant', 'content': ''}, 'done_reason': 'stop', 'done': True, 'total_duration': 1310800083, 'load_duration': 1782000, 'prompt_eval_count': 16, 'prompt_eval_duration': 250199000, 'eval_count': 29, 'eval_duration': 1057192000}, id='run-cbadbe59-2de2-4ec0-a18a-b3220226c3d2-0')"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
+    "# LangChain supports many other chat models. Here, we're using Ollama\n",
+    "from langchain_community.chat_models import ChatOllama\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
-    "        ),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
+    "# supports many more optional parameters. Hover on your `ChatOllama(...)`\n",
+    "# class to view the latest available supported parameters\n",
+    "llm = ChatOllama(model=\"llama3\")\n",
+    "prompt = ChatPromptTemplate.from_template(\"Tell me a short joke about {topic}\")\n",
     "\n",
-    "chain = prompt | llm\n",
-    "chain.invoke(\n",
-    "    {\n",
-    "        \"input_language\": \"English\",\n",
-    "        \"output_language\": \"German\",\n",
-    "        \"input\": \"I love programming.\",\n",
-    "    }\n",
-    ")"
+    "# using LangChain Expressive Language chain syntax\n",
+    "# learn more about the LCEL on\n",
+    "# /docs/concepts/#langchain-expression-language-lcel\n",
+    "chain = prompt | llm | StrOutputParser()\n",
+    "\n",
+    "# for brevity, response is printed in terminal\n",
+    "# You can use LangServe to deploy your application for\n",
+    "# production\n",
+    "print(chain.invoke({\"topic\": \"Space travel\"}))"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "0f51345d-0a9d-43f1-8fca-d0662cb8e21b",
    "metadata": {},
    "source": [
-    "## Tool calling\n",
-    "\n",
-    "We can use [tool calling](https://blog.langchain.dev/improving-core-tool-interfaces-and-docs-in-langchain/) with an LLM [that has been fine-tuned for tool use](https://ollama.com/library/llama3-groq-tool-use): \n",
-    "\n",
-    "```\n",
-    "ollama pull llama3-groq-tool-use\n",
-    "```\n",
-    "\n",
-    "We can just pass normal Python functions directly as tools."
+    "LCEL chains, out of the box, provide extra functionalities, such as streaming of responses, and async support"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
-   "id": "5250bceb-1029-41ff-b447-983518704d88",
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "[{'name': 'validate_user',\n",
-       "  'args': {'addresses': ['123 Fake St, Boston MA',\n",
-       "    '234 Pretend Boulevard, Houston TX'],\n",
-       "   'user_id': 123},\n",
-       "  'id': 'fe2148d3-95fb-48e9-845a-4bfecc1f1f96',\n",
-       "  'type': 'tool_call'}]"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Why\n",
+      " did\n",
+      " the\n",
+      " astronaut\n",
+      " break\n",
+      " up\n",
+      " with\n",
+      " his\n",
+      " girlfriend\n",
+      " before\n",
+      " going\n",
+      " to\n",
+      " Mars\n",
+      "?\n",
+      "\n",
+      "\n",
+      "Because\n",
+      " he\n",
+      " needed\n",
+      " space\n",
+      "!\n",
+      "\n"
+     ]
     }
    ],
    "source": [
-    "from typing import List\n",
+    "topic = {\"topic\": \"Space travel\"}\n",
     "\n",
-    "from langchain_ollama import ChatOllama\n",
-    "from typing_extensions import TypedDict\n",
-    "\n",
-    "\n",
-    "def validate_user(user_id: int, addresses: List) -> bool:\n",
-    "    \"\"\"Validate user using historical addresses.\n",
-    "\n",
-    "    Args:\n",
-    "        user_id: (int) the user ID.\n",
-    "        addresses: Previous addresses.\n",
-    "    \"\"\"\n",
-    "    return True\n",
-    "\n",
-    "\n",
-    "llm = ChatOllama(\n",
-    "    model=\"llama3-groq-tool-use\",\n",
-    "    temperature=0,\n",
-    ").bind_tools([validate_user])\n",
-    "\n",
-    "result = llm.invoke(\n",
-    "    \"Could you validate user 123? They previously lived at \"\n",
-    "    \"123 Fake St in Boston MA and 234 Pretend Boulevard in \"\n",
-    "    \"Houston TX.\"\n",
-    ")\n",
-    "result.tool_calls"
+    "for chunks in chain.stream(topic):\n",
+    "    print(chunks)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "2bb034ff-218f-4865-afea-3f5e57d3bdee",
    "metadata": {},
    "source": [
-    "We look at the LangSmith trace to see that the tool call was performed: \n",
+    "For streaming async support, here's an example - all possible via the single chain created above."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "topic = {\"topic\": \"Space travel\"}\n",
     "\n",
-    "https://smith.langchain.com/public/4169348a-d6be-45df-a7cf-032f6baa4697/r\n",
-    "\n",
-    "In particular, the trace shows how the tool schema was populated."
+    "async for chunks in chain.astream(topic):\n",
+    "    print(chunks)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Take a look at the [LangChain Expressive Language (LCEL) Interface](/docs/concepts#interface) for the other available interfaces for use when a chain is created.\n",
+    "\n",
+    "## Building from source\n",
+    "\n",
+    "For up to date instructions on building from source, check the Ollama documentation on [Building from Source](https://github.com/ollama/ollama?tab=readme-ov-file#building)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Extraction\n",
+    " \n",
+    "Use the latest version of Ollama and supply the [`format`](https://github.com/jmorganca/ollama/blob/main/docs/api.md#json-mode) flag. The `format` flag will force the model to produce the response in JSON.\n",
+    "\n",
+    "> **Note:** You can also try out the experimental [OllamaFunctions](/docs/integrations/chat/ollama_functions) wrapper for convenience."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_models import ChatOllama\n",
+    "\n",
+    "llm = ChatOllama(model=\"llama3\", format=\"json\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content='{ \"morning\": \"blue\", \"noon\": \"clear blue\", \"afternoon\": \"hazy yellow\", \"evening\": \"orange-red\" }\\n\\n  \\n\\n\\n\\n\\n\\n  \\n\\n\\n\\n\\n\\n  \\n\\n\\n\\n\\n\\n  \\n\\n\\n\\n\\n\\n  \\n\\n\\n\\n\\n\\n  \\n\\n\\n\\n\\n\\n  \\n\\n\\n\\n\\n\\n  \\n\\n\\n\\n\\n\\n  \\n\\n\\n\\n\\n\\n  \\n\\n\\n\\n\\n\\n ' id='run-e893700f-e2d0-4df8-ad86-17525dcee318-0'\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "messages = [\n",
+    "    HumanMessage(\n",
+    "        content=\"What color is the sky at different times of the day? Respond using JSON\"\n",
+    "    )\n",
+    "]\n",
+    "\n",
+    "chat_model_response = llm.invoke(messages)\n",
+    "print(chat_model_response)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Name: John\n",
+      "Age: 35\n",
+      "Likes: Pizza\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "\n",
+    "from langchain_community.chat_models import ChatOllama\n",
+    "from langchain_core.messages import HumanMessage\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "json_schema = {\n",
+    "    \"title\": \"Person\",\n",
+    "    \"description\": \"Identifying information about a person.\",\n",
+    "    \"type\": \"object\",\n",
+    "    \"properties\": {\n",
+    "        \"name\": {\"title\": \"Name\", \"description\": \"The person's name\", \"type\": \"string\"},\n",
+    "        \"age\": {\"title\": \"Age\", \"description\": \"The person's age\", \"type\": \"integer\"},\n",
+    "        \"fav_food\": {\n",
+    "            \"title\": \"Fav Food\",\n",
+    "            \"description\": \"The person's favorite food\",\n",
+    "            \"type\": \"string\",\n",
+    "        },\n",
+    "    },\n",
+    "    \"required\": [\"name\", \"age\"],\n",
+    "}\n",
+    "\n",
+    "llm = ChatOllama(model=\"llama2\")\n",
+    "\n",
+    "messages = [\n",
+    "    HumanMessage(\n",
+    "        content=\"Please tell me about a person using the following JSON schema:\"\n",
+    "    ),\n",
+    "    HumanMessage(content=\"{dumps}\"),\n",
+    "    HumanMessage(\n",
+    "        content=\"Now, considering the schema, tell me about a person named John who is 35 years old and loves pizza.\"\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(messages)\n",
+    "dumps = json.dumps(json_schema, indent=2)\n",
+    "\n",
+    "chain = prompt | llm | StrOutputParser()\n",
+    "\n",
+    "print(chain.invoke({\"dumps\": dumps}))"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "4c5e0197",
    "metadata": {},
    "source": [
     "## Multi-modal\n",
     "\n",
-    "Ollama has support for multi-modal LLMs, such as [bakllava](https://ollama.com/library/bakllava) and [llava](https://ollama.com/library/llava).\n",
+    "Ollama has support for multi-modal LLMs, such as [bakllava](https://ollama.ai/library/bakllava) and [llava](https://ollama.ai/library/llava).\n",
     "\n",
-    "    ollama pull bakllava\n",
+    "Browse the full set of versions for models with `tags`, such as [Llava](https://ollama.ai/library/llava/tags).\n",
     "\n",
-    "Be sure to update Ollama so that you have the most recent version to support multi-modal."
+    "Download the desired LLM via `ollama pull bakllava`\n",
+    "\n",
+    "Be sure to update Ollama so that you have the most recent version to support multi-modal.\n",
+    "\n",
+    "Check out the typical example of how to use ChatOllama multi-modal support below:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "36c9b1c2",
+   "execution_count": 18,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install --upgrade --quiet  pillow"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -391,8 +399,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
-   "id": "32b3ba7b",
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -404,8 +411,8 @@
     }
    ],
    "source": [
+    "from langchain_community.chat_models import ChatOllama\n",
     "from langchain_core.messages import HumanMessage\n",
-    "from langchain_ollama import ChatOllama\n",
     "\n",
     "llm = ChatOllama(model=\"bakllava\", temperature=0)\n",
     "\n",
@@ -442,12 +449,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
    "metadata": {},
    "source": [
-    "## API reference\n",
+    "## Concurrency Features\n",
     "\n",
-    "For detailed documentation of all ChatOllama features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_ollama.chat_models.ChatOllama.html"
+    "Ollama supports concurrency inference for a single model, and or loading multiple models simulatenously (at least [version 0.1.33](https://github.com/ollama/ollama/releases)).\n",
+    "\n",
+    "Start the Ollama server with:\n",
+    "\n",
+    "* `OLLAMA_NUM_PARALLEL`: Handle multiple requests simultaneously for a single model\n",
+    "* `OLLAMA_MAX_LOADED_MODELS`: Load multiple models simultaneously\n",
+    "\n",
+    "Example: `OLLAMA_NUM_PARALLEL=4 OLLAMA_MAX_LOADED_MODELS=4 ollama serve`\n",
+    "\n",
+    "Learn more about configuring Ollama server in [the official guide](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-configure-ollama-server)."
    ]
   }
  ],
@@ -471,5 +486,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 5
+ "nbformat_minor": 4
 }