core[patch]: Release 0.2.29 (#25126)

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>

.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
@@ -28,5 +28,3 @@ services:
 networks:
   langchain-network:
     driver: bridge
-    
-    

.github/ISSUE_TEMPLATE/config.yml

@@ -4,9 +4,6 @@ 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

@@ -350,11 +350,7 @@ 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
 
@@ -484,10 +480,16 @@ 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(
@@ -524,9 +526,13 @@ 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 = {
@@ -547,6 +553,7 @@ if __name__ == "__main__":
         "obi1kenobi",
         "langchain-infra",
         "jacoblee93",
+        "isahers1",
         "dqbd",
         "bracesproul",
         "akira",
@@ -558,7 +565,7 @@ 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,
@@ -614,9 +621,7 @@ 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")
@@ -629,9 +634,7 @@ 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)
@@ -640,4 +643,4 @@ 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

@@ -1,7 +1,12 @@
+import glob
 import json
-import sys
 import os
-from typing import Dict
+import sys
+import tomllib
+from collections import defaultdict
+from typing import Dict, List, Set
+from pathlib import Path
+
 
 LANGCHAIN_DIRS = [
     "libs/core",
@@ -11,6 +16,126 @@ 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
+    }
+
+
+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"]
+
+        pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
+        for dep in [
+            *pyproject["dependencies"].keys(),
+            *pyproject["group"]["test"]["dependencies"].keys(),
+        ]:
+            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
+
+
+def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
+    updated = set()
+    for dir_ in dirs_to_eval:
+        # handle core manually because it has so many dependents
+        if "core" in dir_:
+            updated.add(dir_)
+            continue
+        pkg = "langchain-" + dir_.split("/")[-1]
+        updated.update(dependents[pkg])
+        updated.add(dir_)
+    return list(updated)
+
+
+def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
+    if dir_ == "libs/core":
+        return [
+            {"working-directory": dir_, "python-version": f"3.{v}"}
+            for v in range(8, 13)
+        ]
+    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:]
 
@@ -21,10 +146,11 @@ if __name__ == "__main__":
     }
     docs_edited = False
 
-    if len(files) == 300:
+    if len(files) >= 300:
         # max diff length is 300 files - there are likely files missing
-        raise ValueError("Max diff reached. Please manually run CI on changed libs.")
-
+        dirs_to_run["lint"] = all_package_dirs()
+        dirs_to_run["test"] = all_package_dirs()
+        dirs_to_run["extended-test"] = set(LANGCHAIN_DIRS)
     for file in files:
         if any(
             file.startswith(dir_)
@@ -81,14 +207,25 @@ if __name__ == "__main__":
                 docs_edited = True
             dirs_to_run["lint"].add(".")
 
-    outputs = {
-        "dirs-to-lint": list(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"]
-        ),
-        "dirs-to-test": list(dirs_to_run["test"] | dirs_to_run["extended-test"]),
-        "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
-        "docs-edited": "true" if docs_edited else "",
+    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",
+        ]
     }
-    for key, value in outputs.items():
+    map_job_to_configs["test-doc-imports"] = (
+        [{"python-version": "3.12"}] if docs_edited else []
+    )
+
+    for key, value in map_job_to_configs.items():
         json_output = json.dumps(value)
         print(f"{key}={json_output}")

.github/scripts/check_prerelease_dependencies.py

@@ -0,0 +1,35 @@
+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

@@ -1,6 +1,11 @@
 import sys
 
-import tomllib
+if sys.version_info >= (3, 11):
+    import tomllib
+else:
+    # for python 3.10 and below, which doesnt have stdlib tomllib
+    import tomli as tomllib
+
 from packaging.version import parse as parse_version
 import re
 
@@ -9,8 +14,11 @@ 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
@@ -37,7 +45,7 @@ def get_min_version(version: str) -> str:
     raise ValueError(f"Unrecognized version format: {version}")
 
 
-def get_min_version_from_toml(toml_path: str):
+def get_min_version_from_toml(toml_path: str, versions_for: str):
     # Parse the TOML file
     with open(toml_path, "rb") as file:
         toml_data = tomllib.load(file)
@@ -50,6 +58,10 @@ def get_min_version_from_toml(toml_path: 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
@@ -70,10 +82,10 @@ def get_min_version_from_toml(toml_path: 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)
+    min_versions = get_min_version_from_toml(toml_file, versions_for)
 
-    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

@@ -7,6 +7,10 @@ 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"
@@ -17,21 +21,14 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: "poetry run pytest -m compile tests/integration_tests #${{ matrix.python-version }}"
+    name: "poetry run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: compile-integration

.github/workflows/_dependencies.yml

@@ -11,6 +11,10 @@ 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"
@@ -21,21 +25,14 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: dependency checks ${{ matrix.python-version }}
+    name: dependency checks ${{ inputs.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: pydantic-cross-compat

.github/workflows/_integration_test.yml

@@ -6,30 +6,28 @@ on:
       working-directory:
         required: true
         type: string
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
-    environment: Scheduled testing
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.11"
-    name: Python ${{ matrix.python-version }}
+    name: Python ${{ inputs.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core
@@ -53,8 +51,15 @@ jobs:
         shell: bash
         env:
           AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
+          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

.github/workflows/_lint.yml

@@ -11,6 +11,10 @@ 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"
@@ -21,27 +25,15 @@ env:
 
 jobs:
   build:
-    name: "make lint #${{ matrix.python-version }}"
+    name: "make lint #${{ inputs.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"
-          - "3.11"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: lint-with-extras
@@ -86,7 +78,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache
-          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
 
       - name: Analysing the code with our lint
@@ -120,7 +112,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache_test
-          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ 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

@@ -122,7 +122,6 @@ jobs:
           fi
           {
             echo 'release-body<<EOF'
-            echo "# Release $TAG"
             echo $PREAMBLE
             echo
             git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR
@@ -135,6 +134,7 @@ jobs:
       - release-notes
     uses:
       ./.github/workflows/_test_release.yml
+    permissions: write-all
     with:
       working-directory: ${{ inputs.working-directory }}
       dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
@@ -189,7 +189,7 @@ jobs:
             --extra-index-url https://test.pypi.org/simple/ \
             "$PKG_NAME==$VERSION" || \
           ( \
-            sleep 5 && \
+            sleep 15 && \
             poetry run pip install \
               --extra-index-url https://test.pypi.org/simple/ \
               "$PKG_NAME==$VERSION" \
@@ -202,7 +202,7 @@ jobs:
           poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: poetry install --with test,test_integration
+        run: poetry install --with test
         working-directory: ${{ inputs.working-directory }}
 
       # Overwrite the local version of the package with the test PyPI version.
@@ -221,12 +221,17 @@ 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 $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
+          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release)"
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
           echo "min-versions=$min_versions"
 
@@ -245,6 +250,10 @@ jobs:
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
+      - name: Import integration test dependencies
+        run: poetry install --with test,test_integration
+        working-directory: ${{ inputs.working-directory }}
+
       - name: Run integration tests
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         env:
@@ -281,6 +290,7 @@ 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

@@ -11,6 +11,10 @@ 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"
@@ -21,21 +25,14 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: "make test #${{ matrix.python-version }}"
+    name: "make test #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core
@@ -68,3 +65,22 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$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

@@ -2,6 +2,11 @@ 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"
@@ -9,18 +14,14 @@ env:
 jobs:
   build:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.11"
-    name: "check doc imports #${{ matrix.python-version }}"
+    name: "check doc imports #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           cache-key: core
 

.github/workflows/check-broken-links.yml

@@ -7,6 +7,7 @@ on:
 
 jobs:
   check-links:
+    if: github.repository_owner == 'langchain-ai'
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4

.github/workflows/check_diffs.yml

@@ -26,97 +26,103 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.11'
       - id: files
         uses: Ana06/get-changed-files@v2.2.0
       - id: set-matrix
         run: |
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
-      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: ${{ 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 }}
   lint:
-    name: cd ${{ matrix.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-lint != '[]' }}
+    if: ${{ needs.build.outputs.lint != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-lint) }}
+        job-configs: ${{ fromJson(needs.build.outputs.lint) }}
     uses: ./.github/workflows/_lint.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   test:
-    name: cd ${{ matrix.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    if: ${{ needs.build.outputs.test != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+        job-configs: ${{ fromJson(needs.build.outputs.test) }}
     uses: ./.github/workflows/_test.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   test-doc-imports:
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' || needs.build.outputs.docs-edited }}
-    uses: ./.github/workflows/_test_doc_imports.yml
-    secrets: inherit
-
-  compile-integration-tests:
-    name: cd ${{ matrix.working-directory }}
-    needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    if: ${{ needs.build.outputs.test-doc-imports != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+        job-configs: ${{ fromJson(needs.build.outputs.test-doc-imports) }}
+    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 }}
+    needs: [ build ]
+    if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
+    strategy:
+      matrix:
+        job-configs: ${{ fromJson(needs.build.outputs.compile-integration-tests) }}
     uses: ./.github/workflows/_compile_integration_test.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   dependencies:
-    name: cd ${{ matrix.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    if: ${{ needs.build.outputs.dependencies != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+        job-configs: ${{ fromJson(needs.build.outputs.dependencies) }}
     uses: ./.github/workflows/_dependencies.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   extended-tests:
-    name: "cd ${{ matrix.working-directory }} / make extended_tests #${{ matrix.python-version }}"
+    name: "cd ${{ matrix.job-configs.working-directory }} / make extended_tests #${{ matrix.job-configs.python-version }}"
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-extended-test != '[]' }}
+    if: ${{ needs.build.outputs.extended-tests != '[]' }}
     strategy:
       matrix:
         # note different variable for extended test dirs
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-extended-test) }}
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
+        job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
     runs-on: ubuntu-latest
     defaults:
       run:
-        working-directory: ${{ matrix.working-directory }}
+        working-directory: ${{ matrix.job-configs.working-directory }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.job-configs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ matrix.job-configs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ matrix.working-directory }}
+          working-directory: ${{ matrix.job-configs.working-directory }}
           cache-key: extended
 
       - name: Install dependencies

.github/workflows/check_new_docs.yml

@@ -0,0 +1,36 @@
+---
+name: Integration docs lint
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+
+# If another push to the same PR or branch happens while this workflow is still running,
+# cancel the earlier run in favor of the next run.
+#
+# There's no point in testing an outdated version of the code. GitHub only allows
+# a limited number of job runners to be active at the same time, so it's better to cancel
+# pointless jobs early so that more useful jobs can run sooner.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          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/people.yml

@@ -16,6 +16,7 @@ jobs:
   langchain-people:
     if: github.repository_owner == 'langchain-ai'
     runs-on: ubuntu-latest
+    permissions: write-all
     steps:
       - name: Dump GitHub context
         env:

.github/workflows/scheduled_test.yml

@@ -10,6 +10,7 @@ env:
 
 jobs:
   build:
+    if: github.repository_owner == 'langchain-ai'
     name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
     runs-on: ubuntu-latest
     strategy:
@@ -26,11 +27,9 @@ jobs:
           - "libs/partners/groq"
           - "libs/partners/mistralai"
           - "libs/partners/together"
-          - "libs/partners/cohere"
           - "libs/partners/google-vertexai"
           - "libs/partners/google-genai"
           - "libs/partners/aws"
-          - "libs/partners/nvidia-ai-endpoints"
 
     steps:
       - uses: actions/checkout@v4
@@ -40,14 +39,6 @@ jobs:
         with:
           repository: langchain-ai/langchain-google
           path: langchain-google
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-nvidia
-          path: langchain-nvidia
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-cohere
-          path: langchain-cohere
       - uses: actions/checkout@v4
         with:
           repository: langchain-ai/langchain-aws
@@ -57,13 +48,9 @@ jobs:
         run: |
           rm -rf \
             langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/nvidia-ai-endpoints \
-            langchain/libs/partners/cohere
+            langchain/libs/partners/google-vertexai
           mv langchain-google/libs/genai langchain/libs/partners/google-genai
           mv langchain-google/libs/vertexai langchain/libs/partners/google-vertexai
-          mv langchain-nvidia/libs/ai-endpoints langchain/libs/partners/nvidia-ai-endpoints
-          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 }}
@@ -122,8 +109,6 @@ jobs:
           rm -rf \
             langchain/libs/partners/google-genai \
             langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/nvidia-ai-endpoints \
-            langchain/libs/partners/cohere \
             langchain/libs/partners/aws
 
       - name: Ensure the tests did not create any additional files

README.md

@@ -7,11 +7,9 @@
 [![PyPI - License](https://img.shields.io/pypi/l/langchain-core?style=flat-square)](https://opensource.org/licenses/MIT)
 [![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-core?style=flat-square)](https://pypistats.org/packages/langchain-core)
 [![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=flat-square)](https://star-history.com/#langchain-ai/langchain)
-[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain?style=flat-square)](https://libraries.io/github/langchain-ai/langchain)
 [![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).
@@ -38,24 +36,25 @@ conda install langchain -c conda-forge
 
 For these applications, LangChain simplifies the entire application lifecycle:
 
-- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel) and [components](https://python.langchain.com/v0.2/docs/concepts/#components). Integrate with hundreds of [third-party providers](https://python.langchain.com/v0.2/docs/integrations/platforms/).
+- **Open-source libraries**:  Build your applications using LangChain's open-source [building blocks](https://python.langchain.com/v0.2/docs/concepts#langchain-expression-language-lcel), [components](https://python.langchain.com/v0.2/docs/concepts), and [third-party integrations](https://python.langchain.com/v0.2/docs/integrations/platforms/).
+Use [LangGraph](/docs/concepts/#langgraph) to build stateful agents with first-class streaming and human-in-the-loop support.
 - **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://docs.smith.langchain.com/) so that you can constantly optimize and deploy with confidence.
-- **Deployment**: Turn any chain into a REST API with [LangServe](https://python.langchain.com/v0.2/docs/langserve/).
+- **Deployment**: Turn your LangGraph applications into production-ready APIs and Assistants with [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/).
 
 ### Open-source libraries
 - **`langchain-core`**: Base abstractions and LangChain Expression Language.
 - **`langchain-community`**: Third party integrations.
   - Some integrations have been further split into **partner packages** that only rely on **`langchain-core`**. Examples include **`langchain_openai`** and **`langchain_anthropic`**.
 - **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
-- **[`LangGraph`](https://langchain-ai.github.io/langgraph/)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
+- **[`LangGraph`](https://langchain-ai.github.io/langgraph/)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph. Integrates smoothly with LangChain, but can be used without it.
 
 ### Productionization:
 - **[LangSmith](https://docs.smith.langchain.com/)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
 
 ### Deployment:
-- **[LangServe](https://python.langchain.com/v0.2/docs/langserve/)**: A library for deploying LangChain chains as REST APIs.
+- **[LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/)**: Turn your LangGraph applications into production-ready APIs and Assistants.
 
-![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack.svg "LangChain Architecture Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_062024.svg "LangChain Architecture Overview")
 
 ## 🧱 What can you build with LangChain?
 
@@ -106,7 +105,7 @@ Retrieval Augmented Generation involves [loading data](https://python.langchain.
 
 **🤖 Agents**
 
-Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents) along with the [LangGraph](https://github.com/langchain-ai/langgraph) extension for building custom agents.
+Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents), along with [LangGraph](https://github.com/langchain-ai/langgraph) for building custom agents.
 
 ## 📖 Documentation
 
@@ -120,10 +119,9 @@ Please see [here](https://python.langchain.com) for full documentation, which in
 
 ## 🌐 Ecosystem
 
-- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
-- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
-- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploying LangChain runnables and chains as REST APIs.
-  - [LangChain Templates](https://python.langchain.com/v0.2/docs/templates/): Example applications hosted with LangServe.
+- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Trace and evaluate your language model applications and intelligent agents to help you move from prototype to production.
+- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Create stateful, multi-actor applications with LLMs. Integrates smoothly with LangChain, but can be used without it.
+- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploy LangChain runnables and chains as REST APIs.
 
 
 ## 💁 Contributing

cookbook/Multi_modal_RAG.ipynb

@@ -64,7 +64,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai langchain-chroma 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_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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_community openai chromadb langchain-experimental\n",
+    "%pip install -U --quiet langchain langchain-chroma langchain-community openai 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 chromadb langchain-anthropic"
+    "pip install -U langchain umap-learn scikit-learn langchain_community tiktoken langchain-openai langchainhub langchain-chroma langchain-anthropic"
    ]
   },
   {
@@ -645,7 +645,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "\n",
     "# Initialize all_texts with leaf_texts\n",
     "all_texts = leaf_texts.copy()\n",

cookbook/README.md

@@ -36,6 +36,7 @@ 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.
@@ -57,4 +58,6 @@ 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.
+[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.

cookbook/Semi_Structured_RAG.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain unstructured[all-docs] pydantic lxml langchainhub"
+    "! pip install langchain langchain-chroma 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_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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 unstructured[all-docs] pydantic lxml"
+    "! pip install langchain langchain-chroma 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_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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 unstructured[all-docs] pydantic lxml"
+    "! pip install langchain langchain-chroma 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 chromadb langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai langchain_chroma langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -132,7 +132,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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"
+    "%pip install -qU langchain-airbyte langchain_chroma"
    ]
   },
   {
@@ -123,7 +123,7 @@
    "outputs": [],
    "source": [
     "import tiktoken\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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 chromadb hnswlib --upgrade --quiet"
+    "! pip install langchain docugami==0.0.8 dgml-utils==0.3.0 pydantic langchainhub langchain-chroma hnswlib --upgrade --quiet"
    ]
   },
   {
@@ -547,7 +547,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_community.vectorstores.chroma import Chroma\n",
+    "from langchain_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 chromadb tiktoken openai \n",
+    "%pip install --quiet pypdf langchain-chroma 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_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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_community tiktoken langchain-openai langchainhub chromadb langchain langgraph"
+    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub 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_community tiktoken langchain-openai langchainhub chromadb langchain langgraph tavily-python"
+    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub 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_community tiktoken langchain-openai langchainhub chromadb langchain langgraph"
+    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub 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_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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 chromadb langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -187,7 +187,7 @@
     "\n",
     "import chromadb\n",
     "import numpy as np\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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

@@ -18,26 +18,7 @@
     "* 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 \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"
+    "* Passing raw images and text chunks to a multimodal LLM for answer synthesis "
    ]
   },
   {
@@ -53,7 +34,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "id": "5f483872",
    "metadata": {},
    "outputs": [
@@ -61,8 +42,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "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"
+      "a1b9206b08ef626e15b356bf9e031171f7c7eb8f956a2733f196f0109246fe2b\n"
      ]
     }
    ],
@@ -75,9 +55,32 @@
     "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": null,
+   "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,
    "id": "78ac6543",
    "metadata": {},
    "outputs": [],
@@ -95,14 +98,9 @@
     "\n",
     "### Partition PDF text and images\n",
     "  \n",
-    "Let's look at an example pdf containing interesting images.\n",
+    "Let's use famous photographs from the PDF version of Library of Congress Magazine in this example.\n",
     "\n",
-    "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."
+    "We can use `partition_pdf` from [Unstructured](https://unstructured-io.github.io/unstructured/introduction.html#key-concepts) to extract text and images."
    ]
   },
   {
@@ -116,8 +114,8 @@
     "\n",
     "import requests\n",
     "\n",
-    "# Folder with pdf and extracted images\n",
-    "datapath = Path(\"./multimodal_files\").resolve()\n",
+    "# Folder to store pdf and extracted images\n",
+    "datapath = Path(\"./data/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",
@@ -174,14 +172,8 @@
    "source": [
     "## Multi-modal embeddings with our document\n",
     "\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",
-    "```"
+    "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"
    ]
   },
   {
@@ -200,9 +192,7 @@
     "vectorstore = VDMS(\n",
     "    client=vdms_client,\n",
     "    collection_name=\"mm_rag_clip_photos\",\n",
-    "    embedding_function=OpenCLIPEmbeddings(\n",
-    "        model_name=\"ViT-g-14\", checkpoint=\"laion2b_s34b_b88k\"\n",
-    "    ),\n",
+    "    embedding=OpenCLIPEmbeddings(model_name=\"ViT-g-14\", checkpoint=\"laion2b_s34b_b88k\"),\n",
     ")\n",
     "\n",
     "# Get image URIs with .jpg extension only\n",
@@ -233,7 +223,7 @@
    "source": [
     "## RAG\n",
     "\n",
-    "`vectorstore.add_images` will store / retrieve images as base64 encoded strings."
+    "Here we define helper functions for image results."
    ]
   },
   {
@@ -392,7 +382,8 @@
    "id": "1566096d-97c2-4ddc-ba4a-6ef88c525e4e",
    "metadata": {},
    "source": [
-    "## Test retrieval and run RAG"
+    "## Test retrieval and run RAG\n",
+    "Now let's query for a `woman with children` and retrieve the top results."
    ]
   },
   {
@@ -452,6 +443,14 @@
     "        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,
@@ -462,10 +461,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "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"
+      " 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"
      ]
     }
    ],
@@ -492,14 +491,6 @@
    "source": [
     "! docker kill vdms_rag_nb"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "8ba652da",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -518,7 +509,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

cookbook/nomic_embedding_rag.ipynb

@@ -58,7 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain-nomic langchain_community tiktoken langchain-openai chromadb langchain"
+    "! pip install -U langchain-nomic langchain-chroma langchain-community tiktoken langchain-openai langchain"
    ]
   },
   {
@@ -167,7 +167,7 @@
    "source": [
     "import os\n",
     "\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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_community tiktoken langchain-openai chromadb langchain # (newest versions required for multi-modal)"
+    "! pip install -U langchain-nomic langchain-chroma langchain-community tiktoken langchain-openai langchain # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -194,7 +194,7 @@
     "\n",
     "import chromadb\n",
     "import numpy as np\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma 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_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "embeddings = OpenAIEmbeddings()"

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

@@ -0,0 +1,756 @@
+{
+ "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",
@@ -370,13 +370,14 @@
    ],
    "source": [
     "import torch\n",
-    "from langchain.llms.huggingface_pipeline import HuggingFacePipeline\n",
-    "from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline\n",
+    "from langchain_huggingface.llms import HuggingFacePipeline\n",
+    "from optimum.intel.ipex import IPEXModelForCausalLM\n",
+    "from transformers import AutoTokenizer, pipeline\n",
     "\n",
     "model_id = \"Intel/neural-chat-7b-v3-3\"\n",
     "tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
-    "model = AutoModelForCausalLM.from_pretrained(\n",
-    "    model_id, device_map=\"auto\", torch_dtype=torch.bfloat16\n",
+    "model = IPEXModelForCausalLM.from_pretrained(\n",
+    "    model_id, torch_dtype=torch.bfloat16, export=True\n",
     ")\n",
     "\n",
     "pipe = pipeline(\"text-generation\", model=model, tokenizer=tokenizer, max_new_tokens=100)\n",
@@ -581,7 +582,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.10.14"
   }
  },
  "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 chromadb
+poetry run pip install pyyaml langchain_chroma
 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_community.vectorstores import Chroma
+from langchain_chroma 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 chromadb tiktoken openai langchain-together"
+    "! pip install --quiet pypdf tiktoken openai langchain-chroma 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" | 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|couchbase" | tr '\n' ' ')
 
 PORT ?= 3001
 
@@ -38,6 +38,14 @@ 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/kv_store_feat_table.py $(INTERMEDIATE_DIR)
+
+	$(PYTHON) scripts/partner_pkg_table.py $(INTERMEDIATE_DIR)
+
 	$(PYTHON) scripts/copy_templates.py $(INTERMEDIATE_DIR)
 
 	wget -q https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O $(INTERMEDIATE_DIR)/langserve.md
@@ -59,12 +67,15 @@ render:
 	$(PYTHON) scripts/notebook_convert.py $(INTERMEDIATE_DIR) $(OUTPUT_NEW_DOCS_DIR)
 
 md-sync:
-	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
+	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --include="*/_category_.yml" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
+
+append-related:
+	$(PYTHON) scripts/append_related_links.py $(OUTPUT_NEW_DOCS_DIR)
 
 generate-references:
 	$(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(OUTPUT_NEW_DOCS_DIR)
 
-build: install-py-deps generate-files copy-infra render md-sync
+build: install-py-deps generate-files copy-infra render md-sync append-related
 
 vercel-build: install-vercel-deps build generate-references
 	rm -rf docs

docs/api_reference/conf.py

@@ -15,6 +15,8 @@ from pathlib import Path
 
 import toml
 from docutils import nodes
+from docutils.parsers.rst.directives.admonitions import BaseAdmonition
+from docutils.statemachine import StringList
 from sphinx.util.docutils import SphinxDirective
 
 # If extensions (or modules to document with autodoc) are in another directory,
@@ -66,8 +68,23 @@ class ExampleLinksDirective(SphinxDirective):
         return [list_node]
 
 
+class Beta(BaseAdmonition):
+    required_arguments = 0
+    node_class = nodes.admonition
+
+    def run(self):
+        self.content = self.content or StringList(
+            [
+                "This feature is in beta. It is actively being worked on, so the API may change."
+            ]
+        )
+        self.arguments = self.arguments or ["Beta"]
+        return super().run()
+
+
 def setup(app):
     app.add_directive("example_links", ExampleLinksDirective)
+    app.add_directive("beta", Beta)
 
 
 # -- Project information -----------------------------------------------------
@@ -178,3 +195,10 @@ 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

@@ -10,12 +10,21 @@ from pathlib import Path
 from typing import Dict, List, Literal, Optional, Sequence, TypedDict, Union
 
 import toml
+import typing_extensions
+from langchain_core.runnables import Runnable, RunnableSerializable
 from pydantic import BaseModel
 
 ROOT_DIR = Path(__file__).parents[2].absolute()
 HERE = Path(__file__).parent
 
-ClassKind = Literal["TypedDict", "Regular", "Pydantic", "enum"]
+ClassKind = Literal[
+    "TypedDict",
+    "Regular",
+    "Pydantic",
+    "enum",
+    "RunnablePydantic",
+    "RunnableNonPydantic",
+]
 
 
 class ClassInfo(TypedDict):
@@ -29,6 +38,8 @@ class ClassInfo(TypedDict):
     """The kind of the class."""
     is_public: bool
     """Whether the class is public or not."""
+    is_deprecated: bool
+    """Whether the class is deprecated."""
 
 
 class FunctionInfo(TypedDict):
@@ -40,6 +51,8 @@ class FunctionInfo(TypedDict):
     """The fully qualified name of the function."""
     is_public: bool
     """Whether the function is public or not."""
+    is_deprecated: bool
+    """Whether the function is deprecated."""
 
 
 class ModuleMembers(TypedDict):
@@ -69,8 +82,36 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
             continue
 
         if inspect.isclass(type_):
-            if type(type_) == typing._TypedDictMeta:  # type: ignore
+            # The type 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
+            # kinds of thing that we want to render.
+            if type(type_) is typing_extensions._TypedDictMeta:  # type: ignore
                 kind: ClassKind = "TypedDict"
+            elif type(type_) is typing._TypedDictMeta:  # type: ignore
+                kind: ClassKind = "TypedDict"
+            elif (
+                issubclass(type_, Runnable)
+                and issubclass(type_, BaseModel)
+                and type_ is not Runnable
+            ):
+                # RunnableSerializable subclasses from Pydantic which
+                # for which we use autodoc_pydantic for rendering.
+                # We need to distinguish these from regular Pydantic
+                # classes so we can hide inherited Runnable methods
+                # and provide a link to the Runnable interface from
+                # the template.
+                kind = "RunnablePydantic"
+            elif (
+                issubclass(type_, Runnable)
+                and not issubclass(type_, BaseModel)
+                and type_ is not Runnable
+            ):
+                # These are not pydantic classes but are Runnable.
+                # We'll hide all the inherited methods from Runnable
+                # but use a regular class template to render.
+                kind = "RunnableNonPydantic"
             elif issubclass(type_, Enum):
                 kind = "enum"
             elif issubclass(type_, BaseModel):
@@ -84,6 +125,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
                     qualified_name=f"{namespace}.{name}",
                     kind=kind,
                     is_public=not name.startswith("_"),
+                    is_deprecated=".. deprecated::" in (type_.__doc__ or ""),
                 )
             )
         elif inspect.isfunction(type_):
@@ -92,6 +134,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
                     name=name,
                     qualified_name=f"{namespace}.{name}",
                     is_public=not name.startswith("_"),
+                    is_deprecated=".. deprecated::" in (type_.__doc__ or ""),
                 )
             )
         else:
@@ -218,8 +261,24 @@ def _construct_doc(
 
     for module in namespaces:
         _members = members_by_namespace[module]
-        classes = [el for el in _members["classes_"] if el["is_public"]]
-        functions = [el for el in _members["functions"] if el["is_public"]]
+        classes = [
+            el
+            for el in _members["classes_"]
+            if el["is_public"] and not el["is_deprecated"]
+        ]
+        functions = [
+            el
+            for el in _members["functions"]
+            if el["is_public"] and not el["is_deprecated"]
+        ]
+        deprecated_classes = [
+            el for el in _members["classes_"] if el["is_public"] and el["is_deprecated"]
+        ]
+        deprecated_functions = [
+            el
+            for el in _members["functions"]
+            if el["is_public"] and el["is_deprecated"]
+        ]
         if not (classes or functions):
             continue
         section = f":mod:`{package_namespace}.{module}`"
@@ -251,6 +310,10 @@ Classes
                     template = "enum.rst"
                 elif class_["kind"] == "Pydantic":
                     template = "pydantic.rst"
+                elif class_["kind"] == "RunnablePydantic":
+                    template = "runnable_pydantic.rst"
+                elif class_["kind"] == "RunnableNonPydantic":
+                    template = "runnable_non_pydantic.rst"
                 else:
                     template = "class.rst"
 
@@ -269,6 +332,54 @@ Functions
 --------------
 .. currentmodule:: {package_namespace}
 
+.. autosummary::
+    :toctree: {module}
+    :template: function.rst
+
+    {fstring}
+
+"""
+        if deprecated_classes:
+            full_doc += f"""\
+Deprecated classes
+--------------
+
+.. currentmodule:: {package_namespace}
+
+.. autosummary::
+    :toctree: {module}
+"""
+
+            for class_ in sorted(deprecated_classes, key=lambda c: c["qualified_name"]):
+                if class_["kind"] == "TypedDict":
+                    template = "typeddict.rst"
+                elif class_["kind"] == "enum":
+                    template = "enum.rst"
+                elif class_["kind"] == "Pydantic":
+                    template = "pydantic.rst"
+                elif class_["kind"] == "RunnablePydantic":
+                    template = "runnable_pydantic.rst"
+                elif class_["kind"] == "RunnableNonPydantic":
+                    template = "runnable_non_pydantic.rst"
+                else:
+                    template = "class.rst"
+
+                full_doc += f"""\
+    :template: {template}
+
+    {class_["qualified_name"]}
+
+"""
+
+        if deprecated_functions:
+            _functions = [f["qualified_name"] for f in deprecated_functions]
+            fstring = "\n    ".join(sorted(_functions))
+            full_doc += f"""\
+Deprecated functions
+--------------
+
+.. currentmodule:: {package_namespace}
+
 .. autosummary::
     :toctree: {module}
     :template: function.rst

docs/api_reference/templates/class.rst

@@ -33,4 +33,4 @@
    {% endblock %}
 
 
-.. example_links:: {{ objname }}
+.. example_links:: {{ objname }}

docs/api_reference/templates/pydantic.rst

@@ -15,6 +15,8 @@
     :member-order: groupwise
     :show-inheritance: True
     :special-members: __call__
+    :exclude-members: construct, copy, dict, from_orm, parse_file, parse_obj, parse_raw, schema, schema_json, update_forward_refs, validate, json, is_lc_serializable, to_json, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace
+
 
     {% block attributes %}
     {% endblock %}

docs/api_reference/templates/runnable_non_pydantic.rst

@@ -0,0 +1,40 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
+
+    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
+
+.. currentmodule:: {{ module }}
+
+.. autoclass:: {{ objname }}
+
+   {% block attributes %}
+   {% if attributes %}
+   .. rubric:: {{ _('Attributes') }}
+
+   .. autosummary::
+   {% for item in attributes %}
+      ~{{ name }}.{{ item }}
+   {%- endfor %}
+   {% endif %}
+   {% endblock %}
+
+   {% block methods %}
+   {% if methods %}
+   .. rubric:: {{ _('Methods') }}
+
+   .. autosummary::
+   {% for item in methods %}
+      ~{{ name }}.{{ item }}
+   {%- endfor %}
+
+   {% for item in methods %}
+   .. automethod:: {{ name }}.{{ item }}
+   {%- endfor %}
+
+   {% endif %}
+   {% endblock %}
+
+
+.. example_links:: {{ objname }}

docs/api_reference/templates/runnable_pydantic.rst

@@ -0,0 +1,24 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
+
+    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
+
+.. currentmodule:: {{ module }}
+
+.. autopydantic_model:: {{ objname }}
+    :model-show-json: False
+    :model-show-config-summary: False
+    :model-show-validator-members: False
+    :model-show-field-summary: False
+    :field-signature-prefix: param
+    :members:
+    :undoc-members:
+    :inherited-members:
+    :member-order: groupwise
+    :show-inheritance: True
+    :special-members: __call__
+    :exclude-members: construct, copy, dict, from_orm, parse_file, parse_obj, parse_raw, schema, schema_json, update_forward_refs, validate, json, is_lc_serializable, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace, astream_log, transform, atransform, get_output_schema, get_prompts, config_schema, map, pick, pipe, with_listeners, with_alisteners, with_config, with_fallbacks, with_types, with_retry, InputType, OutputType, config_specs, output_schema, get_input_schema, get_graph, get_name, input_schema, name, bind, assign
+
+.. example_links:: {{ objname }}

docs/api_reference/themes/scikit-learn-modern/layout.html

@@ -2,132 +2,129 @@
 {%- set url_root = pathto('', 1) %}
 {%- if url_root == '#' %}{% set url_root = '' %}{% endif %}
 {%- if not embedded and docstitle %}
-  {%- set titlesuffix = " — "|safe + docstitle|e %}
+    {%- set titlesuffix = " — "|safe + docstitle|e %}
 {%- else %}
-  {%- set titlesuffix = "" %}
+    {%- set titlesuffix = "" %}
 {%- endif %}
 {%- set lang_attr = 'en' %}
 
 <!DOCTYPE html>
 <!--[if IE 8]><html class="no-js lt-ie9" lang="{{ lang_attr }}" > <![endif]-->
-<!--[if gt IE 8]><!--> <html class="no-js" lang="{{ lang_attr }}" > <!--<![endif]-->
+<!--[if gt IE 8]><!-->
+<html class="no-js" lang="{{ lang_attr }}"> <!--<![endif]-->
 <head>
-  <meta charset="utf-8">
-  {{ metatags }}
-  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <meta charset="utf-8">
+    {{ metatags }}
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  {% block htmltitle %}
-  <title>{{ title|striptags|e }}{{ titlesuffix }}</title>
-  {% endblock %}
-  <link rel="canonical" href="https://api.python.langchain.com/en/latest/{{pagename}}.html" />
+    {% block htmltitle %}
+        <title>{{ title|striptags|e }}{{ titlesuffix }}</title>
+    {% endblock %}
+    <link rel="canonical"
+          href="https://api.python.langchain.com/en/latest/{{ pagename }}.html"/>
 
-  {% if favicon_url %}
-  <link rel="shortcut icon" href="{{ favicon_url|e }}"/>
-  {% endif %}
+    {% if favicon_url %}
+        <link rel="shortcut icon" href="{{ favicon_url|e }}"/>
+    {% endif %}
 
-  <link rel="stylesheet" href="{{ pathto('_static/css/vendor/bootstrap.min.css', 1) }}" type="text/css" />
-  {%- for css in css_files %}
-    {%- if css|attr("rel") %}
-  <link rel="{{ css.rel }}" href="{{ pathto(css.filename, 1) }}" type="text/css"{% if css.title is not none %} title="{{ css.title }}"{% endif %} />
-    {%- else %}
-  <link rel="stylesheet" href="{{ pathto(css, 1) }}" type="text/css" />
-    {%- endif %}
-  {%- endfor %}
-  <link rel="stylesheet" href="{{ pathto('_static/' + style, 1) }}" type="text/css" />
-<script id="documentation_options" data-url_root="{{ pathto('', 1) }}" src="{{ pathto('_static/documentation_options.js', 1) }}"></script>
-<script src="{{ pathto('_static/jquery.js', 1) }}"></script>
-{%- block extrahead %} {% endblock %}
+    <link rel="stylesheet"
+          href="{{ pathto('_static/css/vendor/bootstrap.min.css', 1) }}"
+          type="text/css"/>
+    {%- for css in css_files %}
+        {%- if css|attr("rel") %}
+            <link rel="{{ css.rel }}" href="{{ pathto(css.filename, 1) }}"
+                  type="text/css"{% if css.title is not none %}
+                  title="{{ css.title }}"{% endif %} />
+        {%- else %}
+            <link rel="stylesheet" href="{{ pathto(css, 1) }}" type="text/css"/>
+        {%- endif %}
+    {%- endfor %}
+    <link rel="stylesheet" href="{{ pathto('_static/' + style, 1) }}" type="text/css"/>
+    <script id="documentation_options" data-url_root="{{ pathto('', 1) }}"
+            src="{{ pathto('_static/documentation_options.js', 1) }}"></script>
+    <script src="{{ pathto('_static/jquery.js', 1) }}"></script>
+    {%- block extrahead %} {% endblock %}
 </head>
 <body>
 {% include "nav.html" %}
 {%- block content %}
-<div class="d-flex" id="sk-doc-wrapper">
-    <input type="checkbox" name="sk-toggle-checkbox" id="sk-toggle-checkbox">
-    <label id="sk-sidemenu-toggle" class="sk-btn-toggle-toc btn sk-btn-primary" for="sk-toggle-checkbox">Toggle Menu</label>
-    <div id="sk-sidebar-wrapper" class="border-right">
-      <div class="sk-sidebar-toc-wrapper">
-        <div class="btn-group w-100 mb-2" role="group" aria-label="rellinks">
-          {%- if prev %}
-            <a href="{{ prev.link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ prev.title|striptags }}">Prev</a>
-          {%- else %}
-            <a href="#" role="button" class="btn sk-btn-rellink py-1 disabled"">Prev</a>
-          {%- endif %}
-          {%- if parents -%}
-            <a href="{{ parents[-1].link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ parents[-1].title|striptags }}">Up</a>
-          {%- else %}
-            <a href="#" role="button" class="btn sk-btn-rellink disabled py-1">Up</a>
-          {%- endif %}
-          {%- if next %}
-            <a href="{{ next.link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ next.title|striptags }}">Next</a>
-          {%- else %}
-            <a href="#" role="button" class="btn sk-btn-rellink py-1 disabled"">Next</a>
-          {%- endif %}
+    <div class="d-flex" id="sk-doc-wrapper">
+        <input type="checkbox" name="sk-toggle-checkbox" id="sk-toggle-checkbox">
+        <label id="sk-sidemenu-toggle" class="sk-btn-toggle-toc btn sk-btn-primary"
+               for="sk-toggle-checkbox">Toggle Menu</label>
+        <div id="sk-sidebar-wrapper" class="border-right">
+            <div class="sk-sidebar-toc-wrapper">
+                {%- if meta and meta['parenttoc']|tobool %}
+                    <div class="sk-sidebar-toc">
+                        {% set nav = get_nav_object(maxdepth=3, collapse=True, numbered=True) %}
+                        <ul>
+                            {% for main_nav_item in nav %}
+                                {% if main_nav_item.active %}
+                                    <li>
+                                        <a href="{{ main_nav_item.url }}"
+                                           class="sk-toc-active">{{ main_nav_item.title }}</a>
+                                    </li>
+                                    <ul>
+                                        {% for nav_item in main_nav_item.children %}
+                                            <li>
+                                                <a href="{{ nav_item.url }}"
+                                                   class="{% if nav_item.active %}sk-toc-active{% endif %}">{{ nav_item.title }}</a>
+                                                {% if nav_item.children %}
+                                                    <ul>
+                                                        {% for inner_child in nav_item.children %}
+                                                            <li class="sk-toctree-l3">
+                                                                <a href="{{ inner_child.url }}">{{ inner_child.title }}</a>
+                                                            </li>
+                                                        {% endfor %}
+                                                    </ul>
+                                                {% endif %}
+                                            </li>
+                                        {% endfor %}
+                                    </ul>
+                                {% endif %}
+                            {% endfor %}
+                        </ul>
+                    </div>
+                {%- elif meta and meta['globalsidebartoc']|tobool %}
+                    <div class="sk-sidebar-toc sk-sidebar-global-toc">
+                        {{ toctree(maxdepth=2, titles_only=True) }}
+                    </div>
+                {%- else %}
+                    <div class="sk-sidebar-toc">
+                        {{ toc }}
+                    </div>
+                {%- endif %}
+            </div>
         </div>
-            {%- if meta and meta['parenttoc']|tobool %}
-            <div class="sk-sidebar-toc">
-            {% set nav = get_nav_object(maxdepth=3, collapse=True, numbered=True) %}
-              <ul>
-              {% for main_nav_item in nav %}
-              {% if main_nav_item.active %}
-              <li>
-                <a href="{{ main_nav_item.url }}" class="sk-toc-active">{{ main_nav_item.title }}</a>
-              </li>
-              <ul>
-              {% for nav_item in main_nav_item.children %}
-                <li>
-                  <a href="{{ nav_item.url }}" class="{% if nav_item.active %}sk-toc-active{% endif %}">{{ nav_item.title }}</a>
-                  {% if nav_item.children %}
-                  <ul>
-                    {% for inner_child in nav_item.children %}
-                      <li class="sk-toctree-l3">
-                        <a href="{{ inner_child.url }}">{{ inner_child.title }}</a>
-                      </li>
-                    {% endfor %}
-                  </ul>
-                  {% endif %}
-                </li>
-              {% endfor %}
-              </ul>
-              {% endif %}
-              {% endfor %}
-              </ul>
+        <div id="sk-page-content-wrapper">
+            <div class="sk-page-content container-fluid body px-md-3" role="main">
+                {% block body %}{% endblock %}
             </div>
-            {%- elif meta and meta['globalsidebartoc']|tobool %}
-            <div class="sk-sidebar-toc sk-sidebar-global-toc">
-              {{ toctree(maxdepth=2, titles_only=True) }}
+            <div class="container">
+                <footer class="sk-content-footer">
+                    {%- if pagename != 'index' %}
+                        {%- if show_copyright %}
+                            {%- if hasdoc('copyright') %}
+                                {% trans path=pathto('copyright'), copyright=copyright|e %}
+                                    &copy; {{ copyright }}.{% endtrans %}
+                            {%- else %}
+                                {% trans copyright=copyright|e %}&copy; {{ copyright }}
+                                    .{% endtrans %}
+                            {%- endif %}
+                        {%- endif %}
+                        {%- if last_updated %}
+                            {% trans last_updated=last_updated|e %}Last updated
+                                on {{ last_updated }}.{% endtrans %}
+                        {%- endif %}
+                        {%- if show_source and has_source and sourcename %}
+                            <a href="{{ pathto('_sources/' + sourcename, true)|e }}"
+                               rel="nofollow">{{ _('Show this page source') }}</a>
+                        {%- endif %}
+                    {%- endif %}
+                </footer>
             </div>
-            {%- else %}
-            <div class="sk-sidebar-toc">
-              {{ toc }}
-            </div>
-            {%- endif %}
-      </div>
+        </div>
     </div>
-    <div id="sk-page-content-wrapper">
-      <div class="sk-page-content container-fluid body px-md-3" role="main">
-        {% block body %}{% endblock %}
-      </div>
-    <div class="container">
-      <footer class="sk-content-footer">
-        {%- if pagename != 'index' %}
-        {%- if show_copyright %}
-          {%- if hasdoc('copyright') %}
-            {% trans path=pathto('copyright'), copyright=copyright|e %}&copy; {{ copyright }}.{% endtrans %}
-          {%- else %}
-            {% trans copyright=copyright|e %}&copy; {{ copyright }}.{% endtrans %}
-          {%- endif %}
-        {%- endif %}
-        {%- if last_updated %}
-          {% trans last_updated=last_updated|e %}Last updated on {{ last_updated }}.{% endtrans %}
-        {%- endif %}
-        {%- if show_source and has_source and sourcename %}
-          <a href="{{ pathto('_sources/' + sourcename, true)|e }}" rel="nofollow">{{ _('Show this page source') }}</a>
-        {%- endif %}
-        {%- endif %}
-      </footer>
-    </div>
-  </div>
-</div>
 {%- endblock %}
 <script src="{{ pathto('_static/js/vendor/bootstrap.min.js', 1) }}"></script>
 {% include "javascript.html" %}

docs/api_reference/themes/scikit-learn-modern/static/css/theme.css

@@ -897,6 +897,13 @@ div.admonition {
   background-color: #eee;
 }
 
+div.admonition-beta {
+  color: #d35400; /* A darker rich orange color */
+  background-color: #FDF2E9; /* A light orange-tinted background color */
+  border-color: #E59866; /* A darker soft orange border color */
+}
+
+
 div.admonition p:last-child,
 div.admonition dl:last-child,
 div.admonition dd:last-child,
@@ -912,6 +919,13 @@ div.deprecated {
   border-color: #eed3d7;
 }
 
+
+div.warning {
+  color: #b94a48;
+  background-color: #F3E5E5;
+  border-color: #eed3d7;
+}
+
 div.seealso {
   background-color: #FFFBE8;
   border-color: #fbeed5;

docs/docs/additional_resources/arxiv_references.mdx

@@ -24,21 +24,22 @@ Here you find [such papers](https://arxiv.org/search/?query=langchain&searchtype
 | `2305.08291v1` [Large Language Model Guided Tree-of-Thought](http://arxiv.org/abs/2305.08291v1) | Jieyi Long | 2023-05-15 | `API:` [langchain_experimental.tot](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.tot), `Cookbook:` [tree_of_thought](https://github.com/langchain-ai/langchain/blob/master/cookbook/tree_of_thought.ipynb)
 | `2305.04091v3` [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](http://arxiv.org/abs/2305.04091v3) | Lei Wang, Wanyu Xu, Yihuai Lan,  et al. | 2023-05-06 | `Cookbook:` [plan_and_execute_agent](https://github.com/langchain-ai/langchain/blob/master/cookbook/plan_and_execute_agent.ipynb)
 | `2304.08485v2` [Visual Instruction Tuning](http://arxiv.org/abs/2304.08485v2) | Haotian Liu, Chunyuan Li, Qingyang Wu,  et al. | 2023-04-17 | `Cookbook:` [Semi_structured_and_multi_modal_RAG](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb), [Semi_structured_multi_modal_RAG_LLaMA2](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb)
-| `2304.03442v2` [Generative Agents: Interactive Simulacra of Human Behavior](http://arxiv.org/abs/2304.03442v2) | Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai,  et al. | 2023-04-07 | `Cookbook:` [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb), [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb)
+| `2304.03442v2` [Generative Agents: Interactive Simulacra of Human Behavior](http://arxiv.org/abs/2304.03442v2) | Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai,  et al. | 2023-04-07 | `Cookbook:` [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb), [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb)
 | `2303.17760v2` [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](http://arxiv.org/abs/2303.17760v2) | Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani,  et al. | 2023-03-31 | `Cookbook:` [camel_role_playing](https://github.com/langchain-ai/langchain/blob/master/cookbook/camel_role_playing.ipynb)
 | `2303.17580v4` [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](http://arxiv.org/abs/2303.17580v4) | Yongliang Shen, Kaitao Song, Xu Tan,  et al. | 2023-03-30 | `API:` [langchain_experimental.autonomous_agents](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.autonomous_agents), `Cookbook:` [hugginggpt](https://github.com/langchain-ai/langchain/blob/master/cookbook/hugginggpt.ipynb)
 | `2303.08774v6` [GPT-4 Technical Report](http://arxiv.org/abs/2303.08774v6) | OpenAI, Josh Achiam, Steven Adler,  et al. | 2023-03-15 | `Docs:` [docs/integrations/vectorstores/mongodb_atlas](https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas)
-| `2301.10226v4` [A Watermark for Large Language Models](http://arxiv.org/abs/2301.10226v4) | John Kirchenbauer, Jonas Geiping, Yuxin Wen,  et al. | 2023-01-24 | `API:` [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
+| `2301.10226v4` [A Watermark for Large Language Models](http://arxiv.org/abs/2301.10226v4) | John Kirchenbauer, Jonas Geiping, Yuxin Wen,  et al. | 2023-01-24 | `API:` [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 | `2212.10496v1` [Precise Zero-Shot Dense Retrieval without Relevance Labels](http://arxiv.org/abs/2212.10496v1) | Luyu Gao, Xueguang Ma, Jimmy Lin,  et al. | 2022-12-20 | `API:` [langchain...HypotheticalDocumentEmbedder](https://api.python.langchain.com/en/latest/chains/langchain.chains.hyde.base.HypotheticalDocumentEmbedder.html#langchain.chains.hyde.base.HypotheticalDocumentEmbedder), `Template:` [hyde](https://python.langchain.com/docs/templates/hyde), `Cookbook:` [hypothetical_document_embeddings](https://github.com/langchain-ai/langchain/blob/master/cookbook/hypothetical_document_embeddings.ipynb)
 | `2212.07425v3` [Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments](http://arxiv.org/abs/2212.07425v3) | Zhivar Sourati, Vishnu Priya Prasanna Venkatesh, Darshan Deshpande,  et al. | 2022-12-12 | `API:` [langchain_experimental.fallacy_removal](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.fallacy_removal)
 | `2211.13892v2` [Complementary Explanations for Effective In-Context Learning](http://arxiv.org/abs/2211.13892v2) | Xi Ye, Srinivasan Iyer, Asli Celikyilmaz,  et al. | 2022-11-25 | `API:` [langchain_core...MaxMarginalRelevanceExampleSelector](https://api.python.langchain.com/en/latest/example_selectors/langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector.html#langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector)
 | `2211.10435v2` [PAL: Program-aided Language Models](http://arxiv.org/abs/2211.10435v2) | Luyu Gao, Aman Madaan, Shuyan Zhou,  et al. | 2022-11-18 | `API:` [langchain_experimental...PALChain](https://api.python.langchain.com/en/latest/pal_chain/langchain_experimental.pal_chain.base.PALChain.html#langchain_experimental.pal_chain.base.PALChain), [langchain_experimental.pal_chain](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.pal_chain), `Cookbook:` [program_aided_language_model](https://github.com/langchain-ai/langchain/blob/master/cookbook/program_aided_language_model.ipynb)
+| `2210.03629v3` [ReAct: Synergizing Reasoning and Acting in Language Models](http://arxiv.org/abs/2210.03629v3) | Shunyu Yao, Jeffrey Zhao, Dian Yu,  et al. | 2022-10-06 | `Docs:` [docs/integrations/providers/cohere](https://python.langchain.com/docs/integrations/providers/cohere), [docs/integrations/chat/huggingface](https://python.langchain.com/docs/integrations/chat/huggingface), [docs/integrations/tools/ionic_shopping](https://python.langchain.com/docs/integrations/tools/ionic_shopping), `API:` [langchain...create_react_agent](https://api.python.langchain.com/en/latest/agents/langchain.agents.react.agent.create_react_agent.html#langchain.agents.react.agent.create_react_agent), [langchain...TrajectoryEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain)
 | `2209.10785v2` [Deep Lake: a Lakehouse for Deep Learning](http://arxiv.org/abs/2209.10785v2) | Sasun Hambardzumyan, Abhinav Tuli, Levon Ghukasyan,  et al. | 2022-09-22 | `Docs:` [docs/integrations/providers/activeloop_deeplake](https://python.langchain.com/docs/integrations/providers/activeloop_deeplake)
 | `2205.12654v1` [Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages](http://arxiv.org/abs/2205.12654v1) | Kevin Heffernan, Onur Çelebi, Holger Schwenk | 2022-05-25 | `API:` [langchain_community...LaserEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain_community.embeddings.laser.LaserEmbeddings.html#langchain_community.embeddings.laser.LaserEmbeddings)
 | `2204.00498v1` [Evaluating the Text-to-SQL Capabilities of Large Language Models](http://arxiv.org/abs/2204.00498v1) | Nitarshan Rajkumar, Raymond Li, Dzmitry Bahdanau | 2022-03-15 | `API:` [langchain_community...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL), [langchain_community...SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase)
-| `2202.00666v5` [Locally Typical Sampling](http://arxiv.org/abs/2202.00666v5) | Clara Meister, Tiago Pimentel, Gian Wiher,  et al. | 2022-02-01 | `API:` [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
+| `2202.00666v5` [Locally Typical Sampling](http://arxiv.org/abs/2202.00666v5) | Clara Meister, Tiago Pimentel, Gian Wiher,  et al. | 2022-02-01 | `API:` [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 | `2103.00020v1` [Learning Transferable Visual Models From Natural Language Supervision](http://arxiv.org/abs/2103.00020v1) | Alec Radford, Jong Wook Kim, Chris Hallacy,  et al. | 2021-02-26 | `API:` [langchain_experimental.open_clip](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.open_clip)
-| `1909.05858v2` [CTRL: A Conditional Transformer Language Model for Controllable Generation](http://arxiv.org/abs/1909.05858v2) | Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney,  et al. | 2019-09-11 | `API:` [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
+| `1909.05858v2` [CTRL: A Conditional Transformer Language Model for Controllable Generation](http://arxiv.org/abs/1909.05858v2) | Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney,  et al. | 2019-09-11 | `API:` [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 | `1908.10084v1` [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](http://arxiv.org/abs/1908.10084v1) | Nils Reimers, Iryna Gurevych | 2019-08-27 | `Docs:` [docs/integrations/text_embedding/sentence_transformers](https://python.langchain.com/docs/integrations/text_embedding/sentence_transformers)
 
 ## Self-Discover: Large Language Models Self-Compose Reasoning Structures
@@ -418,7 +419,7 @@ publicly available.
 - **URL:** http://arxiv.org/abs/2304.03442v2
 - **LangChain:**
 
-   - **Cookbook:** [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb), [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb)
+   - **Cookbook:** [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb), [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb)
 
 **Abstract:** Believable proxies of human behavior can empower interactive applications
 ranging from immersive environments to rehearsal spaces for interpersonal
@@ -540,7 +541,7 @@ more than 1/1,000th the compute of GPT-4.
 - **URL:** http://arxiv.org/abs/2301.10226v4
 - **LangChain:**
 
-   - **API Reference:** [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
+   - **API Reference:** [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 
 **Abstract:** Potential harms of large language models can be mitigated by watermarking
 model output, i.e., embedding signals into generated text that are invisible to
@@ -683,6 +684,41 @@ accuracy on the GSM8K benchmark of math word problems, surpassing PaLM-540B
 which uses chain-of-thought by absolute 15% top-1. Our code and data are
 publicly available at http://reasonwithpal.com/ .
                 
+## ReAct: Synergizing Reasoning and Acting in Language Models
+
+- **arXiv id:** 2210.03629v3
+- **Title:** ReAct: Synergizing Reasoning and Acting in Language Models
+- **Authors:** Shunyu Yao, Jeffrey Zhao, Dian Yu,  et al.
+- **Published Date:** 2022-10-06
+- **URL:** http://arxiv.org/abs/2210.03629v3
+- **LangChain:**
+
+   - **Documentation:** [docs/integrations/providers/cohere](https://python.langchain.com/docs/integrations/providers/cohere), [docs/integrations/chat/huggingface](https://python.langchain.com/docs/integrations/chat/huggingface), [docs/integrations/tools/ionic_shopping](https://python.langchain.com/docs/integrations/tools/ionic_shopping)
+   - **API Reference:** [langchain...create_react_agent](https://api.python.langchain.com/en/latest/agents/langchain.agents.react.agent.create_react_agent.html#langchain.agents.react.agent.create_react_agent), [langchain...TrajectoryEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain)
+
+**Abstract:** While large language models (LLMs) have demonstrated impressive capabilities
+across tasks in language understanding and interactive decision making, their
+abilities for reasoning (e.g. chain-of-thought prompting) and acting (e.g.
+action plan generation) have primarily been studied as separate topics. In this
+paper, we explore the use of LLMs to generate both reasoning traces and
+task-specific actions in an interleaved manner, allowing for greater synergy
+between the two: reasoning traces help the model induce, track, and update
+action plans as well as handle exceptions, while actions allow it to interface
+with external sources, such as knowledge bases or environments, to gather
+additional information. We apply our approach, named ReAct, to a diverse set of
+language and decision making tasks and demonstrate its effectiveness over
+state-of-the-art baselines, as well as improved human interpretability and
+trustworthiness over methods without reasoning or acting components.
+Concretely, on question answering (HotpotQA) and fact verification (Fever),
+ReAct overcomes issues of hallucination and error propagation prevalent in
+chain-of-thought reasoning by interacting with a simple Wikipedia API, and
+generates human-like task-solving trajectories that are more interpretable than
+baselines without reasoning traces. On two interactive decision making
+benchmarks (ALFWorld and WebShop), ReAct outperforms imitation and
+reinforcement learning methods by an absolute success rate of 34% and 10%
+respectively, while being prompted with only one or two in-context examples.
+Project site with code: https://react-lm.github.io
+                
 ## Deep Lake: a Lakehouse for Deep Learning
 
 - **arXiv id:** 2209.10785v2
@@ -768,7 +804,7 @@ few-shot examples.
 - **URL:** http://arxiv.org/abs/2202.00666v5
 - **LangChain:**
 
-   - **API Reference:** [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
+   - **API Reference:** [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 
 **Abstract:** Today's probabilistic language generators fall short when it comes to
 producing coherent and fluent text despite the fact that the underlying models
@@ -832,7 +868,7 @@ https://github.com/OpenAI/CLIP.
 - **URL:** http://arxiv.org/abs/1909.05858v2
 - **LangChain:**
 
-   - **API Reference:** [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
+   - **API Reference:** [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 
 **Abstract:** Large-scale language models show promising text generation capabilities, but
 users cannot easily control particular aspects of the generated text. We

docs/docs/additional_resources/tutorials.mdx

@@ -11,6 +11,7 @@
 ### [by Prompt Engineering](https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr)
 ### [by Mayo Oshin](https://www.youtube.com/@chatwithdata/search?query=langchain)
 ### [by 1 little Coder](https://www.youtube.com/playlist?list=PLpdmBGJ6ELUK-v0MK-t4wZmVEbxM5xk6L)
+### [by BobLin (Chinese language)](https://www.youtube.com/playlist?list=PLbd7ntv6PxC3QMFQvtWfk55p-Op_syO1C)
 
 ## Courses
 
@@ -45,7 +46,6 @@
 - [Generative AI with LangChain](https://www.amazon.com/Generative-AI-LangChain-language-ChatGPT/dp/1835083463/ref=sr_1_1?crid=1GMOMH0G7GLR&keywords=generative+ai+with+langchain&qid=1703247181&sprefix=%2Caps%2C298&sr=8-1) by [Ben Auffrath](https://www.amazon.com/stores/Ben-Auffarth/author/B08JQKSZ7D?ref=ap_rdr&store_ref=ap_rdr&isDramIntegrated=true&shoppingPortalEnabled=true), ©️ 2023 Packt Publishing
 - [LangChain AI Handbook](https://www.pinecone.io/learn/langchain/) By **James Briggs** and **Francisco Ingham**
 - [LangChain Cheatsheet](https://pub.towardsai.net/langchain-cheatsheet-all-secrets-on-a-single-page-8be26b721cde) by **Ivan Reznikov**
+- [Dive into Langchain (Chinese language)](https://langchain.boblin.app/)
 
 ---------------------
-
-

docs/docs/concepts.mdx

@@ -11,7 +11,7 @@ LangChain as a framework consists of a number of packages.
 
 ### `langchain-core`
 This package contains base abstractions of different components and ways to compose them together.
-The interfaces for core components like LLMs, vectorstores, retrievers and more are defined here.
+The interfaces for core components like LLMs, vector stores, retrievers and more are defined here.
 No third party integrations are defined here.
 The dependencies are kept purposefully very lightweight.
 
@@ -30,7 +30,7 @@ All chains, agents, and retrieval strategies here are NOT specific to any one in
 
 This package contains third party integrations that are maintained by the LangChain community.
 Key partner packages are separated out (see below).
-This contains all integrations for various components (LLMs, vectorstores, retrievers).
+This contains all integrations for various components (LLMs, vector stores, retrievers).
 All dependencies in this package are optional to keep the package as lightweight as possible.
 
 ### [`langgraph`](https://langchain-ai.github.io/langgraph)
@@ -51,10 +51,11 @@ A developer platform that lets you debug, test, evaluate, and monitor LLM applic
 <ThemedImage
   alt="Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers."
   sources={{
-    light: useBaseUrl('/svg/langchain_stack.svg'),
-    dark: useBaseUrl('/svg/langchain_stack_dark.svg'),
+    light: useBaseUrl('/svg/langchain_stack_062024.svg'),
+    dark: useBaseUrl('/svg/langchain_stack_062024_dark.svg'),
   }}
   title="LangChain Framework Overview"
+  style={{ width: "100%" }}
 />
 
 ## LangChain Expression Language (LCEL)
@@ -85,20 +86,25 @@ 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.
 
-[**Seamless LangServe deployment**](/docs/langserve)
-Any chain created with LCEL can be easily deployed using [LangServe](/docs/langserve).
+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).
 
 ### Runnable interface
-<span data-heading-keywords="invoke"></span>
+<span data-heading-keywords="invoke,runnable"></span>
 
 To make it as easy as possible to create custom chains, we've implemented a ["Runnable"](https://api.python.langchain.com/en/stable/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable) protocol. Many LangChain components implement the `Runnable` protocol, including chat models, LLMs, output parsers, retrievers, prompt templates, and more. There are also several useful primitives for working with runnables, which you can read about below.
 
 This is a standard interface, which makes it easy to define custom chains as well as invoke them in a standard way.
 The standard interface includes:
 
-- [`stream`](#stream): stream back chunks of the response
-- [`invoke`](#invoke): call the chain on an input
-- [`batch`](#batch): call the chain on a list of inputs
+- `stream`: stream back chunks of the response
+- `invoke`: call the chain on an input
+- `batch`: call the chain on a list of inputs
 
 These also have corresponding async methods that should be used with [asyncio](https://docs.python.org/3/library/asyncio.html) `await` syntax for concurrency:
 
@@ -133,39 +139,67 @@ Some components LangChain implements, some components we rely on third-party int
 <span data-heading-keywords="chat model,chat models"></span>
 
 Language models that use a sequence of messages as inputs and return chat messages as outputs (as opposed to using plain text).
-These are traditionally newer models (older models are generally `LLMs`, see above).
+These are traditionally newer models (older models are generally `LLMs`, see below).
 Chat models support the assignment of distinct roles to conversation messages, helping to distinguish messages from the AI, users, and instructions such as system messages.
 
 Although the underlying models are messages in, message out, the LangChain wrappers also allow these models to take a string as input. This means you can easily use chat models in place of LLMs.
 
-When a string is passed in as input, it is converted to a HumanMessage and then passed to the underlying model.
+When a string is passed in as input, it is converted to a `HumanMessage` and then passed to the underlying model.
 
-LangChain does not provide any ChatModels, rather we rely on third party integrations.
+LangChain does not host any Chat Models, rather we rely on third party integrations.
 
 We have some standardized parameters when constructing ChatModels:
 - `model`: the name of the model
+- `temperature`: the sampling temperature
+- `timeout`: request timeout
+- `max_tokens`: max tokens to generate
+- `stop`: default stop sequences
+- `max_retries`: max number of times to retry requests
+- `api_key`: API key for the model provider
+- `base_url`: endpoint to send requests to
 
-ChatModels also accept other parameters that are specific to that integration.
+Some important things to note:
+- standard params only apply to model providers that expose parameters with the intended functionality. For example, some providers do not expose a configuration for maximum output tokens, so max_tokens can't be supported on these.
+- standard params are currently only enforced on integrations that have their own integration packages (e.g. `langchain-openai`, `langchain-anthropic`, etc.), they're not enforced on models in ``langchain-community``.
+
+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
-**Tool Calling** Some chat models have been fine-tuned for tool calling and provide a dedicated API for tool calling.
+Some chat models have been fine-tuned for **tool calling** and provide a dedicated API for it.
 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.
 :::
 
 For specifics on how to use chat models, see the [relevant how-to guides here](/docs/how_to/#chat-models).
 
+#### Multimodality
+
+Some chat models are multimodal, accepting images, audio and even video as inputs. These are still less common, meaning model providers haven't standardized on the "best" way to define the API. Multimodal **outputs** are even less common. As such, we've kept our multimodal abstractions fairly light weight and plan to further solidify the multimodal APIs and interaction patterns as the field matures.
+
+In LangChain, most chat models that support multimodal inputs also accept those values in OpenAI's content blocks format. So far this is restricted to image inputs. For models like Gemini which support video and other bytes input, the APIs also support the native, model-specific representations.
+
+For specifics on how to use multimodal models, see the [relevant how-to guides here](/docs/how_to/#multimodal).
+
+For a full list of LangChain model providers with multimodal models, [check out this table](/docs/integrations/chat/#advanced-features).
+
 ### LLMs
 <span data-heading-keywords="llm,llms"></span>
 
+:::caution
+Pure text-in/text-out LLMs tend to be older or lower-level. Many popular models are best used as [chat completion models](/docs/concepts/#chat-models),
+even for non-chat use cases.
+
+You are probably looking for [the section above instead](/docs/concepts/#chat-models).
+:::
+
 Language models that takes a string as input and returns a string.
-These are traditionally older models (newer models generally are `ChatModels`, see below).
+These are traditionally older models (newer models generally are [Chat Models](/docs/concepts/#chat-models), see above).
 
 Although the underlying models are string in, string out, the LangChain wrappers also allow these models to take messages as input.
-This makes them interchangeable with ChatModels.
+This gives them the same interface as [Chat Models](/docs/concepts/#chat-models).
 When messages are passed in as input, they will be formatted into a string under the hood before being passed to the underlying model.
 
-LangChain does not provide any LLMs, rather we rely on third party integrations.
+LangChain does not host any LLMs, rather we rely on third party integrations.
 
 For specifics on how to use LLMs, see the [relevant how-to guides here](/docs/how_to/#llms).
 
@@ -202,7 +236,7 @@ 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 dictionaries. Each dictionary has the following keys:
+This property returns a list of `ToolCall`s. A `ToolCall` is a dictionary with the following arguments:
 
 - `name`: The name of the tool that should be called.
 - `args`: The arguments to that tool.
@@ -212,13 +246,18 @@ This property returns a list of dictionaries. Each dictionary has the following
 
 This represents a system message, which tells the model how to behave. Not every model provider supports this.
 
-#### 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.
+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.
+
+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.
 
 
 ### Prompt templates
@@ -363,7 +402,7 @@ An essential component of a conversation is being able to refer to information i
 At bare minimum, a conversational system should be able to access some window of past messages directly.
 
 The concept of `ChatHistory` refers to a class in LangChain which can be used to wrap an arbitrary chain.
-This `ChatHistory` will keep track of inputs and outputs of the underlying chain, and append them as messages to a message database
+This `ChatHistory` will keep track of inputs and outputs of the underlying chain, and append them as messages to a message database.
 Future interactions will then load those messages and pass them into the chain as part of the input.
 
 ### Documents
@@ -415,9 +454,14 @@ For specifics on how to use text splitters, see the [relevant how-to guides here
 ### Embedding models
 <span data-heading-keywords="embedding,embeddings"></span>
 
-The Embeddings class is a class designed for interfacing with text embedding models. There are lots of embedding model providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them.
+Embedding models create a vector representation of a piece of text. You can think of a vector as an array of numbers that captures the semantic meaning of the text.
+By representing the text in this way, you can perform mathematical operations that allow you to do things like search for other pieces of text that are most similar in meaning.
+These natural language search capabilities underpin many types of [context retrieval](/docs/concepts/#retrieval),
+where we provide an LLM with the relevant data it needs to effectively respond to a query.
 
-Embeddings create a vector representation of a piece of text. This is useful because it means we can think about text in the vector space, and do things like semantic search where we look for pieces of text that are most similar in the vector space.
+![](/img/embeddings.png)
+
+The `Embeddings` class is a class designed for interfacing with text embedding models. There are many different embedding model providers (OpenAI, Cohere, Hugging Face, etc) and local models, and this class is designed to provide a standard interface for all of them.
 
 The base Embeddings class in LangChain provides two methods: one for embedding documents and one for embedding a query. The former takes as input multiple texts, while the latter takes a single text. The reason for having these as two separate methods is that some embedding providers have different embedding methods for documents (to be searched over) vs queries (the search query itself).
 
@@ -430,6 +474,9 @@ One of the most common ways to store and search over unstructured data is to emb
 and then at query time to embed the unstructured query and retrieve the embedding vectors that are 'most similar' to the embedded query.
 A vector store takes care of storing embedded data and performing vector search for you.
 
+Most vector stores can also store metadata about embedded vectors and support filtering on that metadata before
+similarity search, allowing you more control over returned documents.
+
 Vector stores can be converted to the retriever interface by doing:
 
 ```python
@@ -445,42 +492,136 @@ For specifics on how to use vector stores, see the [relevant how-to guides here]
 A retriever is an interface that returns documents given an unstructured query.
 It is more general than a vector store.
 A retriever does not need to be able to store documents, only to return (or retrieve) them.
-Retrievers can be created from vectorstores, but are also broad enough to include [Wikipedia search](/docs/integrations/retrievers/wikipedia/) and [Amazon Kendra](/docs/integrations/retrievers/amazon_kendra_retriever/).
+Retrievers can be created from vector stores, but are also broad enough to include [Wikipedia search](/docs/integrations/retrievers/wikipedia/) and [Amazon Kendra](/docs/integrations/retrievers/amazon_kendra_retriever/).
 
 Retrievers accept a string query as input and return a list of Document's as output.
 
 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/) or
+[caching embeddings](/docs/how_to/caching_embeddings/), having a form 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 interfaces that an agent, a chain, or a chat model / LLM can use to interact with the world.
+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.
 
-A tool consists of the following components:
+A tool consists of:
 
-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)
+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).
 
-The name, description and JSON schema are provided as context
-to the LLM, allowing the LLM to determine how to use the tool
-appropriately.
+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:
 
-Given a list of available tools and a prompt, an LLM can request
-that one or more tools be invoked with appropriate arguments.
+```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(...), ...], ...)
+```
 
-Generally, when designing tools to be used by a chat model or LLM, it is important to keep in mind the following:
+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.
 
-- 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.
+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:
 
-For specifics on how to use tools, see the [relevant how-to guides here](/docs/how_to/#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/).
 
 ### 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.
 
@@ -514,13 +655,27 @@ If you are still using AgentExecutor, do not fear: we still have a guide on [how
 It is recommended, however, that you start to transition to LangGraph.
 In order to assist in this we have put together a [transition guide on how to do so](/docs/how_to/migrate_agent).
 
-### Multimodal
+#### ReAct agents
+<span data-heading-keywords="react,react agent"></span>
 
-Some models are multimodal, accepting images, audio and even video as inputs. These are still less common, meaning model providers haven't standardized on the "best" way to define the API. Multimodal **outputs** are even less common. As such, we've kept our multimodal abstractions fairly light weight and plan to further solidify the multimodal APIs and interaction patterns as the field matures.
+One popular architecture for building agents is [**ReAct**](https://arxiv.org/abs/2210.03629).
+ReAct combines reasoning and acting in an iterative process - in fact the name "ReAct" stands for "Reason" and "Act".
 
-In LangChain, most chat models that support multimodal inputs also accept those values in OpenAI's content blocks format. So far this is restricted to image inputs. For models like Gemini which support video and other bytes input, the APIs also support the native, model-specific representations.
+The general flow looks like this:
 
-For specifics on how to use multimodal models, see the [relevant how-to guides here](/docs/how_to/#multimodal).
+- The model will "think" about what step to take in response to an input and any previous observations.
+- The model will then choose an action from available tools (or choose to respond to the user).
+- The model will generate arguments to that tool.
+- The agent runtime (executor) will parse out the chosen tool and call it with the generated arguments.
+- The executor will return the results of the tool call back to the model as an observation.
+- This process repeats until the agent chooses to respond.
+
+There are general prompting based implementations that do not require any model-specific features, but the most
+reliable implementations use features like [tool calling](/docs/how_to/tool_calling/) to reliably format outputs
+and reduce variance.
+
+Please see the [LangGraph documentation](https://langchain-ai.github.io/langgraph/) for more information,
+or [this how-to guide](/docs/how_to/migrate_agent/) for specific information on migrating to LangGraph.
 
 ### Callbacks
 
@@ -596,6 +751,121 @@ For specifics on how to use callbacks, see the [relevant how-to guides here](/do
 
 ## Techniques
 
+### Streaming
+<span data-heading-keywords="stream,streaming"></span>
+
+Individual LLM calls often run for much longer than traditional resource requests.
+This compounds when you build more complex chains or agents that require multiple reasoning steps.
+
+Fortunately, LLMs generate output iteratively, which means it's possible to show sensible intermediate results
+before the final response is ready. Consuming output as soon as it becomes available has therefore become a vital part of the UX
+around building apps with LLMs to help alleviate latency issues, and LangChain aims to have first-class support for streaming.
+
+Below, we'll discuss some concepts and considerations around streaming in LangChain.
+
+#### `.stream()` and `.astream()`
+
+Most modules in LangChain include the `.stream()` method (and the equivalent `.astream()` method for [async](https://docs.python.org/3/library/asyncio.html) environments) as an ergonomic streaming interface.
+`.stream()` returns an iterator, which you can consume with a simple `for` loop. Here's an example with a chat model:
+
+```python
+from langchain_anthropic import ChatAnthropic
+
+model = ChatAnthropic(model="claude-3-sonnet-20240229")
+
+for chunk in model.stream("what color is the sky?"):
+    print(chunk.content, end="|", flush=True)
+```
+
+For models (or other components) that don't support streaming natively, this iterator would just yield a single chunk, but
+you could still use the same general pattern when calling them. Using `.stream()` will also automatically call the model in streaming mode
+without the need to provide additional config.
+
+The type of each outputted chunk depends on the type of component - for example, chat models yield [`AIMessageChunks`](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html).
+Because this method is part of [LangChain Expression Language](/docs/concepts/#langchain-expression-language-lcel),
+you can handle formatting differences from different outputs using an [output parser](/docs/concepts/#output-parsers) to transform
+each yielded chunk.
+
+You can check out [this guide](/docs/how_to/streaming/#using-stream) for more detail on how to use `.stream()`.
+
+#### `.astream_events()`
+<span data-heading-keywords="astream_events,stream_events,stream events"></span>
+
+While the `.stream()` method is intuitive, it can only return the final generated value of your chain. This is fine for single LLM calls,
+but as you build more complex chains of several LLM calls together, you may want to use the intermediate values of
+the chain alongside the final output - for example, returning sources alongside the final generation when building a chat
+over documents app.
+
+There are ways to do this [using callbacks](/docs/concepts/#callbacks-1), or by constructing your chain in such a way that it passes intermediate
+values to the end with something like chained [`.assign()`](/docs/how_to/passthrough/) calls, but LangChain also includes an
+`.astream_events()` method that combines the flexibility of callbacks with the ergonomics of `.stream()`. When called, it returns an iterator
+which yields [various types of events](/docs/how_to/streaming/#event-reference) that you can filter and process according
+to the needs of your project.
+
+Here's one small example that prints just events containing streamed chat model output:
+
+```python
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_anthropic import ChatAnthropic
+
+model = ChatAnthropic(model="claude-3-sonnet-20240229")
+
+prompt = ChatPromptTemplate.from_template("tell me a joke about {topic}")
+parser = StrOutputParser()
+chain = prompt | model | parser
+
+async for event in chain.astream_events({"topic": "parrot"}, version="v2"):
+    kind = event["event"]
+    if kind == "on_chat_model_stream":
+        print(event, end="|", flush=True)
+```
+
+You can roughly think of it as an iterator over callback events (though the format differs) - and you can use it on almost all LangChain components!
+
+See [this guide](/docs/how_to/streaming/#using-stream-events) for more detailed information on how to use `.astream_events()`,
+including a table listing available events.
+
+#### Callbacks
+
+The lowest level way to stream outputs from LLMs in LangChain is via the [callbacks](/docs/concepts/#callbacks) system. You can pass a
+callback handler that handles the [`on_llm_new_token`](https://api.python.langchain.com/en/latest/callbacks/langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.html#langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.on_llm_new_token) event into LangChain components. When that component is invoked, any
+[LLM](/docs/concepts/#llms) or [chat model](/docs/concepts/#chat-models) contained in the component calls
+the callback with the generated token. Within the callback, you could pipe the tokens into some other destination, e.g. a HTTP response.
+You can also handle the [`on_llm_end`](https://api.python.langchain.com/en/latest/callbacks/langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.html#langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.on_llm_end) event to perform any necessary cleanup.
+
+You can see [this how-to section](/docs/how_to/#callbacks) for more specifics on using callbacks.
+
+Callbacks were the first technique for streaming introduced in LangChain. While powerful and generalizable,
+they can be unwieldy for developers. For example:
+
+- You need to explicitly initialize and manage some aggregator or other stream to collect results.
+- The execution order isn't explicitly guaranteed, and you could theoretically have a callback run after the `.invoke()` method finishes.
+- Providers would often make you pass an additional parameter to stream outputs instead of returning them all at once.
+- You would often ignore the result of the actual model call in favor of callback results.
+
+#### Tokens
+
+The unit that most model providers use to measure input and output is via a unit called a **token**.
+Tokens are the basic units that language models read and generate when processing or producing text.
+The exact definition of a token can vary depending on the specific way the model was trained -
+for instance, in English, a token could be a single word like "apple", or a part of a word like "app".
+
+When you send a model a prompt, the words and characters in the prompt are encoded into tokens using a **tokenizer**.
+The model then streams back generated output tokens, which the tokenizer decodes into human-readable text.
+The below example shows how OpenAI models tokenize `LangChain is cool!`:
+
+![](/img/tokenization.png)
+
+You can see that it gets split into 5 different tokens, and that the boundaries between tokens are not exactly the same as word boundaries.
+
+The reason language models use tokens rather than something more immediately intuitive like "characters"
+has to do with how they process and understand text. At a high-level, language models iteratively predict their next generated output based on
+the initial input and their previous generations. Training the model using tokens language models to handle linguistic
+units (like words or subwords) that carry meaning, rather than individual characters, which makes it easier for the model
+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
@@ -605,67 +875,390 @@ we treat all models as though they can return multiple tool or function calls in
 each message.
 :::
 
-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
+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.
 
-A tool call includes a name, arguments dict, and an optional identifier. The
-arguments dict is structured `{argument_name: argument_value}`.
+![Diagram of a tool call by a chat model](/img/tool_call.png)
 
-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).
+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.
+* `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.
 
-There are two main use cases for function/tool calling:
+#### 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
+range of inputs, but for some use-cases, it can be useful to constrain the LLM's output
+to a specific format or structure. This is referred to as **structured output**.
+
+For example, if the output is to be stored in a relational database,
+it is much easier if the model generates output that adheres to a defined schema or format.
+[Extracting specific information](/docs/tutorials/extraction/) from unstructured text is another
+case where this is particularly useful. Most commonly, the output format will be JSON,
+though other formats such as [YAML](/docs/how_to/output_parser_yaml/) can be useful too. Below, we'll discuss
+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.
+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.
+In addition to your query, you can give instructions describing what kind of output you'd like, then
+parse the output using an [output parser](/docs/concepts/#output-parsers) to convert the raw
+model message or string output into something more easily manipulated.
+
+The biggest benefit to raw prompting is its flexibility:
+
+- Raw prompting does not require any special model features, only sufficient reasoning capability to understand
+the passed schema.
+- You can prompt for any format you'd like, not just JSON. This can be useful if the model you
+are using is more heavily trained on a certain type of data, such as XML or YAML.
+
+However, there are some drawbacks too:
+
+- LLMs are non-deterministic, and prompting a LLM to consistently output data in the exactly correct format
+for smooth parsing can be surprisingly difficult and model-specific.
+- Individual models have quirks depending on the data they were trained on, and optimizing prompts can be quite difficult.
+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.
+
+#### JSON mode
+<span data-heading-keywords="json mode"></span>
+
+Some models, such as [Mistral](/docs/integrations/chat/mistralai/), [OpenAI](/docs/integrations/chat/openai/),
+[Together AI](/docs/integrations/chat/together/) and [Ollama](/docs/integrations/chat/ollama/),
+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/).
+
+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.
+
+Here's an example:
+
+```python
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_openai import ChatOpenAI
+from langchain.output_parsers.json import SimpleJsonOutputParser
+
+model = ChatOpenAI(
+    model="gpt-4o",
+    model_kwargs={ "response_format": { "type": "json_object" } },
+)
+
+prompt = ChatPromptTemplate.from_template(
+    "Answer the user's question to the best of your ability."
+    'You must always output a JSON object with an "answer" key and a "followup_question" key.'
+    "{question}"
+)
+
+chain = prompt | model | SimpleJsonOutputParser()
+
+chain.invoke({ "question": "What is the powerhouse of the cell?" })
+```
+
+```
+{'answer': 'The powerhouse of the cell is the mitochondrion. It is responsible for producing energy in the form of ATP through cellular respiration.',
+ 'followup_question': 'Would you like to know more about how mitochondria produce energy?'}
+```
+
+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}
+
+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.
+
+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.
+
+There are several acceptable formats you can use to bind tools to a model in LangChain. Here's one example:
+
+```python
+from langchain_core.pydantic_v1 import BaseModel, Field
+from langchain_openai import ChatOpenAI
+
+class ResponseFormatter(BaseModel):
+    """Always use this tool to structure your response to the user."""
+
+    answer: str = Field(description="The answer to the user's question")
+    followup_question: str = Field(description="A followup question the user could ask")
+
+model = ChatOpenAI(
+    model="gpt-4o",
+    temperature=0,
+)
+
+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:
 
 - [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/)
+- [How to use a model to call tools](/docs/how_to/tool_calling)
+
+For a full list of model providers that support tool calling, [see this table](/docs/integrations/chat/#advanced-features).
 
 ### Retrieval
 
-LangChain provides several advanced retrieval types. A full list is below, along with the following information:
+LLMs are trained on a large but fixed dataset, limiting their ability to reason over private or recent information. Fine-tuning an LLM with specific facts is one way to mitigate this, but is often [poorly suited for factual recall](https://www.anyscale.com/blog/fine-tuning-is-for-form-not-facts) and [can be costly](https://www.glean.com/blog/how-to-build-an-ai-assistant-for-the-enterprise). 
+Retrieval is the process of providing relevant information to an LLM to improve its response for a given input. Retrieval augmented generation (RAG) is the process of grounding the LLM generation (output) using the retrieved information.
 
-**Name**: Name of the retrieval algorithm.
+:::tip
 
-**Index Type**: Which index type (if any) this relies on.
+* See our RAG from Scratch [code](https://github.com/langchain-ai/rag-from-scratch) and [video series](https://youtube.com/playlist?list=PLfaIDFEXuae2LXbO1_PKyVJiQ23ZztA0x&feature=shared).
+* For a high-level guide on retrieval, see this [tutorial on RAG](/docs/tutorials/rag/).
 
-**Uses an LLM**: Whether this retrieval method uses an LLM.
+:::
 
-**When to Use**: Our commentary on when you should considering using this retrieval method.
+RAG is only as good as the retrieved documents’ relevance and quality. Fortunately, an emerging set of techniques can be employed to design and improve RAG systems. We've focused on taxonomizing and summarizing many of these techniques (see below figure) and will share some high-level strategic guidance in the following sections.
+You can and should experiment with using different pieces together. You might also find [this LangSmith guide](https://docs.smith.langchain.com/how_to_guides/evaluation/evaluate_llm_application) useful for showing how to evaluate different iterations of your app.
 
-**Description**: Description of what this retrieval algorithm is doing.
+![](/img/rag_landscape.png)
+
+#### Query Translation
+
+First, consider the user input(s) to your RAG system. Ideally, a RAG system can handle a wide range of inputs, from poorly worded questions to complex multi-part queries.
+**Using an LLM to review and optionally modify the input is the central idea behind query translation.** This serves as a general buffer, optimizing raw user inputs for your retrieval system. 
+For example, this can be as simple as extracting keywords or as complex as generating multiple sub-questions for a complex query.
+
+| Name          | When to use | Description |
+|---------------|-------------|-------------|
+| [Multi-query](/docs/how_to/MultiQueryRetriever/)   | When you need to cover multiple perspectives of a question. | Rewrite the user question from multiple perspectives, retrieve documents for each rewritten question, return the unique documents for all queries. |
+| [Decomposition](https://github.com/langchain-ai/rag-from-scratch/blob/main/rag_from_scratch_5_to_9.ipynb) | When a question can be broken down into smaller subproblems. | Decompose a question into a set of subproblems / questions, which can either be solved sequentially (use the answer from first + retrieval to answer the second) or in parallel (consolidate each answer into final answer). |
+| [Step-back](https://github.com/langchain-ai/rag-from-scratch/blob/main/rag_from_scratch_5_to_9.ipynb)     | When a higher-level conceptual understanding is required. | First prompt the LLM to ask a generic step-back question about higher-level concepts or principles, and retrieve relevant facts about them. Use this grounding to help answer the user question. |
+| [HyDE](https://github.com/langchain-ai/rag-from-scratch/blob/main/rag_from_scratch_5_to_9.ipynb)          | If you have challenges retrieving relevant documents using the raw user inputs. | Use an LLM to convert questions into hypothetical documents that answer the question. Use the embedded hypothetical documents to retrieve real documents with the premise that doc-doc similarity search can produce more relevant matches. |
+
+:::tip
+
+See our RAG from Scratch videos for a few different specific approaches:
+- [Multi-query](https://youtu.be/JChPi0CRnDY?feature=shared)
+- [Decomposition](https://youtu.be/h0OPWlEOank?feature=shared)
+- [Step-back](https://youtu.be/xn1jEjRyJ2U?feature=shared)
+- [HyDE](https://youtu.be/SaDzIVkYqyY?feature=shared)
+
+:::
+
+#### Routing
+
+Second, consider the data sources available to your RAG system. You want to query across more than one database or across structured and unstructured data sources. **Using an LLM to review the input and route it to the appropriate data source is a simple and effective approach for querying across sources.**
+
+| Name             | When to use                                | Description |
+|------------------|--------------------------------------------|-------------|
+| [Logical routing](/docs/how_to/routing/)  | When you can prompt an LLM with rules to decide where to route the input. | Logical routing can use an LLM to reason about the query and choose which datastore is most appropriate. |
+| [Semantic routing](/docs/how_to/routing/#routing-by-semantic-similarity) | When semantic similarity is an effective way to determine where to route the input. | Semantic routing embeds both query and, typically a set of prompts. It then chooses the appropriate prompt based upon similarity. |
+
+:::tip
+
+See our RAG from Scratch video on [routing](https://youtu.be/pfpIndq7Fi8?feature=shared).  
+
+:::
+
+#### Query Construction
+
+Third, consider whether any of your data sources require specific query formats. Many structured databases use SQL. Vector stores often have specific syntax for applying keyword filters to document metadata. **Using an LLM to convert a natural language query into a query syntax is a popular and powerful approach.**
+In particular, [text-to-SQL](/docs/tutorials/sql_qa/), [text-to-Cypher](/docs/tutorials/graph/), and [query analysis for metadata filters](/docs/tutorials/query_analysis/#query-analysis) are useful ways to interact with structured, graph, and vector databases respectively. 
+
+| Name                                        | When to Use                                                                                                                                   | Description                                                                                                                                                                                                                                                                                      |
+|---------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| [Text to SQL](/docs/tutorials/sql_qa/)      | If users are asking questions that require information housed in a relational database, accessible via SQL.                                   | This uses an LLM to transform user input into a SQL query.                                             |
+| [Text-to-Cypher](/docs/tutorials/graph/)    | If users are asking questions that require information housed in a graph database, accessible via Cypher.                                     | This uses an LLM to transform user input into a Cypher query.                                              |
+| [Self Query](/docs/how_to/self_query/)      | If users are asking questions that are better answered by fetching documents based on metadata rather than similarity with the text.          | This uses an LLM to transform user input into two things: (1) a string to look up semantically, (2) a metadata filter to go along with it. This is useful because oftentimes questions are about the METADATA of documents (not the content itself).                                              |
+
+:::tip
+
+See our [blog post overview](https://blog.langchain.dev/query-construction/) and RAG from Scratch video on [query construction](https://youtu.be/kl6NwWYxvbM?feature=shared), the process of text-to-DSL where DSL is a domain specific language required to interact with a given database. This converts user questions into structured queries. 
+
+:::
+
+#### 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).
+
+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. 
+
+Two approaches can address this tension: (1) [Multi Vector](/docs/how_to/multi_vector/) retriever using an LLM to translate documents into any form (e.g., often into a summary) that is well-suited for indexing, but returns full documents to the LLM for generation. (2) [ParentDocument](/docs/how_to/parent_document_retriever/) retriever embeds document chunks, but also returns full documents. The idea is to get the best of both worlds: use concise representations (summaries or chunks) for retrieval, but use the full documents for answer generation.
 
 | Name                      | Index Type                   | Uses an LLM               | When to Use                                                                                                                                   | Description                                                                                                                                                                                                                                                                                      |
 |---------------------------|------------------------------|---------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| [Vectorstore](/docs/how_to/vectorstore_retriever/)               | Vectorstore                  | No                        | If you are just getting started and looking for something quick and easy.                                                                     | This is the simplest method and the one that is easiest to get started with. It involves creating embeddings for each piece of text.                                                                                                                                                             |
-| [ParentDocument](/docs/how_to/parent_document_retriever/)            | Vectorstore + Document Store | No                        | If your pages have lots of smaller pieces of distinct information that are best indexed by themselves, but best retrieved all together.       | This involves indexing multiple chunks for each document. Then you find the chunks that are most similar in embedding space, but you retrieve the whole parent document and return that (rather than individual chunks).                                                                         |
-| [Multi Vector](/docs/how_to/multi_vector/)              | Vectorstore + Document Store | Sometimes during indexing | If you are able to extract information from documents that you think is more relevant to index than the text itself.                          | This involves creating multiple vectors for each document. Each vector could be created in a myriad of ways - examples include summaries of the text and hypothetical questions.                                                                                                                 |
-| [Self Query](/docs/how_to/self_query/)               | Vectorstore                  | Yes                       | If users are asking questions that are better answered by fetching documents based on metadata rather than similarity with the text.          | This uses an LLM to transform user input into two things: (1) a string to look up semantically, (2) a metadata filer to go along with it. This is useful because oftentimes questions are about the METADATA of documents (not the content itself).                                              |
-| [Contextual Compression](/docs/how_to/contextual_compression/)    | Any                          | Sometimes                 | If you are finding that your retrieved documents contain too much irrelevant information and are distracting the LLM.                         | This puts a post-processing step on top of another retriever and extracts only the most relevant information from retrieved documents. This can be done with embeddings or an LLM.                                                                                                               |
-| [Time-Weighted Vectorstore](/docs/how_to/time_weighted_vectorstore/) | Vectorstore                  | No                        | If you have timestamps associated with your documents, and you want to retrieve the most recent ones                                          | This fetches documents based on a combination of semantic similarity (as in normal vector retrieval) and recency (looking at timestamps of indexed documents)                                                                                                                                    |
-| [Multi-Query Retriever](/docs/how_to/MultiQueryRetriever/)     | Any                          | Yes                       | If users are asking questions that are complex and require multiple pieces of distinct information to respond                                 | This uses an LLM to generate multiple queries from the original one. This is useful when the original query needs pieces of information about multiple topics to be properly answered. By generating multiple queries, we can then fetch documents for each of them.                             |
-| [Ensemble](/docs/how_to/ensemble_retriever/)                  | Any                          | No                        | If you have multiple retrieval methods and want to try combining them.                                                                        | This fetches documents from multiple retrievers and then combines them.                                                                                                                                                                                                                          |
+| [Vector store](/docs/how_to/vectorstore_retriever/)               | Vector store                  | No                        | If you are just getting started and looking for something quick and easy.                                                                     | This is the simplest method and the one that is easiest to get started with. It involves creating embeddings for each piece of text.                                                                                                                                                             |
+| [ParentDocument](/docs/how_to/parent_document_retriever/)            | Vector store + Document Store | No                        | If your pages have lots of smaller pieces of distinct information that are best indexed by themselves, but best retrieved all together.       | This involves indexing multiple chunks for each document. Then you find the chunks that are most similar in embedding space, but you retrieve the whole parent document and return that (rather than individual chunks).                                                                         |
+| [Multi Vector](/docs/how_to/multi_vector/)              | Vector store + Document Store | Sometimes during indexing | If you are able to extract information from documents that you think is more relevant to index than the text itself.                          | This involves creating multiple vectors for each document. Each vector could be created in a myriad of ways - examples include summaries of the text and hypothetical questions.                                                                                                                 |
+| [Time-Weighted Vector store](/docs/how_to/time_weighted_vectorstore/) | Vector store                  | No                        | If you have timestamps associated with your documents, and you want to retrieve the most recent ones                                          | This fetches documents based on a combination of semantic similarity (as in normal vector retrieval) and recency (looking at timestamps of indexed documents)                                                                                                                                    |
 
-For a high-level guide on retrieval, see this [tutorial on RAG](/docs/tutorials/rag/).
+:::tip
+
+- See our RAG from Scratch video on [indexing fundamentals](https://youtu.be/bjb_EMsTDKI?feature=shared)
+- See our RAG from Scratch video on [multi vector retriever](https://youtu.be/gTCU9I6QqCE?feature=shared)
+
+:::
+
+Fifth, consider ways to improve the quality of your similarity search itself. Embedding models compress text into fixed-length (vector) representations that capture the semantic content of the document. This compression is useful for search / retrieval, but puts a heavy burden on that single vector representation to capture the semantic nuance / detail of the document. In some cases, irrelevant or redundant content can dilute the semantic usefulness of the embedding.
+
+[ColBERT](https://docs.google.com/presentation/d/1IRhAdGjIevrrotdplHNcc4aXgIYyKamUKTWtB3m3aMU/edit?usp=sharing) is an interesting approach to address this with a higher granularity embeddings: (1) produce a contextually influenced embedding for each token in the document and query, (2) score similarity between each query token and all document tokens, (3) take the max, (4) do this for all query tokens, and (5) take the sum of the max scores (in step 3) for all query tokens to get a query-document similarity score; this token-wise scoring can yield strong results. 
+
+![](/img/colbert.png)
+
+There are some additional tricks to improve the quality of your retrieval. Embeddings excel at capturing semantic information, but may struggle with keyword-based queries. Many [vector stores](/docs/integrations/retrievers/pinecone_hybrid_search/) offer built-in [hybrid-search](https://docs.pinecone.io/guides/data/understanding-hybrid-search) to combine keyword and semantic similarity, which marries the benefits of both approaches. Furthermore, many vector stores have [maximal marginal relevance](https://python.langchain.com/v0.1/docs/modules/model_io/prompts/example_selectors/mmr/), which attempts to diversify the results of a search to avoid returning similar and redundant documents. 
+
+| Name              | When to use                                              | Description |
+|-------------------|----------------------------------------------------------|-------------|
+| [ColBERT](/docs/integrations/providers/ragatouille/#using-colbert-as-a-reranker)           | When higher granularity embeddings are needed.           | ColBERT uses contextually influenced embeddings for each token in the document and query to get a granular query-document similarity score. |
+| [Hybrid search](/docs/integrations/retrievers/pinecone_hybrid_search/)     | When combining keyword-based and semantic similarity.    | Hybrid search combines keyword and semantic similarity, marrying the benefits of both approaches. |
+| [Maximal Marginal Relevance (MMR)](/docs/integrations/vectorstores/pinecone/#maximal-marginal-relevance-searches) | When needing to diversify search results. | MMR attempts to diversify the results of a search to avoid returning similar and redundant documents. |
+
+:::tip
+
+See our RAG from Scratch video on [ColBERT](https://youtu.be/cN6S0Ehm7_8?feature=shared>).
+
+:::
+
+#### Post-processing
+
+Sixth, consider ways to filter or rank retrieved documents. This is very useful if you are [combining documents returned from multiple sources](/docs/integrations/retrievers/cohere-reranker/#doing-reranking-with-coherererank), since it can can down-rank less relevant documents and / or [compress similar documents](/docs/how_to/contextual_compression/#more-built-in-compressors-filters). 
+
+| Name                      | Index Type                   | Uses an LLM               | When to Use                                                                                                                                   | Description                                                                                                                                                                                                                                                                                      |
+|---------------------------|------------------------------|---------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| [Contextual Compression](/docs/how_to/contextual_compression/)    | Any                          | Sometimes                 | If you are finding that your retrieved documents contain too much irrelevant information and are distracting the LLM.                         | This puts a post-processing step on top of another retriever and extracts only the most relevant information from retrieved documents. This can be done with embeddings or an LLM.                                                                                                               |
+| [Ensemble](/docs/how_to/ensemble_retriever/)                  | Any                          | No                        | If you have multiple retrieval methods and want to try combining them.                                                                        | This fetches documents from multiple retrievers and then combines them.                                                                                                                                                                                                                          |
+| [Re-ranking](/docs/integrations/retrievers/cohere-reranker/)                  | Any                          | Yes                        |  If you want to rank retrieved documents based upon relevance, especially if you want to combine results from multiple retrieval methods .                                                                         | Given a query and a list of documents, Rerank indexes the documents from most to least semantically relevant to the query.                                                                                                                                                                                                                         |
+
+:::tip
+
+See our RAG from Scratch video on [RAG-Fusion](https://youtu.be/77qELPbNgxA?feature=shared), on approach for post-processing across multiple queries:  Rewrite the user question from multiple perspectives, retrieve documents for each rewritten question, and combine the ranks of multiple search result lists to produce a single, unified ranking with [Reciprocal Rank Fusion (RRF)](https://towardsdatascience.com/forget-rag-the-future-is-rag-fusion-1147298d8ad1).
+
+:::
+
+#### Generation
+
+**Finally, consider ways to build self-correction into your RAG system.** RAG systems can suffer from low quality retrieval (e.g., if a user question is out of the domain for the index) and / or hallucinations in generation. A naive retrieve-generate pipeline has no ability to detect or self-correct from these kinds of errors. The concept of ["flow engineering"](https://x.com/karpathy/status/1748043513156272416) has been introduced [in the context of code generation](https://arxiv.org/abs/2401.08500): iteratively build an answer to a code question with unit tests to check and self-correct errors. Several works have applied this RAG, such as Self-RAG and Corrective-RAG. In both cases, checks for document relevance, hallucinations, and / or answer quality are performed in the RAG answer generation flow.
+
+We've found that graphs are a great way to reliably express logical flows and have implemented ideas from several of these papers [using LangGraph](https://github.com/langchain-ai/langgraph/tree/main/examples/rag), as shown in the figure below (red - routing, blue - fallback, green - self-correction):
+- **Routing:** Adaptive RAG ([paper](https://arxiv.org/abs/2403.14403)). Route questions to different retrieval approaches, as discussed above 
+- **Fallback:** Corrective RAG ([paper](https://arxiv.org/pdf/2401.15884.pdf)). Fallback to web search if docs are not relevant to query
+- **Self-correction:** Self-RAG ([paper](https://arxiv.org/abs/2310.11511)). Fix answers w/ hallucinations or don’t address question
+
+![](/img/langgraph_rag.png)
+
+| Name              | When to use                                               | Description |
+|-------------------|-----------------------------------------------------------|-------------|
+| Self-RAG          | When needing to fix answers with hallucinations or irrelevant content. | Self-RAG performs checks for document relevance, hallucinations, and answer quality during the RAG answer generation flow, iteratively building an answer and self-correcting errors. |
+| Corrective-RAG    | When needing a fallback mechanism for low relevance docs. | Corrective-RAG includes a fallback (e.g., to web search) if the retrieved documents are not relevant to the query, ensuring higher quality and more relevant retrieval. |
+
+:::tip
+
+See several videos and cookbooks showcasing RAG with LangGraph: 
+- [LangGraph Corrective RAG](https://www.youtube.com/watch?v=E2shqsYwxck)
+- [LangGraph combining Adaptive, Self-RAG, and Corrective RAG](https://www.youtube.com/watch?v=-ROS6gfYIts) 
+- [Cookbooks for RAG using LangGraph](https://github.com/langchain-ai/langgraph/tree/main/examples/rag)
+
+See our LangGraph RAG recipes with partners:
+- [Meta](https://github.com/meta-llama/llama-recipes/tree/main/recipes/3p_integrations/langchain)
+- [Mistral](https://github.com/mistralai/cookbook/tree/main/third_party/langchain)
+
+:::
 
 ### Text splitting
 
@@ -690,8 +1283,31 @@ 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>
 
+Evaluation is the process of assessing the performance and effectiveness of your LLM-powered applications.
+It involves testing the model's responses against a set of predefined criteria or benchmarks to ensure it meets the desired quality standards and fulfills the intended purpose.
+This process is vital for building reliable applications.
 
+![](/img/langsmith_evaluate.png)
 
+[LangSmith](https://docs.smith.langchain.com/) helps with this process in a few ways:
+
+- It makes it easier to create and curate datasets via its tracing and annotation features
+- It provides an evaluation framework that helps you define metrics and run your app against your dataset
+- It allows you to track results over time and automatically run your evaluators on a schedule or as part of CI/Code
+
+To learn more, check out [this LangSmith guide](https://docs.smith.langchain.com/concepts/evaluation).
+
+### Tracing
+<span data-heading-keywords="trace,tracing"></span>
+
+A trace is essentially a series of steps that your application takes to go from input to output.
+Traces contain individual steps called `runs`. These can be individual calls from a model, retriever,
+tool, or sub-chains.
+Tracing gives you observability inside your chains and agents, and is vital in diagnosing issues.
+
+For a deeper dive, check out [this LangSmith conceptual guide](https://docs.smith.langchain.com/concepts/tracing).

docs/docs/contributing/code/guidelines.mdx

@@ -0,0 +1,35 @@
+# General guidelines
+
+Here are some things to keep in mind for all types of contributions:
+
+- Follow the ["fork and pull request"](https://docs.github.com/en/get-started/exploring-projects-on-github/contributing-to-a-project) workflow.
+- Fill out the checked-in pull request template when opening pull requests. Note related issues and tag relevant maintainers.
+- Ensure your PR passes formatting, linting, and testing checks before requesting a review.
+  - If you would like comments or feedback on your current progress, please open an issue or discussion and tag a maintainer.
+  - See the sections on [Testing](/docs/contributing/code/setup#testing) and [Formatting and Linting](/docs/contributing/code/setup#formatting-and-linting) for how to run these checks locally.
+- Backwards compatibility is key. Your changes must not be breaking, except in case of critical bug and security fixes.
+- Look for duplicate PRs or issues that have already been opened before opening a new one.
+- Keep scope as isolated as possible. As a general rule, your changes should not affect more than one package at a time.
+
+## Bugfixes
+
+We encourage and appreciate bugfixes. We ask that you:
+
+- Explain the bug in enough detail for maintainers to be able to reproduce it.
+  - If an accompanying issue exists, link to it. Prefix with `Fixes` so that the issue will close automatically when the PR is merged.
+- Avoid breaking changes if possible.
+- Include unit tests that fail without the bugfix.
+
+If you come across a bug and don't know how to fix it, we ask that you open an issue for it describing in detail the environment in which you encountered the bug.
+
+## New features
+
+We aim to keep the bar high for new features. We generally don't accept new core abstractions, changes to infra, changes to dependencies,
+or new agents/chains from outside contributors without an existing GitHub discussion or issue that demonstrates an acute need for them.
+
+- New features must come with docs, unit tests, and (if appropriate) integration tests.
+- New integrations must come with docs, unit tests, and (if appropriate) integration tests.
+  - See [this page](/docs/contributing/integrations) for more details on contributing new integrations.
+- New functionality should not inherit from or use deprecated methods or classes.
+- We will reject features that are likely to lead to security vulnerabilities or reports.
+- Do not add any hard dependencies. Integrations may add optional dependencies.

docs/docs/contributing/code/index.mdx

@@ -0,0 +1,6 @@
+# Contribute Code
+
+If you would like to add a new feature or update an existing one, please read the resources below before getting started:
+
+- [General guidelines](/docs/contributing/code/guidelines/)
+- [Setup](/docs/contributing/code/setup/)

docs/docs/contributing/code/setup.mdx

@@ -1,36 +1,9 @@
----
-sidebar_position: 1
----
-# Contribute Code
+# Setup
 
-To contribute to this project, please follow the ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow.
-Please do not try to push directly to this repo unless you are a maintainer.
-
-Please follow the checked-in pull request template when opening pull requests. Note related issues and tag relevant
-maintainers.
-
-Pull requests cannot land without passing the formatting, linting, and testing checks first. See [Testing](#testing) and
-[Formatting and Linting](#formatting-and-linting) for how to run these checks locally.
-
-It's essential that we maintain great documentation and testing. If you:
-- Fix a bug
-  - Add a relevant unit or integration test when possible. These live in `tests/unit_tests` and `tests/integration_tests`.
-- Make an improvement
-  - Update any affected example notebooks and documentation. These live in `docs`.
-  - Update unit and integration tests when relevant.
-- Add a feature
-  - Add a demo notebook in `docs/docs/`.
-  - Add unit and integration tests.
-
-We are a small, progress-oriented team. If there's something you'd like to add or change, opening a pull request is the
-best way to get our attention.
-
-## 🚀 Quick Start
-
-This quick start guide explains how to run the repository locally.
+This guide walks through how to run the repository locally and check in your first code.
 For a [development container](https://containers.dev/), see the [.devcontainer folder](https://github.com/langchain-ai/langchain/tree/master/.devcontainer).
 
-### Dependency Management: Poetry and other env/dependency managers
+## Dependency Management: Poetry and other env/dependency managers
 
 This project utilizes [Poetry](https://python-poetry.org/) v1.7.1+ as a dependency manager.
 
@@ -41,7 +14,7 @@ Install Poetry: **[documentation on how to install it](https://python-poetry.org
 ❗Note: If you use `Conda` or `Pyenv` as your environment/package manager, after installing Poetry,
 tell Poetry to use the virtualenv python environment (`poetry config virtualenvs.prefer-active-python true`)
 
-### Different packages
+## Different packages
 
 This repository contains multiple packages:
 - `langchain-core`: Base interfaces for key abstractions as well as logic for combining them in chains (LangChain Expression Language).
@@ -59,7 +32,7 @@ For this quickstart, start with langchain-community:
 cd libs/community
 ```
 
-### Local Development Dependencies
+## Local Development Dependencies
 
 Install langchain-community development requirements (for running langchain, running examples, linting, formatting, tests, and coverage):
 
@@ -79,9 +52,9 @@ If you are still seeing this bug on v1.6.1+, you may also try disabling "modern
 (`poetry config installer.modern-installation false`) and re-installing requirements.
 See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.
 
-### Testing
+## Testing
 
-_In `langchain`, `langchain-community`, and `langchain-experimental`, some test dependencies are optional; see section about optional dependencies_.
+**Note:** In `langchain`, `langchain-community`, and `langchain-experimental`, some test dependencies are optional. See the following section about optional dependencies.
 
 Unit tests cover modular logic that does not require calls to outside APIs.
 If you add new logic, please add a unit test.
@@ -118,11 +91,11 @@ poetry install --with test
 make test
 ```
 
-### Formatting and Linting
+## Formatting and Linting
 
 Run these locally before submitting a PR; the CI system will check also.
 
-#### Code Formatting
+### Code Formatting
 
 Formatting for this project is done via [ruff](https://docs.astral.sh/ruff/rules/).
 
@@ -174,7 +147,7 @@ This can be very helpful when you've made changes to only certain parts of the p
 
 We recognize linting can be annoying - if you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
 
-#### Spellcheck
+### Spellcheck
 
 Spellchecking for this project is done via [codespell](https://github.com/codespell-project/codespell).
 Note that `codespell` finds common typos, so it could have false-positive (correctly spelled but rarely used) and false-negatives (not finding misspelled) words.

docs/docs/contributing/documentation/_category_.yml

@@ -1,2 +0,0 @@
-label: 'Documentation'
-position: 3

docs/docs/contributing/documentation/index.mdx

@@ -0,0 +1,7 @@
+# Contribute Documentation
+
+Documentation is a vital part of LangChain. We welcome both new documentation for new features and 
+community improvements to our current documentation. Please read the resources below before getting started:
+
+- [Documentation style guide](/docs/contributing/documentation/style_guide/)
+- [Setup](/docs/contributing/documentation/setup/)

docs/docs/contributing/documentation/setup.mdx

@@ -1,4 +1,8 @@
-# Technical logistics
+---
+sidebar_class_name: "hidden"
+---
+
+# Setup
 
 LangChain documentation consists of two components:
 
@@ -12,8 +16,6 @@ used to generate the externally facing [API Reference](https://api.python.langch
 The content for the API reference is autogenerated by scanning the docstrings in the codebase. For this reason we ask that
 developers document their code well.
 
-The main documentation is built using [Quarto](https://quarto.org) and [Docusaurus 2](https://docusaurus.io/).
-
 The `API Reference` is largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/)
 from the code and is hosted by [Read the Docs](https://readthedocs.org/).
 
@@ -29,7 +31,7 @@ The content for the main documentation is located in the `/docs` directory of th
 
 The documentation is written using a combination of ipython notebooks (`.ipynb` files)
 and markdown (`.mdx` files). The notebooks are converted to markdown
-using [Quarto](https://quarto.org) and then built using [Docusaurus 2](https://docusaurus.io/).
+and then built using [Docusaurus 2](https://docusaurus.io/).
 
 Feel free to make contributions to the main documentation! 🥰
 
@@ -48,10 +50,6 @@ locally to ensure that it looks good and is free of errors.
 If you're unable to build it locally that's okay as well, as you will be able to
 see a preview of the documentation on the pull request page.
 
-### Install dependencies
-
-- [Quarto](https://quarto.org) - package that converts Jupyter notebooks (`.ipynb` files) into mdx files for serving in Docusaurus. [Download link](https://quarto.org/docs/download/).
-
 From the **monorepo root**, run the following command to install the dependencies:
 
 ```bash
@@ -71,8 +69,6 @@ make docs_clean
 make api_docs_clean
 ```
 
-
-
 Next, you can build the documentation as outlined below:
 
 ```bash

docs/docs/contributing/documentation/style_guide.mdx

@@ -1,10 +1,8 @@
 ---
-sidebar_label: "Style guide"
+sidebar_class_name: "hidden"
 ---
 
-# LangChain Documentation Style Guide
-
-## Introduction
+# Documentation Style Guide
 
 As LangChain continues to grow, the surface area of documentation required to cover it continues to grow too.
 This page provides guidelines for anyone writing documentation for LangChain, as well as some of our philosophies around
@@ -12,116 +10,139 @@ organization and structure.
 
 ## Philosophy
 
-LangChain's documentation aspires to follow the [Diataxis framework](https://diataxis.fr).
-Under this framework, all documentation falls under one of four categories:
+LangChain's documentation follows the [Diataxis framework](https://diataxis.fr).
+Under this framework, all documentation falls under one of four categories: [Tutorials](/docs/contributing/documentation/style_guide/#tutorials),
+[How-to guides](/docs/contributing/documentation/style_guide/#how-to-guides),
+[References](/docs/contributing/documentation/style_guide/#references), and [Explanations](/docs/contributing/documentation/style_guide/#conceptual-guide).
 
-- **Tutorials**: Lessons that take the reader by the hand through a series of conceptual steps to complete a project.
-  - An example of this is our [LCEL streaming guide](/docs/how_to/streaming).
-  - Our guides on [custom components](/docs/how_to/custom_chat_model) is another one.
-- **How-to guides**: Guides that take the reader through the steps required to solve a real-world problem.
-  - The clearest examples of this are our [Use case](/docs/how_to#use-cases) quickstart pages.
-- **Reference**: Technical descriptions of the machinery and how to operate it.
-  - Our [Runnable interface](/docs/concepts#interface) page is an example of this.
-  - The [API reference pages](https://api.python.langchain.com/) are another.
-- **Explanation**: Explanations that clarify and illuminate a particular topic.
-  - The [LCEL primitives pages](/docs/how_to/sequence) are an example of this.
+### Tutorials
+
+Tutorials are lessons that take the reader through a practical activity. Their purpose is to help the user
+gain understanding of concepts and how they interact by showing one way to achieve some goal in a hands-on way. They should **avoid** giving
+multiple permutations of ways to achieve that goal in-depth. Instead, it should guide a new user through a recommended path to accomplishing the tutorial's goal. While the end result of a tutorial does not necessarily need to
+be completely production-ready, it should be useful and practically satisfy the the goal that you clearly stated in the tutorial's introduction. Information on how to address additional scenarios
+belongs in how-to guides.
+
+To quote the Diataxis website:
+
+> A tutorial serves the user’s *acquisition* of skills and knowledge - their study. Its purpose is not to help the user get something done, but to help them learn.
+
+In LangChain, these are often higher level guides that show off end-to-end use cases.
+
+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:
+
+- Focus on guiding the user to get something done, but keep in mind the end-goal is more to impart principles than to create a perfect production system.
+- Be specific, not abstract and follow one path.
+  - No need to go deeply into alternative approaches, but it’s ok to reference them, ideally with a link to an appropriate how-to guide.
+- Get "a point on the board" as soon as possible - something the user can run that outputs something.
+  - You can iterate and expand afterwards.
+  - Try to frequently checkpoint at given steps where the user can run code and see progress.
+- Focus on results, not technical explanation.
+  - Crosslink heavily to appropriate conceptual/reference pages.
+- The first time you mention a LangChain concept, use its full name (e.g. "LangChain Expression Language (LCEL)"), and link to its conceptual/other documentation page.
+  - It's also helpful to add a prerequisite callout that links to any pages with necessary background information.
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as related how-to guides.
+  
+### How-to guides
+
+A how-to guide, as the name implies, demonstrates how to do something discrete and specific.
+It should assume that the user is already familiar with underlying concepts, and is trying to solve an immediate problem, but
+should still give some background or list the scenarios where the information contained within can be relevant.
+They can and should discuss alternatives if one approach may be better than another in certain cases.
+
+To quote the Diataxis website:
+
+> A how-to guide serves the work of the already-competent user, whom you can assume to know what they want to do, and to be able to follow your instructions correctly.
+
+Some examples include:
+
+- [How to: return structured data from a model](/docs/how_to/structured_output/)
+- [How to: write a custom chat model](/docs/how_to/custom_chat_model/)
+
+Here are some high-level tips on writing a good how-to guide:
+
+- Clearly explain what you are guiding the user through at the start.
+- Assume higher intent than a tutorial and show what the user needs to do to get that task done.
+- Assume familiarity of concepts, but explain why suggested actions are helpful.
+  - Crosslink heavily to conceptual/reference pages.
+- Discuss alternatives and responses to real-world tradeoffs that may arise when solving a problem.
+- Use lots of example code.
+  - Prefer full code blocks that the reader can copy and run.
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as other related how-to guides.
+
+### Conceptual guide
+
+LangChain's conceptual guide falls under the **Explanation** quadrant of Diataxis. They should cover LangChain terms and concepts
+in a more abstract way than how-to guides or tutorials, and should be geared towards curious users interested in
+gaining a deeper understanding of the framework. Try to avoid excessively large code examples - the goal here is to
+impart perspective to the user rather than to finish a practical project. These guides should cover **why** things work they way they do.
+
+This guide on documentation style is meant to fall under this category.
+
+To quote the Diataxis website:
+
+> The perspective of explanation is higher and wider than that of the other types. It does not take the user’s eye-level view, as in a how-to guide, or a close-up view of the machinery, like reference material. Its scope in each case is a topic - “an area of knowledge”, that somehow has to be bounded in a reasonable, meaningful way.
+
+Some examples include:
+
+- [Retrieval conceptual docs](/docs/concepts/#retrieval)
+- [Chat model conceptual docs](/docs/concepts/#chat-models)
+
+Here are some high-level tips on writing a good conceptual guide:
+
+- Explain design decisions. Why does concept X exist and why was it designed this way?
+- Use analogies and reference other concepts and alternatives
+- Avoid blending in too much reference content
+- You can and should reference content covered in other guides, but make sure to link to them
+
+### References
+
+References contain detailed, low-level information that describes exactly what functionality exists and how to use it.
+In LangChain, this is mainly our API reference pages, which are populated from docstrings within code.
+References pages are generally not read end-to-end, but are consulted as necessary when a user needs to know
+how to use something specific.
+
+To quote the Diataxis website:
+
+> The only purpose of a reference guide is to describe, as succinctly as possible, and in an orderly way. Whereas the content of tutorials and how-to guides are led by needs of the user, reference material is led by the product it describes.
+
+Many of the reference pages in LangChain are automatically generated from code,
+but here are some high-level tips on writing a good docstring:
+
+- Be concise
+- Discuss special cases and deviations from a user's expectations
+- Go into detail on required inputs and outputs
+- Light details on when one might use the feature are fine, but in-depth details belong in other sections.
 
 Each category serves a distinct purpose and requires a specific approach to writing and structuring the content.
 
-## Taxonomy
-
-Keeping the above in mind, we have sorted LangChain's docs into categories. It is helpful to think in these terms
-when contributing new documentation:
-
-### Getting started
-
-The [getting started section](/docs/introduction) includes a high-level introduction to LangChain, a quickstart that
-tours LangChain's various features, and logistical instructions around installation and project setup.
-
-It contains elements of **How-to guides** and **Explanations**.
-
-### Use cases
-
-[Use cases](/docs/how_to#use-cases) are guides that are meant to show how to use LangChain to accomplish a specific task (RAG, information extraction, etc.).
-The quickstarts should be good entrypoints for first-time LangChain developers who prefer to learn by getting something practical prototyped,
-then taking the pieces apart retrospectively. These should mirror what LangChain is good at.
-
-The quickstart pages here should fit the **How-to guide** category, with the other pages intended to be **Explanations** of more
-in-depth concepts and strategies that accompany the main happy paths.
-
-:::note
-The below sections are listed roughly in order of increasing level of abstraction.
-:::
-
-### Expression Language
-
-[LangChain Expression Language (LCEL)](/docs/concepts#langchain-expression-language) is the fundamental way that most LangChain components fit together, and this section is designed to teach
-developers how to use it to build with LangChain's primitives effectively.
-
-This section should contains **Tutorials** that teach how to stream and use LCEL primitives for more abstract tasks, **Explanations** of specific behaviors,
-and some **References** for how to use different methods in the Runnable interface.
-
-### Components
-
-The [components section](/docs/concepts) covers concepts one level of abstraction higher than LCEL.
-Abstract base classes like `BaseChatModel` and `BaseRetriever` should be covered here, as well as core implementations of these base classes,
-such as `ChatPromptTemplate` and `RecursiveCharacterTextSplitter`. Customization guides belong here too.
-
-This section should contain mostly conceptual **Tutorials**, **References**, and **Explanations** of the components they cover.
-
-:::note
-As a general rule of thumb, everything covered in the `Expression Language` and `Components` sections (with the exception of the `Composition` section of components) should
-cover only components that exist in `langchain_core`.
-:::
-
-### Integrations
-
-The [integrations](/docs/integrations/platforms/) are specific implementations of components. These often involve third-party APIs and services.
-If this is the case, as a general rule, these are maintained by the third-party partner.
-
-This section should contain mostly **Explanations** and **References**, though the actual content here is more flexible than other sections and more at the
-discretion of the third-party provider.
-
-:::note
-Concepts covered in `Integrations` should generally exist in `langchain_community` or specific partner packages.
-:::
-
-### Guides and Ecosystem
-
-The [Guides](/docs/tutorials) and [Ecosystem](https://docs.smith.langchain.com/) sections should contain guides that address higher-level problems than the sections above.
-This includes, but is not limited to, considerations around productionization and development workflows.
-
-These should contain mostly **How-to guides**, **Explanations**, and **Tutorials**.
-
-### API references
-
-LangChain's API references. Should act as **References** (as the name implies) with some **Explanation**-focused content as well. 
-
-## Sample developer journey
-
-We have set up our docs to assist a new developer to LangChain. Let's walk through the intended path:
-
-- The developer lands on https://python.langchain.com, and reads through the introduction and the diagram.
-- If they are just curious, they may be drawn to the [Quickstart](/docs/tutorials/llm_chain) to get a high-level tour of what LangChain contains.
-- If they have a specific task in mind that they want to accomplish, they will be drawn to the Use-Case section. The use-case should provide a good, concrete hook that shows the value LangChain can provide them and be a good entrypoint to the framework.
-- They can then move to learn more about the fundamentals of LangChain through the Expression Language sections.
-- Next, they can learn about LangChain's various components and integrations.
-- Finally, they can get additional knowledge through the Guides.
-
-This is only an ideal of course - sections will inevitably reference lower or higher-level concepts that are documented in other sections.
-
-## Guidelines
+## General guidelines
 
 Here are some other guidelines you should think about when writing and organizing documentation.
 
-### Linking to other sections
+We generally do not merge new tutorials from outside contributors without an actue need.
+We welcome updates as well as new integration docs, how-tos, and references.
+
+### Avoid duplication
+
+Multiple pages that cover the same material in depth are difficult to maintain and cause confusion. There should
+be only one (very rarely two), canonical pages for a given concept or feature. Instead, you should link to other guides.
+
+### Link to other sections
 
 Because sections of the docs do not exist in a vacuum, it is important to link to other sections as often as possible
 to allow a developer to learn more about an unfamiliar topic inline.
 
 This includes linking to the API references as well as conceptual sections!
 
-### Conciseness
+### Be concise
 
 In general, take a less-is-more approach. If a section with a good explanation of a concept already exists, you should link to it rather than
 re-explain it, unless the concept you are documenting presents some new wrinkle.
@@ -130,9 +151,10 @@ Be concise, including in code samples.
 
 ### General style
 
-- Use active voice and present tense whenever possible.
-- Use examples and code snippets to illustrate concepts and usage.
-- Use appropriate header levels (`#`, `##`, `###`, etc.) to organize the content hierarchically.
-- Use bullet points and numbered lists to break down information into easily digestible chunks.
-- Use tables (especially for **Reference** sections) and diagrams often to present information visually.
-- Include the table of contents for longer documentation pages to help readers navigate the content, but hide it for shorter pages.
+- Use active voice and present tense whenever possible
+- Use examples and code snippets to illustrate concepts and usage
+- Use appropriate header levels (`#`, `##`, `###`, etc.) to organize the content hierarchically
+- Use fewer cells with more code to make copy/paste easier
+- Use bullet points and numbered lists to break down information into easily digestible chunks
+- Use tables (especially for **Reference** sections) and diagrams often to present information visually
+- Include the table of contents for longer documentation pages to help readers navigate the content, but hide it for shorter pages

docs/docs/contributing/index.mdx

@@ -12,8 +12,8 @@ As an open-source project in a rapidly developing field, we are extremely open t
 
 There are many ways to contribute to LangChain. Here are some common ways people contribute:
 
-- [**Documentation**](/docs/contributing/documentation/style_guide): Help improve our docs, including this one!
-- [**Code**](./code.mdx): Help us write code, fix bugs, or improve our infrastructure.
+- [**Documentation**](/docs/contributing/documentation/): Help improve our docs, including this one!
+- [**Code**](/docs/contributing/code/): Help us write code, fix bugs, or improve our infrastructure.
 - [**Integrations**](integrations.mdx): Help us integrate with your favorite vendors and tools.
 - [**Discussions**](https://github.com/langchain-ai/langchain/discussions): Help answer usage questions and discuss issues with users.
 
@@ -48,7 +48,7 @@ In a similar vein, we do enforce certain linting, formatting, and documentation
 If you are finding these difficult (or even just annoying) to work with, feel free to contact a maintainer for help -
 we do not want these to get in the way of getting good code into the codebase.
 
-# 🌟 Recognition
+### 🌟 Recognition
 
 If your contribution has made its way into a release, we will want to give you credit on Twitter (only if you want though)!
-If you have a Twitter account you would like us to mention, please let us know in the PR or through another means.
+If you have a Twitter account you would like us to mention, please let us know in the PR or through another means.

docs/docs/contributing/integrations.mdx

@@ -1,6 +1,7 @@
 ---
 sidebar_position: 5
 ---
+
 # Contribute Integrations
 
 To begin, make sure you have all the dependencies outlined in guide on [Contributing Code](/docs/contributing/code/).
@@ -10,7 +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`.
 
@@ -59,6 +60,10 @@ 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/contributing/repo_structure.mdx

@@ -7,6 +7,7 @@ If you plan on contributing to LangChain code or documentation, it can be useful
 to understand the high level structure of the repository.
 
 LangChain is organized as a [monorepo](https://en.wikipedia.org/wiki/Monorepo) that contains multiple packages.
+You can check out our [installation guide](/docs/how_to/installation/) for more on how they fit together.
 
 Here's the structure visualized as a tree:
 
@@ -15,12 +16,22 @@ Here's the structure visualized as a tree:
 ├── cookbook # Tutorials and examples
 ├── docs # Contains content for the documentation here: https://python.langchain.com/
 ├── libs
-│   ├── langchain # Main package
+│   ├── langchain
+│   │   ├── langchain
 │   │   ├── tests/unit_tests # Unit tests (present in each package not shown for brevity)
 │   │   ├── tests/integration_tests # Integration tests (present in each package not shown for brevity)
-│   ├── langchain-community # Third-party integrations
-│   ├── langchain-core # Base interfaces for key abstractions
-│   ├── langchain-experimental # Experimental components and chains
+│   ├── community # Third-party integrations
+│   │   ├── langchain-community
+│   ├── core # Base interfaces for key abstractions
+│   │   ├── langchain-core
+│   ├── experimental # Experimental components and chains
+│   │   ├── langchain-experimental
+|   ├── cli # Command line interface
+│   │   ├── langchain-cli
+│   ├── text-splitters
+│   │   ├── langchain-text-splitters
+│   ├── standard-tests
+│   │   ├── langchain-standard-tests
 │   ├── partners
 │       ├── langchain-partner-1
 │       ├── langchain-partner-2
@@ -41,7 +52,7 @@ There are other files in the root directory level, but their presence should be
 The `/docs` directory contains the content for the documentation that is shown
 at https://python.langchain.com/ and the associated API Reference https://api.python.langchain.com/en/latest/langchain_api_reference.html.
 
-See the [documentation](/docs/contributing/documentation/style_guide) guidelines to learn how to contribute to the documentation.
+See the [documentation](/docs/contributing/documentation/) guidelines to learn how to contribute to the documentation.
 
 ## Code
 
@@ -49,6 +60,6 @@ The `/libs` directory contains the code for the LangChain packages.
 
 To learn more about how to contribute code see the following guidelines:
 
-- [Code](./code.mdx) Learn how to develop in the LangChain codebase.
-- [Integrations](./integrations.mdx) to learn how to contribute to third-party integrations to langchain-community or to start a new partner package.
-- [Testing](./testing.mdx) guidelines to learn how to write tests for the packages.
+- [Code](/docs/contributing/code/): Learn how to develop in the LangChain codebase.
+- [Integrations](./integrations.mdx): Learn how to contribute to third-party integrations to `langchain-community` or to start a new partner package.
+- [Testing](./testing.mdx): Guidelines to learn how to write tests for the packages.

docs/docs/contributing/testing.mdx

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 2
+sidebar_position: 6
 ---
 
 # Testing

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 lines\n",
+    "        return list(filter(None, lines))  # Remove empty lines\n",
     "\n",
     "\n",
     "output_parser = LineListOutputParser()\n",

docs/docs/how_to/binding.ipynb

@@ -23,7 +23,7 @@
     "This guide assumes familiarity with the following concepts:\n",
     "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
     "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Tool calling](/docs/how_to/tool_calling/)\n",
+    "- [Tool calling](/docs/how_to/tool_calling)\n",
     "\n",
     ":::\n",
     "\n",
@@ -142,7 +142,7 @@
     "\n",
     "## Attaching OpenAI tools\n",
     "\n",
-    "Another common use-case is tool calling. While you should generally use the [`.bind_tools()`](/docs/how_to/tool_calling/) method for tool-calling models, you can also bind provider-specific args directly if you want lower level control:"
+    "Another common use-case is tool calling. While you should generally use the [`.bind_tools()`](/docs/how_to/tool_calling) method for tool-calling models, you can also bind provider-specific args directly if you want lower level control:"
    ]
   },
   {

docs/docs/how_to/callbacks_custom_events.ipynb

@@ -0,0 +1,342 @@
+{
+ "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

@@ -0,0 +1,146 @@
+{
+ "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

@@ -5,7 +5,7 @@
    "id": "cfdf4f09-8125-4ed1-8063-6feed57da8a3",
    "metadata": {},
    "source": [
-    "# How to let your end users choose their model\n",
+    "# How to init any model in one line\n",
     "\n",
     "Many LLM applications let end users specify what model provider and model they want the application to be powered by. This requires writing some logic to initialize different ChatModels based on some user configuration. The `init_chat_model()` helper method makes it easy to initialize a number of different model integrations without having to worry about import paths and class names.\n",
     "\n",
@@ -15,6 +15,12 @@
     "\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",
     ":::"
    ]
   },
@@ -25,7 +31,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -qU langchain langchain-openai langchain-anthropic langchain-google-vertexai"
+    "%pip install -qU langchain>=0.2.8 langchain-openai langchain-anthropic langchain-google-vertexai"
    ]
   },
   {
@@ -76,32 +82,6 @@
     "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",
@@ -125,12 +105,215 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "da07b5c0-d2e6-42e4-bfcd-2efcfaae6221",
+   "cell_type": "markdown",
+   "id": "476a44db-c50d-4846-951d-0f1c9ba8bbaa",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "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",
+   "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"
+   ]
   }
  ],
  "metadata": {
@@ -149,7 +332,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.9"
   }
  },
  "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 >= 0.1.8`."
+    "This guide requires `langchain-openai >= 0.1.9`."
    ]
   },
   {
@@ -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 >= 0.1.8` and can be enabled by setting `stream_options={\"include_usage\": True}`.\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",
     "\n",
     "```{=mdx}\n",
     ":::note\n",
@@ -172,18 +172,18 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "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"
+      "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"
      ]
     }
    ],
@@ -191,7 +191,7 @@
     "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
     "\n",
     "aggregate = None\n",
-    "for chunk in llm.stream(\"hello\", stream_options={\"include_usage\": True}):\n",
+    "for chunk in llm.stream(\"hello\", stream_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 `\"include_usage\"` to False in `stream_options`, or omit it from the parameters:"
+    "To disable streaming token counts for OpenAI, set `stream_usage` to False, or omit it from the parameters:"
    ]
   },
   {
@@ -242,17 +242,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "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"
+      "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"
      ]
     }
    ],
@@ -267,7 +267,7 @@
    "id": "6a5d9617-be3a-419a-9276-de9c29fa50ae",
    "metadata": {},
    "source": [
-    "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",
+    "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",
     "\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": "57dec1fb-bd9c-4c98-8798-8fbbe67f6b2c",
+   "id": "0b1523d8-127e-4314-82fa-bd97aca37f9a",
    "metadata": {},
    "outputs": [
     {
@@ -301,7 +301,7 @@
     "\n",
     "llm = ChatOpenAI(\n",
     "    model=\"gpt-3.5-turbo-0125\",\n",
-    "    model_kwargs={\"stream_options\": {\"include_usage\": True}},\n",
+    "    stream_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": "31667d54",
+   "id": "b04a4486-72fd-48ce-8f9e-5d281b441195",
    "metadata": {},
    "outputs": [
     {
@@ -361,7 +361,11 @@
     "\n",
     "from langchain_community.callbacks.manager import get_openai_callback\n",
     "\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(\n",
+    "    model=\"gpt-3.5-turbo-0125\",\n",
+    "    temperature=0,\n",
+    "    stream_usage=True,\n",
+    ")\n",
     "\n",
     "with get_openai_callback() as cb:\n",
     "    result = llm.invoke(\"Tell me a joke\")\n",
@@ -379,14 +383,14 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "e09420f4",
+   "id": "05f22a1d-b021-490f-8840-f628a07459f2",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "55\n"
+      "54\n"
      ]
     }
    ],
@@ -397,37 +401,29 @@
     "    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": "b241069a-265d-4497-af34-b0a5f95ae67f",
+   "id": "c00c9158-7bb4-4279-88e6-ea70f46e6ac2",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "28\n"
+      "Tokens Used: 27\n",
+      "\tPrompt Tokens: 11\n",
+      "\tCompletion Tokens: 16\n",
+      "Successful Requests: 1\n",
+      "Total Cost (USD): $2.95e-05\n"
      ]
     }
    ],
    "source": [
     "with get_openai_callback() as cb:\n",
-    "    for chunk in llm.stream(\"Tell me a joke\", stream_options={\"include_usage\": True}):\n",
+    "    for chunk in llm.stream(\"Tell me a joke\"):\n",
     "        pass\n",
-    "    print(cb.total_tokens)"
+    "    print(cb)"
    ]
   },
   {
@@ -457,21 +453,7 @@
     ")\n",
     "tools = load_tools([\"wikipedia\"])\n",
     "agent = create_tool_calling_agent(llm, tools, prompt)\n",
-    "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",
-    "```"
+    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
    ]
   },
   {
@@ -503,36 +485,30 @@
       "\n",
       "\n",
       "\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",
+      "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",
       "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 is the peregrine falcon (Falco peregrinus), which can exceed speeds of 320 km/h (200 mph) in its dives.\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 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",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n",
-      "Total Tokens: 1787\n",
-      "Prompt Tokens: 1687\n",
-      "Completion Tokens: 100\n",
-      "Total Cost (USD): $0.0009935\n"
+      "Total Tokens: 1675\n",
+      "Prompt Tokens: 1538\n",
+      "Completion Tokens: 137\n",
+      "Total Cost (USD): $0.0009745000000000001\n"
      ]
     }
    ],

docs/docs/how_to/chatbots_memory.ipynb

@@ -71,13 +71,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "chat = ChatOpenAI(model=\"gpt-3.5-turbo-1106\")"
+    "chat = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")"
    ]
   },
   {
@@ -95,19 +95,15 @@
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='I said \"J\\'adore la programmation,\" which means \"I love programming\" in French.')"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "I said \"J'adore la programmation,\" which means \"I love programming\" in French.\n"
+     ]
     }
    ],
    "source": [
-    "from langchain_core.messages import AIMessage, HumanMessage\n",
-    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
@@ -115,23 +111,25 @@
     "            \"system\",\n",
     "            \"You are a helpful assistant. Answer all questions to the best of your ability.\",\n",
     "        ),\n",
-    "        MessagesPlaceholder(variable_name=\"messages\"),\n",
+    "        (\"placeholder\", \"{messages}\"),\n",
     "    ]\n",
     ")\n",
     "\n",
     "chain = prompt | chat\n",
     "\n",
-    "chain.invoke(\n",
+    "ai_msg = chain.invoke(\n",
     "    {\n",
     "        \"messages\": [\n",
-    "            HumanMessage(\n",
-    "                content=\"Translate this sentence from English to French: I love programming.\"\n",
+    "            (\n",
+    "                \"human\",\n",
+    "                \"Translate this sentence from English to French: I love programming.\",\n",
     "            ),\n",
-    "            AIMessage(content=\"J'adore la programmation.\"),\n",
-    "            HumanMessage(content=\"What did you just say?\"),\n",
+    "            (\"ai\", \"J'adore la programmation.\"),\n",
+    "            (\"human\", \"What did you just say?\"),\n",
     "        ],\n",
     "    }\n",
-    ")"
+    ")\n",
+    "print(ai_msg.content)"
    ]
   },
   {
@@ -193,7 +191,7 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='You asked me to translate the sentence \"I love programming\" from English to French.')"
+       "AIMessage(content='You just asked me to translate the sentence \"I love programming\" from English to French.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 61, 'total_tokens': 79}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5cbb21c2-9c30-4031-8ea8-bfc497989535-0', usage_metadata={'input_tokens': 61, 'output_tokens': 18, 'total_tokens': 79})"
       ]
      },
      "execution_count": 5,
@@ -250,7 +248,7 @@
     "            \"system\",\n",
     "            \"You are a helpful assistant. Answer all questions to the best of your ability.\",\n",
     "        ),\n",
-    "        MessagesPlaceholder(variable_name=\"chat_history\"),\n",
+    "        (\"placeholder\", \"{chat_history}\"),\n",
     "        (\"human\", \"{input}\"),\n",
     "    ]\n",
     ")\n",
@@ -304,10 +302,17 @@
    "execution_count": 8,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Parent run dc4e2f79-4bcd-4a36-9506-55ace9040588 not found for run 34b5773e-3ced-46a6-8daf-4d464c15c940. Treating as a root run.\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='The translation of \"I love programming\" in French is \"J\\'adore la programmation.\"')"
+       "AIMessage(content='\"J\\'adore la programmation.\"', response_metadata={'token_usage': {'completion_tokens': 9, 'prompt_tokens': 39, 'total_tokens': 48}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-648b0822-b0bb-47a2-8e7d-7d34744be8f2-0', usage_metadata={'input_tokens': 39, 'output_tokens': 9, 'total_tokens': 48})"
       ]
      },
      "execution_count": 8,
@@ -327,10 +332,17 @@
    "execution_count": 9,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Parent run cc14b9d8-c59e-40db-a523-d6ab3fc2fa4f not found for run 5b75e25c-131e-46ee-9982-68569db04330. Treating as a root run.\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='You just asked me to translate the sentence \"I love programming\" from English to French.')"
+       "AIMessage(content='You asked me to translate the sentence \"I love programming\" from English to French.', response_metadata={'token_usage': {'completion_tokens': 17, 'prompt_tokens': 63, 'total_tokens': 80}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5950435c-1dc2-43a6-836f-f989fd62c95e-0', usage_metadata={'input_tokens': 63, 'output_tokens': 17, 'total_tokens': 80})"
       ]
      },
      "execution_count": 9,
@@ -354,12 +366,12 @@
     "\n",
     "### Trimming messages\n",
     "\n",
-    "LLMs and chat models have limited context windows, and even if you're not directly hitting limits, you may want to limit the amount of distraction the model has to deal with. One solution is to only load and store the most recent `n` messages. Let's use an example history with some preloaded messages:"
+    "LLMs and chat models have limited context windows, and even if you're not directly hitting limits, you may want to limit the amount of distraction the model has to deal with. One solution is trim the historic messages before passing them to the model. Let's use an example history with some preloaded messages:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -371,7 +383,7 @@
        " AIMessage(content='Fine thanks!')]"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -396,34 +408,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Parent run 7ff2d8ec-65e2-4f67-8961-e498e2c4a591 not found for run 3881e990-6596-4326-84f6-2b76949e0657. Treating as a root run.\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Your name is Nemo.')"
+       "AIMessage(content='Your name is Nemo.', response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 66, 'total_tokens': 72}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-f8aabef8-631a-4238-a39b-701e881fbe47-0', usage_metadata={'input_tokens': 66, 'output_tokens': 6, 'total_tokens': 72})"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"You are a helpful assistant. Answer all questions to the best of your ability.\",\n",
-    "        ),\n",
-    "        MessagesPlaceholder(variable_name=\"chat_history\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "chain = prompt | chat\n",
-    "\n",
     "chain_with_message_history = RunnableWithMessageHistory(\n",
     "    chain,\n",
     "    lambda session_id: demo_ephemeral_chat_history,\n",
@@ -443,34 +449,33 @@
    "source": [
     "We can see the chain remembers the preloaded name.\n",
     "\n",
-    "But let's say we have a very small context window, and we want to trim the number of messages passed to the chain to only the 2 most recent ones. We can use the `clear` method to remove messages and re-add them to the history. We don't have to, but let's put this method at the front of our chain to ensure it's always called:"
+    "But let's say we have a very small context window, and we want to trim the number of messages passed to the chain to only the 2 most recent ones. We can use the built in [trim_messages](/docs/how_to/trim_messages/) util to trim messages based on their token count before they reach our prompt. In this case we'll count each message as 1 \"token\" and keep only the last two messages:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
+    "from operator import itemgetter\n",
+    "\n",
+    "from langchain_core.messages import trim_messages\n",
     "from langchain_core.runnables import RunnablePassthrough\n",
     "\n",
-    "\n",
-    "def trim_messages(chain_input):\n",
-    "    stored_messages = demo_ephemeral_chat_history.messages\n",
-    "    if len(stored_messages) <= 2:\n",
-    "        return False\n",
-    "\n",
-    "    demo_ephemeral_chat_history.clear()\n",
-    "\n",
-    "    for message in stored_messages[-2:]:\n",
-    "        demo_ephemeral_chat_history.add_message(message)\n",
-    "\n",
-    "    return True\n",
-    "\n",
+    "trimmer = trim_messages(strategy=\"last\", max_tokens=2, token_counter=len)\n",
     "\n",
     "chain_with_trimming = (\n",
-    "    RunnablePassthrough.assign(messages_trimmed=trim_messages)\n",
-    "    | chain_with_message_history\n",
+    "    RunnablePassthrough.assign(chat_history=itemgetter(\"chat_history\") | trimmer)\n",
+    "    | prompt\n",
+    "    | chat\n",
+    ")\n",
+    "\n",
+    "chain_with_trimmed_history = RunnableWithMessageHistory(\n",
+    "    chain_with_trimming,\n",
+    "    lambda session_id: demo_ephemeral_chat_history,\n",
+    "    input_messages_key=\"input\",\n",
+    "    history_messages_key=\"chat_history\",\n",
     ")"
    ]
   },
@@ -483,22 +488,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Parent run 775cde65-8d22-4c44-80bb-f0b9811c32ca not found for run 5cf71d0e-4663-41cd-8dbe-e9752689cfac. Treating as a root run.\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"P. Sherman's address is 42 Wallaby Way, Sydney.\")"
+       "AIMessage(content='P. Sherman is a fictional character from the animated movie \"Finding Nemo\" who lives at 42 Wallaby Way, Sydney.', response_metadata={'token_usage': {'completion_tokens': 27, 'prompt_tokens': 53, 'total_tokens': 80}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5642ef3a-fdbe-43cf-a575-d1785976a1b9-0', usage_metadata={'input_tokens': 53, 'output_tokens': 27, 'total_tokens': 80})"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chain_with_trimming.invoke(\n",
+    "chain_with_trimmed_history.invoke(\n",
     "    {\"input\": \"Where does P. Sherman live?\"},\n",
     "    {\"configurable\": {\"session_id\": \"unused\"}},\n",
     ")"
@@ -506,19 +518,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[HumanMessage(content=\"What's my name?\"),\n",
-       " AIMessage(content='Your name is Nemo.'),\n",
+       "[HumanMessage(content=\"Hey there! I'm Nemo.\"),\n",
+       " AIMessage(content='Hello!'),\n",
+       " HumanMessage(content='How are you today?'),\n",
+       " AIMessage(content='Fine thanks!'),\n",
+       " HumanMessage(content=\"What's my name?\"),\n",
+       " AIMessage(content='Your name is Nemo.', response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 66, 'total_tokens': 72}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-f8aabef8-631a-4238-a39b-701e881fbe47-0', usage_metadata={'input_tokens': 66, 'output_tokens': 6, 'total_tokens': 72}),\n",
        " HumanMessage(content='Where does P. Sherman live?'),\n",
-       " AIMessage(content=\"P. Sherman's address is 42 Wallaby Way, Sydney.\")]"
+       " AIMessage(content='P. Sherman is a fictional character from the animated movie \"Finding Nemo\" who lives at 42 Wallaby Way, Sydney.', response_metadata={'token_usage': {'completion_tokens': 27, 'prompt_tokens': 53, 'total_tokens': 80}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5642ef3a-fdbe-43cf-a575-d1785976a1b9-0', usage_metadata={'input_tokens': 53, 'output_tokens': 27, 'total_tokens': 80})]"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 25,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -536,48 +552,39 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Parent run fde7123f-6fd3-421a-a3fc-2fb37dead119 not found for run 061a4563-2394-470d-a3ed-9bf1388ca431. Treating as a root run.\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"I'm sorry, I don't have access to your personal information.\")"
+       "AIMessage(content=\"I'm sorry, but I don't have access to your personal information, so I don't know your name. How else may I assist you today?\", response_metadata={'token_usage': {'completion_tokens': 31, 'prompt_tokens': 74, 'total_tokens': 105}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-0ab03495-1f7c-4151-9070-56d2d1c565ff-0', usage_metadata={'input_tokens': 74, 'output_tokens': 31, 'total_tokens': 105})"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chain_with_trimming.invoke(\n",
+    "chain_with_trimmed_history.invoke(\n",
     "    {\"input\": \"What is my name?\"},\n",
     "    {\"configurable\": {\"session_id\": \"unused\"}},\n",
     ")"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 16,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[HumanMessage(content='Where does P. Sherman live?'),\n",
-       " AIMessage(content=\"P. Sherman's address is 42 Wallaby Way, Sydney.\"),\n",
-       " HumanMessage(content='What is my name?'),\n",
-       " AIMessage(content=\"I'm sorry, I don't have access to your personal information.\")]"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
    "source": [
-    "demo_ephemeral_chat_history.messages"
+    "Check out our [how to guide on trimming messages](/docs/how_to/trim_messages/) for more."
    ]
   },
   {
@@ -638,7 +645,7 @@
     "            \"system\",\n",
     "            \"You are a helpful assistant. Answer all questions to the best of your ability. The provided chat history includes facts about the user you are speaking with.\",\n",
     "        ),\n",
-    "        MessagesPlaceholder(variable_name=\"chat_history\"),\n",
+    "        (\"placeholder\", \"{chat_history}\"),\n",
     "        (\"user\", \"{input}\"),\n",
     "    ]\n",
     ")\n",
@@ -672,7 +679,7 @@
     "        return False\n",
     "    summarization_prompt = ChatPromptTemplate.from_messages(\n",
     "        [\n",
-    "            MessagesPlaceholder(variable_name=\"chat_history\"),\n",
+    "            (\"placeholder\", \"{chat_history}\"),\n",
     "            (\n",
     "                \"user\",\n",
     "                \"Distill the above chat messages into a single summary message. Include as many specific details as you can.\",\n",
@@ -772,9 +779,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/docs/how_to/code_splitter.ipynb

@@ -54,7 +54,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9e4144de-d925-4d4c-91c3-685ef8baa57c",
+   "id": "2bb9c73f-9d00-4a19-a81f-cab2f0fd921a",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -63,7 +63,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "a9e37aa1",
    "metadata": {},
    "outputs": [],
@@ -300,7 +300,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 2,
    "id": "ac9295d3",
    "metadata": {},
    "outputs": [],
@@ -312,10 +312,8 @@
     "\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",
     "\"\"\""
@@ -323,7 +321,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 3,
    "id": "3a0cb17a",
    "metadata": {},
    "outputs": [
@@ -332,15 +330,14 @@
       "text/plain": [
        "[Document(page_content='# 🦜️🔗 LangChain'),\n",
        " Document(page_content='⚡ Building applications with LLMs through composability ⚡'),\n",
-       " Document(page_content='## Quick Install\\n\\n```bash'),\n",
+       " Document(page_content='## Quick Install'),\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": 9,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -721,8 +718,44 @@
     "php_splitter = RecursiveCharacterTextSplitter.from_language(\n",
     "    language=Language.PHP, chunk_size=50, chunk_overlap=0\n",
     ")\n",
-    "haskell_docs = php_splitter.create_documents([PHP_CODE])\n",
-    "haskell_docs"
+    "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"
    ]
   }
  ],

docs/docs/how_to/configure.ipynb

@@ -48,20 +48,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "40ed76a2",
    "metadata": {},
-   "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"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "%pip install --upgrade --quiet langchain langchain-openai\n",
     "\n",
@@ -419,7 +409,7 @@
     "    # When configuring the end runnable, we can then use this id to configure this field\n",
     "    ConfigurableField(id=\"prompt\"),\n",
     "    # This sets a default_key.\n",
-    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
+    "    # If we specify this key, the default prompt (asking for a joke, as initialized above) will be used\n",
     "    default_key=\"joke\",\n",
     "    # This adds a new option, with name `poem`\n",
     "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",
@@ -504,7 +494,7 @@
     "    # When configuring the end runnable, we can then use this id to configure this field\n",
     "    ConfigurableField(id=\"prompt\"),\n",
     "    # This sets a default_key.\n",
-    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
+    "    # If we specify this key, the default prompt (asking for a joke, as initialized above) will be used\n",
     "    default_key=\"joke\",\n",
     "    # This adds a new option, with name `poem`\n",
     "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",

docs/docs/how_to/contextual_compression.ipynb

@@ -220,6 +220,57 @@
     "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",
@@ -295,7 +346,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "617a1756",
    "metadata": {},
    "outputs": [],

docs/docs/how_to/convert_runnable_to_tool.ipynb

@@ -0,0 +1,549 @@
+{
+ "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` characetrs of the last message in the prompt!\n",
+    "Let's implement a chat model that echoes back the first `n` characters 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 custom tools\n",
+    "# How to create 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",
@@ -16,13 +16,15 @@
     "| 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 provides 3 ways to create tools:\n",
+    "LangChain supports the creation of tools from:\n",
     "\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",
+    "1. Functions;\n",
+    "2. LangChain [Runnables](/docs/concepts#runnable-interface);\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",
-    "The `@tool` or the `StructuredTool.from_function` class method should be sufficient for most use cases.\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",
     "\n",
     ":::{.callout-tip}\n",
     "\n",
@@ -35,7 +37,9 @@
    "id": "c7326b23",
    "metadata": {},
    "source": [
-    "## @tool decorator\n",
+    "## Creating tools from functions\n",
+    "\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. "
    ]
@@ -51,7 +55,7 @@
      "output_type": "stream",
      "text": [
       "multiply\n",
-      "multiply(a: int, b: int) -> int - Multiply two numbers.\n",
+      "Multiply two numbers.\n",
       "{'a': {'title': 'A', 'type': 'integer'}, 'b': {'title': 'B', 'type': 'integer'}}\n"
      ]
     }
@@ -96,6 +100,57 @@
     "    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",
@@ -106,7 +161,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "9216d03a-f6ea-4216-b7e1-0661823a4c0b",
    "metadata": {},
    "outputs": [
@@ -115,7 +170,7 @@
      "output_type": "stream",
      "text": [
       "multiplication-tool\n",
-      "multiplication-tool(a: int, b: int) -> int - Multiply two numbers.\n",
+      "Multiply two numbers.\n",
       "{'a': {'title': 'A', 'description': 'first number', 'type': 'integer'}, 'b': {'title': 'B', 'description': 'second number', 'type': 'integer'}}\n",
       "True\n"
      ]
@@ -145,17 +200,82 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b63fcc3b",
+   "id": "33a9e94d-0b60-48f3-a4c2-247dce096e66",
    "metadata": {},
    "source": [
-    "## StructuredTool\n",
-    "\n",
-    "The `StrurcturedTool.from_function` class method provides a bit more configurability than the `@tool` decorator, without requiring much additional code."
+    "#### 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": 4,
+   "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",
+    "\n",
+    "The `StructuredTool.from_function` class method provides a bit more configurability than the `@tool` decorator, without requiring much additional code."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
    "id": "564fbe6f-11df-402d-b135-ef6ff25e1e63",
    "metadata": {},
    "outputs": [
@@ -198,7 +318,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "id": "6bc055d4-1fbe-4db5-8881-9c382eba6b1b",
    "metadata": {},
    "outputs": [
@@ -208,7 +328,7 @@
      "text": [
       "6\n",
       "Calculator\n",
-      "Calculator(a: int, b: int) -> int - multiply numbers\n",
+      "multiply numbers\n",
       "{'a': {'title': 'A', 'description': 'first number', 'type': 'integer'}, 'b': {'title': 'B', 'description': 'second number', 'type': 'integer'}}\n"
      ]
     }
@@ -239,6 +359,63 @@
     "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",
@@ -251,7 +428,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 10,
    "id": "1dad8f8e",
    "metadata": {},
    "outputs": [],
@@ -300,7 +477,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 11,
    "id": "bb551c33",
    "metadata": {},
    "outputs": [
@@ -351,7 +528,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 12,
    "id": "6615cb77-fd4c-4676-8965-f92cc71d4944",
    "metadata": {},
    "outputs": [
@@ -383,7 +560,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 13,
    "id": "bb2af583-eadd-41f4-a645-bf8748bd3dcd",
    "metadata": {},
    "outputs": [
@@ -428,7 +605,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 14,
    "id": "4ad0932c-8610-4278-8c57-f9218f654c8a",
    "metadata": {},
    "outputs": [
@@ -473,7 +650,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 15,
    "id": "7094c0e8-6192-4870-a942-aad5b5ae48fd",
    "metadata": {},
    "outputs": [],
@@ -496,7 +673,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 16,
    "id": "b4d22022-b105-4ccc-a15b-412cb9ea3097",
    "metadata": {},
    "outputs": [
@@ -506,7 +683,7 @@
        "'Error: There is no city by the name of foobar.'"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -530,7 +707,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 17,
    "id": "3fad1728-d367-4e1b-9b54-3172981271cf",
    "metadata": {},
    "outputs": [
@@ -540,7 +717,7 @@
        "\"There is no such city, but it's probably above 0K there!\""
       ]
      },
-     "execution_count": 13,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -564,7 +741,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 18,
    "id": "ebfe7c1f-318d-4e58-99e1-f31e69473c46",
    "metadata": {},
    "outputs": [
@@ -574,7 +751,7 @@
        "'The following errors occurred during tool execution: `Error: There is no city by the name of foobar.`'"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -591,13 +768,189 @@
     "\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": "Python 3 (ipykernel)",
+   "display_name": "poetry-venv-311",
    "language": "python",
-   "name": "python3"
+   "name": "poetry-venv-311"
   },
   "language_info": {
    "codemirror_mode": {
@@ -609,7 +962,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.9"
   },
   "vscode": {
    "interpreter": {

docs/docs/how_to/document_loader_html.ipynb

@@ -23,12 +23,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install \"unstructured[html]\""
+    "%pip install unstructured"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "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": 2,
+   "execution_count": 4,
    "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": "3.10.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/document_loader_markdown.ipynb

@@ -21,12 +21,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": null,
    "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": 1,
+   "execution_count": 4,
    "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": 2,
+   "execution_count": 5,
    "id": "a986bbce-7fd3-41d1-bc47-49f9f57c7cd1",
    "metadata": {},
    "outputs": [
@@ -92,11 +92,11 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Number of documents: 65\n",
+      "Number of documents: 66\n",
       "\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",
+      "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",
       "\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",
+      "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",
       "\n"
      ]
     }
@@ -121,7 +121,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "id": "75abc139-3ded-4e8e-9f21-d0c8ec40fdfc",
    "metadata": {},
    "outputs": [
@@ -129,13 +129,21 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'Title', 'NarrativeText', 'ListItem'}\n"
+      "{'ListItem', 'NarrativeText', 'Title'}\n"
      ]
     }
    ],
    "source": [
     "print(set(document.metadata[\"category\"] for document in data))"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "223b4c11",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -154,7 +162,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/dynamic_chain.ipynb

@@ -58,6 +58,8 @@
     }
    ],
    "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",
@@ -86,7 +88,7 @@
     "        # NOTE: This is returning another Runnable, not an actual output.\n",
     "        return contextualize_question\n",
     "    else:\n",
-    "        return RunnablePassthrough()\n",
+    "        return RunnablePassthrough() | itemgetter(\"question\")\n",
     "\n",
     "\n",
     "@chain\n",

docs/docs/how_to/embed_text.mdx

@@ -67,15 +67,16 @@ 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="...")
+embeddings_model = CohereEmbeddings(cohere_api_key="...", model='embed-english-v3.0')
 ```
 
-Otherwise you can initialize without any params:
+Otherwise you can initialize simply as shown below:
 ```python
 from langchain_cohere import CohereEmbeddings
 
-embeddings_model = CohereEmbeddings()
+embeddings_model = CohereEmbeddings(model='embed-english-v3.0')
 ```
+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/extraction_examples.ipynb

@@ -246,11 +246,11 @@
     "examples = [\n",
     "    (\n",
     "        \"The ocean is vast and blue. It's more than 20,000 feet deep. There are many fish in it.\",\n",
-    "        Person(name=None, height_in_meters=None, hair_color=None),\n",
+    "        Data(people=[]),\n",
     "    ),\n",
     "    (\n",
     "        \"Fiona traveled far from France to Spain.\",\n",
-    "        Person(name=\"Fiona\", height_in_meters=None, hair_color=None),\n",
+    "        Data(people=[Person(name=\"Fiona\", height_in_meters=None, hair_color=None)]),\n",
     "    ),\n",
     "]\n",
     "\n",

docs/docs/how_to/few_shot_examples.ipynb

@@ -23,7 +23,7 @@
     "- [Prompt templates](/docs/concepts/#prompt-templates)\n",
     "- [Example selectors](/docs/concepts/#example-selectors)\n",
     "- [LLMs](/docs/concepts/#llms)\n",
-    "- [Vectorstores](/docs/concepts/#vectorstores)\n",
+    "- [Vectorstores](/docs/concepts/#vector-stores)\n",
     "\n",
     ":::\n",
     "\n",

docs/docs/how_to/few_shot_examples_chat.ipynb

@@ -23,7 +23,7 @@
     "- [Prompt templates](/docs/concepts/#prompt-templates)\n",
     "- [Example selectors](/docs/concepts/#example-selectors)\n",
     "- [Chat models](/docs/concepts/#chat-model)\n",
-    "- [Vectorstores](/docs/concepts/#vectorstores)\n",
+    "- [Vectorstores](/docs/concepts/#vector-stores)\n",
     "\n",
     ":::\n",
     "\n",
@@ -51,7 +51,7 @@
     "- `examples`: A list of dictionary examples to include in the final prompt.\n",
     "- `example_prompt`: converts each example into 1 or more messages through its [`format_messages`](https://api.python.langchain.com/en/latest/prompts/langchain_core.prompts.chat.ChatPromptTemplate.html?highlight=format_messages#langchain_core.prompts.chat.ChatPromptTemplate.format_messages) method. A common example would be to convert each example into one human message and one AI message response, or a human message followed by a function call message.\n",
     "\n",
-    "Below is a simple demonstration. First, define the examples you'd like to include:"
+    "Below is a simple demonstration. First, define the examples you'd like to include. Let's give the LLM an unfamiliar mathematical operator, denoted by the \"🦜\" emoji:"
    ]
   },
   {
@@ -59,17 +59,7 @@
    "execution_count": 1,
    "id": "5b79e400",
    "metadata": {},
-   "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"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "%pip install -qU langchain langchain-openai langchain-chroma\n",
     "\n",
@@ -79,9 +69,50 @@
     "os.environ[\"OPENAI_API_KEY\"] = getpass()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "30856d92",
+   "metadata": {},
+   "source": [
+    "If we try to ask the model what the result of this expression is, it will fail:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
+   "id": "174dec5b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The expression \"2 🦜 9\" is not a standard mathematical operation or equation. It appears to be a combination of the number 2 and the parrot emoji 🦜 followed by the number 9. It does not have a specific mathematical meaning.', response_metadata={'token_usage': {'completion_tokens': 54, 'prompt_tokens': 17, 'total_tokens': 71}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-aad12dda-5c47-4a1e-9949-6fe94e03242a-0', usage_metadata={'input_tokens': 17, 'output_tokens': 54, 'total_tokens': 71})"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0.0)\n",
+    "\n",
+    "model.invoke(\"What is 2 🦜 9?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e6d58385",
+   "metadata": {},
+   "source": [
+    "Now let's see what happens if we give the LLM some examples to work with. We'll define some below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
    "id": "0fc5a02a-6249-4e92-95c3-30fff9671e8b",
    "metadata": {
     "tags": []
@@ -91,8 +122,8 @@
     "from langchain_core.prompts import ChatPromptTemplate, FewShotChatMessagePromptTemplate\n",
     "\n",
     "examples = [\n",
-    "    {\"input\": \"2+2\", \"output\": \"4\"},\n",
-    "    {\"input\": \"2+3\", \"output\": \"5\"},\n",
+    "    {\"input\": \"2 🦜 2\", \"output\": \"4\"},\n",
+    "    {\"input\": \"2 🦜 3\", \"output\": \"5\"},\n",
     "]"
    ]
   },
@@ -106,7 +137,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "id": "65e72ad1-9060-47d0-91a1-bc130c8b98ac",
    "metadata": {
     "tags": []
@@ -116,7 +147,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[HumanMessage(content='2+2'), AIMessage(content='4'), HumanMessage(content='2+3'), AIMessage(content='5')]\n"
+      "[HumanMessage(content='2 🦜 2'), AIMessage(content='4'), HumanMessage(content='2 🦜 3'), AIMessage(content='5')]\n"
      ]
     }
    ],
@@ -146,7 +177,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "id": "9f86d6d9-50de-41b6-b6c7-0f9980cc0187",
    "metadata": {
     "tags": []
@@ -162,9 +193,17 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "dd8029c5",
+   "metadata": {},
+   "source": [
+    "And now let's ask the model the initial question and see how it does:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
    "id": "97d443b1-6fae-4b36-bede-3ff7306288a3",
    "metadata": {
     "tags": []
@@ -173,10 +212,10 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='A triangle does not have a square. The square of a number is the result of multiplying the number by itself.', response_metadata={'token_usage': {'completion_tokens': 23, 'prompt_tokens': 52, 'total_tokens': 75}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-3456c4ef-7b4d-4adb-9e02-8079de82a47a-0')"
+       "AIMessage(content='11', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 60, 'total_tokens': 61}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5ec4e051-262f-408e-ad00-3f2ebeb561c3-0', usage_metadata={'input_tokens': 60, 'output_tokens': 1, 'total_tokens': 61})"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -184,9 +223,9 @@
    "source": [
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "chain = final_prompt | ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0.0)\n",
+    "chain = final_prompt | model\n",
     "\n",
-    "chain.invoke({\"input\": \"What's the square of a triangle?\"})"
+    "chain.invoke({\"input\": \"What is 2 🦜 9?\"})"
    ]
   },
   {
@@ -194,6 +233,8 @@
    "id": "70ab7114-f07f-46be-8874-3705a25aba5f",
    "metadata": {},
    "source": [
+    "And we can see that the model has now inferred that the parrot emoji means addition from the given few-shot examples!\n",
+    "\n",
     "## Dynamic few-shot prompting\n",
     "\n",
     "Sometimes you may want to select only a few examples from your overall set to show based on the input. For this, you can replace the `examples` passed into `FewShotChatMessagePromptTemplate` with an `example_selector`. The other components remain the same as above! Our dynamic few-shot prompt template would look like:\n",
@@ -208,7 +249,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 9,
    "id": "ad66f06a-66fd-4fcc-8166-5d0e3c801e57",
    "metadata": {
     "tags": []
@@ -220,9 +261,9 @@
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "examples = [\n",
-    "    {\"input\": \"2+2\", \"output\": \"4\"},\n",
-    "    {\"input\": \"2+3\", \"output\": \"5\"},\n",
-    "    {\"input\": \"2+4\", \"output\": \"6\"},\n",
+    "    {\"input\": \"2 🦜 2\", \"output\": \"4\"},\n",
+    "    {\"input\": \"2 🦜 3\", \"output\": \"5\"},\n",
+    "    {\"input\": \"2 🦜 4\", \"output\": \"6\"},\n",
     "    {\"input\": \"What did the cow say to the moon?\", \"output\": \"nothing at all\"},\n",
     "    {\n",
     "        \"input\": \"Write me a poem about the moon\",\n",
@@ -247,7 +288,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 10,
    "id": "7790303a-f722-452e-8921-b14bdf20bdff",
    "metadata": {
     "tags": []
@@ -257,10 +298,10 @@
      "data": {
       "text/plain": [
        "[{'input': 'What did the cow say to the moon?', 'output': 'nothing at all'},\n",
-       " {'input': '2+4', 'output': '6'}]"
+       " {'input': '2 🦜 4', 'output': '6'}]"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -287,7 +328,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 11,
    "id": "253c255e-41d7-45f6-9d88-c7a0ced4b1bd",
    "metadata": {
     "tags": []
@@ -297,7 +338,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[HumanMessage(content='2+3'), AIMessage(content='5'), HumanMessage(content='2+2'), AIMessage(content='4')]\n"
+      "[HumanMessage(content='2 🦜 3'), AIMessage(content='5'), HumanMessage(content='2 🦜 4'), AIMessage(content='6')]\n"
      ]
     }
    ],
@@ -317,7 +358,7 @@
     "    ),\n",
     ")\n",
     "\n",
-    "print(few_shot_prompt.invoke(input=\"What's 3+3?\").to_messages())"
+    "print(few_shot_prompt.invoke(input=\"What's 3 🦜 3?\").to_messages())"
    ]
   },
   {
@@ -330,7 +371,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 12,
    "id": "e731cb45-f0ea-422c-be37-42af2a6cb2c4",
    "metadata": {
     "tags": []
@@ -340,7 +381,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "messages=[HumanMessage(content='2+3'), AIMessage(content='5'), HumanMessage(content='2+2'), AIMessage(content='4')]\n"
+      "messages=[HumanMessage(content='2 🦜 3'), AIMessage(content='5'), HumanMessage(content='2 🦜 4'), AIMessage(content='6')]\n"
      ]
     }
    ],
@@ -353,7 +394,7 @@
     "    ]\n",
     ")\n",
     "\n",
-    "print(few_shot_prompt.invoke(input=\"What's 3+3?\"))"
+    "print(few_shot_prompt.invoke(input=\"What's 3 🦜 3?\"))"
    ]
   },
   {
@@ -368,7 +409,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 13,
    "id": "0568cbc6-5354-47f1-ab4d-dfcc616cf583",
    "metadata": {
     "tags": []
@@ -377,10 +418,10 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='6', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 51, 'total_tokens': 52}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-6bcbe158-a8e3-4a85-a754-1ba274a9f147-0')"
+       "AIMessage(content='6', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 60, 'total_tokens': 61}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-d1863e5e-17cd-4e9d-bf7a-b9f118747a65-0', usage_metadata={'input_tokens': 60, 'output_tokens': 1, 'total_tokens': 61})"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -388,7 +429,7 @@
    "source": [
     "chain = final_prompt | ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0.0)\n",
     "\n",
-    "chain.invoke({\"input\": \"What's 3+3?\"})"
+    "chain.invoke({\"input\": \"What's 3 🦜 3?\"})"
    ]
   },
   {
@@ -428,7 +469,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/filter_messages.ipynb

@@ -0,0 +1,203 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e389175d-8a65-4f0d-891c-dbdfabb3c3ef",
+   "metadata": {},
+   "source": [
+    "# How to filter messages\n",
+    "\n",
+    "In more complex chains and agents we might track state with a list of messages. This list can start to accumulate messages from multiple different models, speakers, sub-chains, etc., and we may only want to pass subsets of this full list of messages to each model call in the chain/agent.\n",
+    "\n",
+    "The `filter_messages` utility makes it easy to filter messages by type, id, or name.\n",
+    "\n",
+    "## Basic usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f4ad2fd3-3cab-40d4-a989-972115865b8b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='example input', name='example_user', id='2'),\n",
+       " HumanMessage(content='real input', name='bob', id='4')]"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    "    filter_messages,\n",
+    ")\n",
+    "\n",
+    "messages = [\n",
+    "    SystemMessage(\"you are a good assistant\", id=\"1\"),\n",
+    "    HumanMessage(\"example input\", id=\"2\", name=\"example_user\"),\n",
+    "    AIMessage(\"example output\", id=\"3\", name=\"example_assistant\"),\n",
+    "    HumanMessage(\"real input\", id=\"4\", name=\"bob\"),\n",
+    "    AIMessage(\"real output\", id=\"5\", name=\"alice\"),\n",
+    "]\n",
+    "\n",
+    "filter_messages(messages, include_types=\"human\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7b663a1e-a8ae-453e-a072-8dd75dfab460",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[SystemMessage(content='you are a good assistant', id='1'),\n",
+       " HumanMessage(content='real input', name='bob', id='4'),\n",
+       " AIMessage(content='real output', name='alice', id='5')]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "filter_messages(messages, exclude_names=[\"example_user\", \"example_assistant\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "db170e46-03f8-4710-b967-23c70c3ac054",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='example input', name='example_user', id='2'),\n",
+       " HumanMessage(content='real input', name='bob', id='4'),\n",
+       " AIMessage(content='real output', name='alice', id='5')]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "filter_messages(messages, include_types=[HumanMessage, AIMessage], exclude_ids=[\"3\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b7c4e5ad-d1b4-4c18-b250-864adde8f0dd",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "`filter_messages` can be used in an imperatively (like above) or declaratively, making it easy to compose with other components in a chain:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "675f8f79-db39-401c-a582-1df2478cba30",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=[], response_metadata={'id': 'msg_01Wz7gBHahAwkZ1KCBNtXmwA', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 16, 'output_tokens': 3}}, id='run-b5d8a3fe-004f-4502-a071-a6c025031827-0', usage_metadata={'input_tokens': 16, 'output_tokens': 3, 'total_tokens': 19})"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# pip install -U langchain-anthropic\n",
+    "from langchain_anthropic import ChatAnthropic\n",
+    "\n",
+    "llm = ChatAnthropic(model=\"claude-3-sonnet-20240229\", temperature=0)\n",
+    "# Notice we don't pass in messages. This creates\n",
+    "# a RunnableLambda that takes messages as input\n",
+    "filter_ = filter_messages(exclude_names=[\"example_user\", \"example_assistant\"])\n",
+    "chain = filter_ | llm\n",
+    "chain.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4133ab28-f49c-480f-be92-b51eb6559153",
+   "metadata": {},
+   "source": [
+    "Looking at the LangSmith trace we can see that before the messages are passed to the model they are filtered: https://smith.langchain.com/public/f808a724-e072-438e-9991-657cc9e7e253/r\n",
+    "\n",
+    "Looking at just the filter_, we can see that it's a Runnable object that can be invoked like all Runnables:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "c090116a-1fef-43f6-a178-7265dff9db00",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='real input', name='bob', id='4'),\n",
+       " AIMessage(content='real output', name='alice', id='5')]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "filter_.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ff339066-d424-4042-8cca-cd4b007c1a8e",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For a complete description of all arguments head to the API reference: https://api.python.langchain.com/en/latest/messages/langchain_core.messages.utils.filter_messages.html"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv-2",
+   "language": "python",
+   "name": "poetry-venv-2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/functions.ipynb

@@ -300,7 +300,11 @@
    "id": "922b48bd",
    "metadata": {},
    "source": [
-    "# Streaming\n",
+    "## Streaming\n",
+    "\n",
+    ":::{.callout-note}\n",
+    "[RunnableLambda](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableLambda.html) is best suited for code that does not need to support streaming. If you need to support streaming (i.e., be able to operate on chunks of inputs and yield chunks of outputs), use [RunnableGenerator](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableGenerator.html) instead as in the example below.\n",
+    ":::\n",
     "\n",
     "You can use generator functions (ie. functions that use the `yield` keyword, and behave like iterators) in a chain.\n",
     "\n",

docs/docs/how_to/hybrid.ipynb

@@ -9,11 +9,13 @@
    "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, ...) 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, 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",
     "\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`. 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`.\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",
     "\n",
     "**Step 2: Add that parameter as a configurable field for the chain**\n",
     "\n",

docs/docs/how_to/index.mdx

@@ -14,13 +14,14 @@ For comprehensive descriptions of every class and function see the [API Referenc
 ## Installation
 
 - [How to: install LangChain packages](/docs/how_to/installation/)
+- [How to: use LangChain with different Pydantic versions](/docs/how_to/pydantic_compatibility)
 
 ## Key features
 
 This highlights functionality that is core to using LangChain.
 
 - [How to: return structured data from a model](/docs/how_to/structured_output/)
-- [How to: use a model to call tools](/docs/how_to/tool_calling/)
+- [How to: use a model to call tools](/docs/how_to/tool_calling)
 - [How to: stream runnables](/docs/how_to/streaming)
 - [How to: debug your LLM apps](/docs/how_to/debugging/)
 
@@ -30,6 +31,8 @@ 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/)
@@ -42,6 +45,7 @@ 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
 
@@ -78,7 +82,22 @@ 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: work with local models](/docs/how_to/local_llms)
+- [How to: init any model in one line](/docs/how_to/chat_models_universal_init/)
+
+### Messages
+
+[Messages](/docs/concepts/#messages) are the input and output of chat models. They have some `content` and a `role`, which describes the source of the message.
+
+- [How to: trim messages](/docs/how_to/trim_messages/)
+- [How to: filter messages](/docs/how_to/filter_messages/)
+- [How to: merge consecutive messages of the same type](/docs/how_to/merge_message_runs/)
 
 ### LLMs
 
@@ -88,7 +107,7 @@ What LangChain calls [LLMs](/docs/concepts/#llms) are older forms of language mo
 - [How to: create a custom LLM class](/docs/how_to/custom_llm)
 - [How to: stream a response back](/docs/how_to/streaming_llm)
 - [How to: track token usage](/docs/how_to/llm_token_usage_tracking)
-- [How to: work with local LLMs](/docs/how_to/local_llms)
+- [How to: work with local models](/docs/how_to/local_llms)
 
 ### Output parsers
 
@@ -167,15 +186,23 @@ 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).
+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. 
 
-- [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 a chat model to call tools](/docs/how_to/tool_calling/)
-- [How to: add ad-hoc tool calling capability to LLMs and chat models](/docs/how_to/tools_prompting)
+- [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: pass run time values to tools](/docs/how_to/tool_runtime)
-- [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: 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)
 
 ### Multimodal
 
@@ -187,7 +214,7 @@ 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://github.com/langchain-ai/langgraph) documentation.
+For in depth how-to guides for agents, please check out [LangGraph](https://langchain-ai.github.io/langgraph/) documentation.
 
 :::
 
@@ -203,6 +230,7 @@ For in depth how-to guides for agents, please check out [LangGraph](https://gith
 - [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
 
@@ -215,7 +243,10 @@ 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)
 
 ## Use cases
 
@@ -250,6 +281,7 @@ For a high-level tutorial on building chatbots, check out [this guide](/docs/tut
 - [How to: manage memory](/docs/how_to/chatbots_memory)
 - [How to: do retrieval](/docs/how_to/chatbots_retrieval)
 - [How to: use tools](/docs/how_to/chatbots_tools)
+- [How to: manage large chat history](/docs/how_to/trim_messages/)
 
 ### Query analysis
 
@@ -294,7 +326,26 @@ You can peruse [LangGraph how-to guides here](https://langchain-ai.github.io/lan
 ## [LangSmith](https://docs.smith.langchain.com/)
 
 LangSmith allows you to closely trace, monitor and evaluate your LLM application.
-It seamlessly integrates with LangChain, and you can use it to inspect and debug individual steps of your chains as you build.
+It seamlessly integrates with LangChain and LangGraph, and you can use it to inspect and debug individual steps of your chains and agents as you build.
 
 LangSmith documentation is hosted on a separate site.
-You can peruse [LangSmith how-to guides here](https://docs.smith.langchain.com/how_to_guides/).
+You can peruse [LangSmith how-to guides here](https://docs.smith.langchain.com/how_to_guides/), but we'll highlight a few sections that are particularly
+relevant to LangChain below:
+
+### Evaluation
+<span data-heading-keywords="evaluation,evaluate"></span>
+
+Evaluating performance is a vital part of building LLM-powered applications.
+LangSmith helps with every step of the process from creating a dataset to defining metrics to running evaluators.
+
+To learn more, check out the [LangSmith evaluation how-to guides](https://docs.smith.langchain.com/how_to_guides#evaluation).
+
+### Tracing
+<span data-heading-keywords="trace,tracing"></span>
+
+Tracing gives you observability inside your chains and agents, and is vital in diagnosing issues.
+
+- [How to: trace with LangChain](https://docs.smith.langchain.com/how_to_guides/tracing/trace_with_langchain)
+- [How to: add metadata and tags to traces](https://docs.smith.langchain.com/how_to_guides/tracing/trace_with_langchain#add-metadata-and-tags-to-traces)
+
+You can see general tracing-related how-tos [in this section of the LangSmith docs](https://docs.smith.langchain.com/how_to_guides/tracing).