wip

.devcontainer/README.md

@@ -10,7 +10,7 @@ You can use the dev container configuration in this folder to build and run the
 You may use the button above, or follow these steps to open this repo in a Codespace:
 1. Click the **Code** drop-down menu at the top of https://github.com/langchain-ai/langchain.
 1. Click on the **Codespaces** tab.
-1. Click **Create codespace on master**.
+1. Click **Create codespace on master** .
 
 For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
   

.devcontainer/docker-compose.yaml

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

.github/ISSUE_TEMPLATE/config.yml

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

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

@@ -350,7 +350,11 @@ def get_graphql_pr_edges(*, settings: Settings, after: Union[str, None] = None):
         print("Querying PRs...")
     else:
         print(f"Querying PRs with cursor {after}...")
-    data = get_graphql_response(settings=settings, query=prs_query, after=after)
+    data = get_graphql_response(
+        settings=settings,
+        query=prs_query,
+        after=after
+    )
     graphql_response = PRsResponse.model_validate(data)
     return graphql_response.data.repository.pullRequests.edges
 
@@ -480,16 +484,10 @@ def get_contributors(settings: Settings):
             lines_changed = pr.additions + pr.deletions
             score = _logistic(files_changed, 20) + _logistic(lines_changed, 100)
             contributor_scores[pr.author.login] += score
-            three_months_ago = datetime.now(timezone.utc) - timedelta(days=3 * 30)
+            three_months_ago = (datetime.now(timezone.utc) - timedelta(days=3*30))
             if pr.createdAt > three_months_ago:
                 recent_contributor_scores[pr.author.login] += score
-    return (
-        contributors,
-        contributor_scores,
-        recent_contributor_scores,
-        reviewers,
-        authors,
-    )
+    return contributors, contributor_scores, recent_contributor_scores, reviewers, authors
 
 
 def get_top_users(
@@ -526,13 +524,9 @@ if __name__ == "__main__":
     # question_commentors, question_last_month_commentors, question_authors = get_experts(
     #     settings=settings
     # )
-    (
-        contributors,
-        contributor_scores,
-        recent_contributor_scores,
-        reviewers,
-        pr_authors,
-    ) = get_contributors(settings=settings)
+    contributors, contributor_scores, recent_contributor_scores, reviewers, pr_authors = get_contributors(
+        settings=settings
+    )
     # authors = {**question_authors, **pr_authors}
     authors = {**pr_authors}
     maintainers_logins = {
@@ -553,7 +547,6 @@ if __name__ == "__main__":
         "obi1kenobi",
         "langchain-infra",
         "jacoblee93",
-        "isahers1",
         "dqbd",
         "bracesproul",
         "akira",
@@ -565,7 +558,7 @@ if __name__ == "__main__":
         maintainers.append(
             {
                 "login": login,
-                "count": contributors[login],  # + question_commentors[login],
+                "count": contributors[login], #+ question_commentors[login],
                 "avatarUrl": user.avatarUrl,
                 "twitterUsername": user.twitterUsername,
                 "url": user.url,
@@ -621,7 +614,9 @@ if __name__ == "__main__":
     new_people_content = yaml.dump(
         people, sort_keys=False, width=200, allow_unicode=True
     )
-    if people_old_content == new_people_content:
+    if (
+        people_old_content == new_people_content
+    ):
         logging.info("The LangChain People data hasn't changed, finishing.")
         sys.exit(0)
     people_path.write_text(new_people_content, encoding="utf-8")
@@ -634,7 +629,9 @@ if __name__ == "__main__":
     logging.info(f"Creating a new branch {branch_name}")
     subprocess.run(["git", "checkout", "-B", branch_name], check=True)
     logging.info("Adding updated file")
-    subprocess.run(["git", "add", str(people_path)], check=True)
+    subprocess.run(
+        ["git", "add", str(people_path)], check=True
+    )
     logging.info("Committing updated file")
     message = "👥 Update LangChain people data"
     result = subprocess.run(["git", "commit", "-m", message], check=True)
@@ -643,4 +640,4 @@ if __name__ == "__main__":
     logging.info("Creating PR")
     pr = repo.create_pull(title=message, body=message, base="master", head=branch_name)
     logging.info(f"Created PR: {pr.number}")
-    logging.info("Finished")
+    logging.info("Finished")

.github/scripts/check_diff.py

@@ -1,13 +1,7 @@
-import glob
 import json
-import os
-import re
 import sys
-import tomllib
-from collections import defaultdict
-from typing import Dict, List, Set
-from pathlib import Path
-
+import os
+from typing import Dict
 
 LANGCHAIN_DIRS = [
     "libs/core",
@@ -17,121 +11,6 @@ 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]]:
-    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:]
 
@@ -142,11 +21,10 @@ 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
-        dirs_to_run["lint"] = all_package_dirs()
-        dirs_to_run["test"] = all_package_dirs()
-        dirs_to_run["extended-test"] = set(LANGCHAIN_DIRS)
+        raise ValueError("Max diff reached. Please manually run CI on changed libs.")
+
     for file in files:
         if any(
             file.startswith(dir_)
@@ -203,25 +81,14 @@ if __name__ == "__main__":
                 docs_edited = True
             dirs_to_run["lint"].add(".")
 
-    dependents = dependents_graph()
-
-    # we now have dirs_by_job
-    # todo: clean this up
-
-    map_job_to_configs = {
-        job: _get_configs_for_multi_dirs(job, dirs_to_run, dependents)
-        for job in [
-            "lint",
-            "test",
-            "extended-tests",
-            "compile-integration-tests",
-            "dependencies",
-        ]
+    outputs = {
+        "dirs-to-lint": 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 "",
     }
-    map_job_to_configs["test-doc-imports"] = (
-        [{"python-version": "3.12"}] if docs_edited else []
-    )
-
-    for key, value in map_job_to_configs.items():
+    for key, value in outputs.items():
         json_output = json.dumps(value)
         print(f"{key}={json_output}")

.github/scripts/check_prerelease_dependencies.py

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

.github/scripts/get_min_versions.py

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

.github/workflows/.codespell-exclude

@@ -1,7 +0,0 @@
-libs/community/langchain_community/llms/yuan2.py
-"NotIn": "not in",
-- `/checkin`: Check-in
-docs/docs/integrations/providers/trulens.mdx
-self.assertIn(
-from trulens_eval import Tru
-tru = Tru()

.github/workflows/_compile_integration_test.yml

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

.github/workflows/_dependencies.yml

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

.github/workflows/_integration_test.yml

@@ -6,28 +6,30 @@ 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
-    name: Python ${{ inputs.python-version }}
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core
@@ -51,15 +53,8 @@ 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

@@ -11,10 +11,6 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -25,15 +21,27 @@ env:
 
 jobs:
   build:
-    name: "make lint #${{ inputs.python-version }}"
+    name: "make lint #${{ matrix.python-version }}"
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        # Only lint on the min and max supported Python versions.
+        # It's extremely unlikely that there's a lint issue on any version in between
+        # that doesn't show up on the min or max versions.
+        #
+        # GitHub rate-limits how many jobs can be running at any one time.
+        # Starting new jobs is also relatively slow,
+        # so linting on fewer versions makes CI faster.
+        python-version:
+          - "3.8"
+          - "3.11"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: lint-with-extras
@@ -78,7 +86,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache
-          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
 
       - name: Analysing the code with our lint
@@ -112,7 +120,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache_test
-          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
       - name: Analysing the code with our lint
         working-directory: ${{ inputs.working-directory }}

.github/workflows/_release.yml

@@ -72,69 +72,12 @@ jobs:
         run: |
           echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
           echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
-  release-notes:
-    needs:
-      - build
-    runs-on: ubuntu-latest
-    outputs:
-      release-body: ${{ steps.generate-release-body.outputs.release-body }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain
-          path: langchain
-          sparse-checkout: | # this only grabs files for relevant dir
-            ${{ inputs.working-directory }}
-          ref: master # this scopes to just master branch
-          fetch-depth: 0 # this fetches entire commit history
-      - name: Check Tags
-        id: check-tags
-        shell: bash
-        working-directory: langchain/${{ inputs.working-directory }}
-        env:
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          VERSION: ${{ needs.build.outputs.version }}
-        run: |
-          REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
-          echo $REGEX
-          PREV_TAG=$(git tag --sort=-creatordate | grep -P $REGEX || true | head -1)
-          TAG="${PKG_NAME}==${VERSION}"
-          if [ "$TAG" == "$PREV_TAG" ]; then
-            echo "No new version to release"
-            exit 1
-          fi
-          echo tag="$TAG" >> $GITHUB_OUTPUT
-          echo prev-tag="$PREV_TAG" >> $GITHUB_OUTPUT
-      - name: Generate release body
-        id: generate-release-body
-        working-directory: langchain
-        env:
-          WORKING_DIR: ${{ inputs.working-directory }}
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          TAG: ${{ steps.check-tags.outputs.tag }}
-          PREV_TAG: ${{ steps.check-tags.outputs.prev-tag }}
-        run: |
-          PREAMBLE="Changes since $PREV_TAG"
-          # if PREV_TAG is empty, then we are releasing the first version
-          if [ -z "$PREV_TAG" ]; then
-            PREAMBLE="Initial release"
-            PREV_TAG=$(git rev-list --max-parents=0 HEAD)
-          fi
-          {
-            echo 'release-body<<EOF'
-            echo $PREAMBLE
-            echo
-            git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR
-            echo EOF
-          } >> "$GITHUB_OUTPUT"
 
   test-pypi-publish:
     needs:
       - build
-      - release-notes
     uses:
       ./.github/workflows/_test_release.yml
-    permissions: write-all
     with:
       working-directory: ${{ inputs.working-directory }}
       dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
@@ -143,7 +86,6 @@ jobs:
   pre-release-checks:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
     runs-on: ubuntu-latest
     steps:
@@ -189,7 +131,7 @@ jobs:
             --extra-index-url https://test.pypi.org/simple/ \
             "$PKG_NAME==$VERSION" || \
           ( \
-            sleep 15 && \
+            sleep 5 && \
             poetry run pip install \
               --extra-index-url https://test.pypi.org/simple/ \
               "$PKG_NAME==$VERSION" \
@@ -202,7 +144,7 @@ jobs:
           poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: poetry install --with test
+        run: poetry install --with test,test_integration
         working-directory: ${{ inputs.working-directory }}
 
       # Overwrite the local version of the package with the test PyPI version.
@@ -221,17 +163,12 @@ jobs:
         run: make tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: Check for prerelease versions
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          poetry run python $GITHUB_WORKSPACE/.github/scripts/check_prerelease_dependencies.py pyproject.toml
-
       - name: Get minimum versions
         working-directory: ${{ inputs.working-directory }}
         id: min-version
         run: |
           poetry run pip install packaging
-          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release)"
+          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
           echo "min-versions=$min_versions"
 
@@ -250,10 +187,6 @@ 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:
@@ -290,14 +223,12 @@ 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 }}
 
   publish:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
       - pre-release-checks
     runs-on: ubuntu-latest
@@ -339,7 +270,6 @@ jobs:
   mark-release:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
       - pre-release-checks
       - publish
@@ -376,6 +306,6 @@ jobs:
           token: ${{ secrets.GITHUB_TOKEN }}
           generateReleaseNotes: false
           tag: ${{needs.build.outputs.pkg-name}}==${{ needs.build.outputs.version }}
-          body: ${{ needs.release-notes.outputs.release-body }}
+          body: "# Release ${{needs.build.outputs.pkg-name}}==${{ needs.build.outputs.version }}\n\nPackage-specific release note generation coming soon."
           commit: ${{ github.sha }}
           makeLatest: ${{ needs.build.outputs.pkg-name == 'langchain-core'}}

.github/workflows/_test.yml

@@ -11,10 +11,6 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -25,14 +21,21 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: "make test #${{ inputs.python-version }}"
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: "make test #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core
@@ -65,22 +68,3 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
-          
-      - name: Get minimum versions
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
-        run: |
-          poetry run pip install packaging tomli
-          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-# Temporarily disabled until we can get the minimum versions working
-#      - name: Run unit tests with minimum dependency versions
-#        if: ${{ steps.min-version.outputs.min-versions != '' }}
-#        env:
-#          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-#        run: |
-#          poetry run pip install --force-reinstall $MIN_VERSIONS --editable .
-#          make tests
-#        working-directory: ${{ inputs.working-directory }}

.github/workflows/_test_doc_imports.yml

@@ -2,11 +2,6 @@ name: test_doc_imports
 
 on:
   workflow_call:
-    inputs:
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -14,14 +9,18 @@ env:
 jobs:
   build:
     runs-on: ubuntu-latest
-    name: "check doc imports #${{ inputs.python-version }}"
+    strategy:
+      matrix:
+        python-version:
+          - "3.11"
+    name: "check doc imports #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           cache-key: core
 

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

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

.github/workflows/check_diffs.yml

@@ -26,112 +26,104 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.11'
+          python-version: '3.10'
       - 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:
-      lint: ${{ steps.set-matrix.outputs.lint }}
-      test: ${{ steps.set-matrix.outputs.test }}
-      extended-tests: ${{ steps.set-matrix.outputs.extended-tests }}
-      compile-integration-tests: ${{ steps.set-matrix.outputs.compile-integration-tests }}
-      dependencies: ${{ steps.set-matrix.outputs.dependencies }}
-      test-doc-imports: ${{ steps.set-matrix.outputs.test-doc-imports }}
+      dirs-to-lint: ${{ steps.set-matrix.outputs.dirs-to-lint }}
+      dirs-to-test: ${{ steps.set-matrix.outputs.dirs-to-test }}
+      dirs-to-extended-test: ${{ steps.set-matrix.outputs.dirs-to-extended-test }}
+      docs-edited: ${{ steps.set-matrix.outputs.docs-edited }}
   lint:
-    name: cd ${{ matrix.job-configs.working-directory }}
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.lint != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-lint != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.lint) }}
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-lint) }}
     uses: ./.github/workflows/_lint.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
   test:
-    name: cd ${{ matrix.job-configs.working-directory }}
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.test != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test) }}
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
     uses: ./.github/workflows/_test.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
   test-doc-imports:
     needs: [ build ]
-    if: ${{ needs.build.outputs.test-doc-imports != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test-doc-imports) }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' || needs.build.outputs.docs-edited }}
     uses: ./.github/workflows/_test_doc_imports.yml
     secrets: inherit
-    with:
-      python-version: ${{ matrix.job-configs.python-version }}
 
   compile-integration-tests:
-    name: cd ${{ matrix.job-configs.working-directory }}
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.compile-integration-tests) }}
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
     uses: ./.github/workflows/_compile_integration_test.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
   dependencies:
-    name: cd ${{ matrix.job-configs.working-directory }}
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dependencies != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.dependencies) }}
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
     uses: ./.github/workflows/_dependencies.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
   extended-tests:
-    name: "cd ${{ matrix.job-configs.working-directory }} / make extended_tests #${{ matrix.job-configs.python-version }}"
+    name: "cd ${{ matrix.working-directory }} / make extended_tests #${{ matrix.python-version }}"
     needs: [ build ]
-    if: ${{ needs.build.outputs.extended-tests != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-extended-test != '[]' }}
     strategy:
       matrix:
         # note different variable for extended test dirs
-        job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-extended-test) }}
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
     runs-on: ubuntu-latest
     defaults:
       run:
-        working-directory: ${{ matrix.job-configs.working-directory }}
+        working-directory: ${{ matrix.working-directory }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.job-configs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.job-configs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ matrix.job-configs.working-directory }}
+          working-directory: ${{ matrix.working-directory }}
           cache-key: extended
 
       - name: Install dependencies
         shell: bash
         run: |
           echo "Running extended tests, installing dependencies with poetry..."
-          poetry install --with test
-          poetry run pip install uv
-          poetry run uv pip install -r extended_testing_deps.txt
+          poetry install -E extended_testing --with test
 
       - name: Run extended tests
         run: make extended_tests

.github/workflows/check_new_docs.yml

@@ -1,36 +0,0 @@
----
-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/codespell.yml

@@ -29,9 +29,9 @@ jobs:
           python .github/workflows/extract_ignored_words_list.py
         id: extract_ignore_words
 
-#      - name: Codespell
-#        uses: codespell-project/actions-codespell@v2
-#        with:
-#          skip: guide_imports.json,*.ambr,./cookbook/data/imdb_top_1000.csv,*.lock
-#          ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}
-#          exclude_file: ./.github/workflows/codespell-exclude
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2
+        with:
+          skip: guide_imports.json,*.ambr,./cookbook/data/imdb_top_1000.csv,*.lock
+          ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}
+          exclude_file: libs/community/langchain_community/llms/yuan2.py

.github/workflows/people.yml

@@ -16,7 +16,6 @@ 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

@@ -10,8 +10,6 @@ env:
 
 jobs:
   build:
-    if: github.repository_owner == 'langchain-ai'
-    name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
@@ -27,38 +25,16 @@ jobs:
           - "libs/partners/groq"
           - "libs/partners/mistralai"
           - "libs/partners/together"
-          - "libs/partners/google-vertexai"
-          - "libs/partners/google-genai"
-          - "libs/partners/aws"
-
+    name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
     steps:
       - uses: actions/checkout@v4
-        with:
-          path: langchain
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-google
-          path: langchain-google
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-aws
-          path: langchain-aws
-
-      - name: Move libs
-        run: |
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            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-aws/libs/aws langchain/libs/partners/aws
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: "./langchain/.github/actions/poetry_setup"
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: langchain/${{ matrix.working-directory }}
+          working-directory: ${{ matrix.working-directory }}
           cache-key: scheduled
 
       - name: 'Authenticate to Google Cloud'
@@ -67,20 +43,16 @@ jobs:
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
-      - name: Configure AWS Credentials
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ secrets.AWS_REGION }}
-
       - name: Install dependencies
+        working-directory: ${{ matrix.working-directory }}
+        shell: bash
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
-          cd langchain/${{ matrix.working-directory }}
           poetry install --with=test_integration,test
 
       - name: Run integration tests
+        working-directory: ${{ matrix.working-directory }}
+        shell: bash
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
@@ -95,24 +67,12 @@ jobs:
           GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
-          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
         run: |
-          cd langchain/${{ matrix.working-directory }}
-          make integration_tests
-
-      - name: Remove external libraries
-        run: | 
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/aws
+          make integration_test
 
       - name: Ensure the tests did not create any additional files
-        working-directory: langchain
+        working-directory: ${{ matrix.working-directory }}
+        shell: bash
         run: |
           set -eu
 

.gitignore

@@ -133,7 +133,6 @@ env.bak/
 
 # mypy
 .mypy_cache/
-.mypy_cache_test/
 .dmypy.json
 dmypy.json
 

Makefile

@@ -32,13 +32,10 @@ api_docs_build:
 	poetry run python docs/api_reference/create_api_rst.py
 	cd docs/api_reference && poetry run make html
 
-API_PKG ?= text-splitters
-
 api_docs_quick_preview:
-	poetry run pip install "pydantic<2"
-	poetry run python docs/api_reference/create_api_rst.py $(API_PKG)
+	poetry run python docs/api_reference/create_api_rst.py text-splitters
 	cd docs/api_reference && poetry run make html
-	open docs/api_reference/_build/html/$(shell echo $(API_PKG) | sed 's/-/_/g')_api_reference.html
+	open docs/api_reference/_build/html/text_splitters_api_reference.html
 
 ## api_docs_clean: Clean the API Reference documentation build artifacts.
 api_docs_clean:

README.md

@@ -2,16 +2,17 @@
 
 ⚡ Build context-aware reasoning applications ⚡
 
-[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/releases)
+[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/releases)
 [![CI](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml)
-[![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)
+[![Downloads](https://static.pepy.tech/badge/langchain-core/month)](https://pepy.tech/project/langchain-core)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
+[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
+[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](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)
+[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=social)](https://star-history.com/#langchain-ai/langchain)
+[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain)](https://libraries.io/github/langchain-ai/langchain)
+[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/issues)
 
 Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
@@ -37,44 +38,43 @@ conda install langchain -c conda-forge
 
 For these applications, LangChain simplifies the entire application lifecycle:
 
-- **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 your LangGraph applications into production-ready APIs and Assistants with [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/).
+- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/docs/expression_language/) and [components](https://python.langchain.com/docs/modules/). Integrate with hundreds of [third-party providers](https://python.langchain.com/docs/integrations/platforms/).
+- **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://python.langchain.com/docs/langsmith/) so that you can constantly optimize and deploy with confidence.
+- **Deployment**: Turn any chain into a REST API with [LangServe](https://python.langchain.com/docs/langserve).
 
 ### 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. Integrates smoothly with LangChain, but can be used without it.
+- **[`LangGraph`](https://python.langchain.com/docs/langgraph)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
 
 ### 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.
+- **[LangSmith](https://python.langchain.com/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
 
 ### Deployment:
-- **[LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/)**: Turn your LangGraph applications into production-ready APIs and Assistants.
+- **[LangServe](https://python.langchain.com/docs/langserve)**: A library for deploying LangChain chains as REST APIs.
 
-![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")
+![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")
 
 ## 🧱 What can you build with LangChain?
 
 **❓ Question answering with RAG**
 
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/rag/)
+- [Documentation](https://python.langchain.com/docs/use_cases/question_answering/)
 - End-to-end Example: [Chat LangChain](https://chat.langchain.com) and [repo](https://github.com/langchain-ai/chat-langchain)
 
 **🧱 Extracting structured output**
 
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/extraction/)
+- [Documentation](https://python.langchain.com/docs/use_cases/extraction/)
 - End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain-extract/)
 
 **🤖 Chatbots**
 
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/chatbot/)
+- [Documentation](https://python.langchain.com/docs/use_cases/chatbots)
 - End-to-end Example: [Web LangChain (web researcher chatbot)](https://weblangchain.vercel.app) and [repo](https://github.com/langchain-ai/weblangchain)
 
-And much more! Head to the [Tutorials](https://python.langchain.com/v0.2/docs/tutorials/) section of the docs for more.
+And much more! Head to the [Use cases](https://python.langchain.com/docs/use_cases/) section of the docs for more.
 
 ## 🚀 How does LangChain help?
 The main value props of the LangChain libraries are:
@@ -87,49 +87,49 @@ Off-the-shelf chains make it easy to get started. Components make it easy to cus
 
 LCEL is the foundation of many of LangChain's components, and is a declarative way to compose chains. LCEL was designed from day 1 to support putting prototypes in production, with no code changes, from the simplest “prompt + LLM” chain to the most complex chains.
 
-- **[Overview](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel)**: LCEL and its benefits
-- **[Interface](https://python.langchain.com/v0.2/docs/concepts/#runnable-interface)**: The standard Runnable interface for LCEL objects
-- **[Primitives](https://python.langchain.com/v0.2/docs/how_to/#langchain-expression-language-lcel)**: More on the primitives LCEL includes
-- **[Cheatsheet](https://python.langchain.com/v0.2/docs/how_to/lcel_cheatsheet/)**: Quick overview of the most common usage patterns
+- **[Overview](https://python.langchain.com/docs/expression_language/)**: LCEL and its benefits
+- **[Interface](https://python.langchain.com/docs/expression_language/interface)**: The standard interface for LCEL objects
+- **[Primitives](https://python.langchain.com/docs/expression_language/primitives)**: More on the primitives LCEL includes
 
 ## Components
 
 Components fall into the following **modules**:
 
-**📃 Model I/O**
+**📃 Model I/O:**
 
-This includes [prompt management](https://python.langchain.com/v0.2/docs/concepts/#prompt-templates), [prompt optimization](https://python.langchain.com/v0.2/docs/concepts/#example-selectors), a generic interface for [chat models](https://python.langchain.com/v0.2/docs/concepts/#chat-models) and [LLMs](https://python.langchain.com/v0.2/docs/concepts/#llms), and common utilities for working with [model outputs](https://python.langchain.com/v0.2/docs/concepts/#output-parsers).
+This includes [prompt management](https://python.langchain.com/docs/modules/model_io/prompts/), [prompt optimization](https://python.langchain.com/docs/modules/model_io/prompts/example_selectors/), a generic interface for [chat models](https://python.langchain.com/docs/modules/model_io/chat/) and [LLMs](https://python.langchain.com/docs/modules/model_io/llms/), and common utilities for working with [model outputs](https://python.langchain.com/docs/modules/model_io/output_parsers/).
 
-**📚 Retrieval**
+**📚 Retrieval:**
 
-Retrieval Augmented Generation involves [loading data](https://python.langchain.com/v0.2/docs/concepts/#document-loaders) from a variety of sources, [preparing it](https://python.langchain.com/v0.2/docs/concepts/#text-splitters), then [searching over (a.k.a. retrieving from)](https://python.langchain.com/v0.2/docs/concepts/#retrievers) it for use in the generation step.
+Retrieval Augmented Generation involves [loading data](https://python.langchain.com/docs/modules/data_connection/document_loaders/) from a variety of sources, [preparing it](https://python.langchain.com/docs/modules/data_connection/document_loaders/), [then retrieving it](https://python.langchain.com/docs/modules/data_connection/retrievers/) for use in the generation step.
 
-**🤖 Agents**
+**🤖 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.
+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 done. LangChain provides a [standard interface for agents](https://python.langchain.com/docs/modules/agents/), a [selection of agents](https://python.langchain.com/docs/modules/agents/agent_types/) to choose from, and examples of end-to-end agents.
 
 ## 📖 Documentation
 
 Please see [here](https://python.langchain.com) for full documentation, which includes:
 
-- [Introduction](https://python.langchain.com/v0.2/docs/introduction/): Overview of the framework and the structure of the docs.
-- [Tutorials](https://python.langchain.com/docs/use_cases/): If you're looking to build something specific or are more of a hands-on learner, check out our tutorials. This is the best place to get started.
-- [How-to guides](https://python.langchain.com/v0.2/docs/how_to/): Answers to “How do I….?” type questions. These guides are goal-oriented and concrete; they're meant to help you complete a specific task.
-- [Conceptual guide](https://python.langchain.com/v0.2/docs/concepts/): Conceptual explanations of the key parts of the framework.
-- [API Reference](https://api.python.langchain.com): Thorough documentation of every class and method.
+- [Getting started](https://python.langchain.com/docs/get_started/introduction): installation, setting up the environment, simple examples
+- [Use case](https://python.langchain.com/docs/use_cases/) walkthroughs and best practice [guides](https://python.langchain.com/docs/guides/)
+- Overviews of the [interfaces](https://python.langchain.com/docs/expression_language/), [components](https://python.langchain.com/docs/modules/), and [integrations](https://python.langchain.com/docs/integrations/providers)
+
+You can also check out the full [API Reference docs](https://api.python.langchain.com).
 
 ## 🌐 Ecosystem
 
-- [🦜🛠️ 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.
+- [🦜🛠️ LangSmith](https://python.langchain.com/docs/langsmith/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
+- [🦜🕸️ LangGraph](https://python.langchain.com/docs/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/docs/templates/): Example applications hosted with LangServe.
 
 
 ## 💁 Contributing
 
 As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
 
-For detailed information on how to contribute, see [here](https://python.langchain.com/v0.2/docs/contributing/).
+For detailed information on how to contribute, see [here](https://python.langchain.com/docs/contributing/).
 
 ## 🌟 Contributors
 

cookbook/Multi_modal_RAG.ipynb

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

cookbook/Multi_modal_RAG_google.ipynb

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

cookbook/RAPTOR.ipynb

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

cookbook/README.md

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

cookbook/Semi_Structured_RAG.ipynb

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

cookbook/Semi_structured_and_multi_modal_RAG.ipynb

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

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

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

cookbook/advanced_rag_eval.ipynb

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

cookbook/agent_vectorstore.ipynb

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

cookbook/airbyte_github.ipynb

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

cookbook/autogpt/marathon_times.ipynb

@@ -46,7 +46,7 @@
     "from langchain_experimental.autonomous_agents import AutoGPT\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "# Needed since jupyter runs an async eventloop\n",
+    "# Needed synce jupyter runs an async eventloop\n",
     "nest_asyncio.apply()"
    ]
   },

cookbook/docugami_xml_kg_rag.ipynb

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

cookbook/fireworks_rag.ipynb

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

cookbook/hypothetical_document_embeddings.ipynb

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

cookbook/langgraph_agentic_rag.ipynb

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

cookbook/langgraph_crag.ipynb

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

cookbook/langgraph_self_rag.ipynb

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

cookbook/multi_modal_RAG_chroma.ipynb

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

cookbook/multi_modal_RAG_vdms.ipynb

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

cookbook/nomic_embedding_rag.ipynb

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

cookbook/nomic_multimodal_rag.ipynb

@@ -1,497 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "9fc3897d-176f-4729-8fd1-cfb4add53abd",
-   "metadata": {},
-   "source": [
-    "## Nomic multi-modal RAG\n",
-    "\n",
-    "Many documents contain a mixture of content types, including text and images. \n",
-    "\n",
-    "Yet, information captured in images is lost in most RAG applications.\n",
-    "\n",
-    "With the emergence of multimodal LLMs, like [GPT-4V](https://openai.com/research/gpt-4v-system-card), it is worth considering how to utilize images in RAG:\n",
-    "\n",
-    "In this demo we\n",
-    "\n",
-    "* Use multimodal embeddings from Nomic Embed [Vision](https://huggingface.co/nomic-ai/nomic-embed-vision-v1.5) and [Text](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) to embed images and text\n",
-    "* Retrieve both using similarity search\n",
-    "* Pass raw images and text chunks to a multimodal LLM for answer synthesis \n",
-    "\n",
-    "## Signup\n",
-    "\n",
-    "Get your API token, then run:\n",
-    "```\n",
-    "! nomic login\n",
-    "```\n",
-    "\n",
-    "Then run with your generated API token \n",
-    "```\n",
-    "! nomic login < token > \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": null,
-   "id": "54926b9b-75c2-4cd4-8f14-b3882a0d370b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "! nomic login token"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "febbc459-ebba-4c1a-a52b-fed7731593f8",
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "! pip install -U langchain-nomic langchain-chroma langchain-community tiktoken langchain-openai langchain # (newest versions required for multi-modal)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "acbdc603-39e2-4a5f-836c-2bbaecd46b0b",
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
-    "! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml pillow matplotlib tiktoken"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1e94b3fb-8e3e-4736-be0a-ad881626c7bd",
-   "metadata": {},
-   "source": [
-    "## Data Loading\n",
-    "\n",
-    "### Partition PDF text and images\n",
-    "  \n",
-    "Let's look at an example pdfs containing interesting images.\n",
-    "\n",
-    "1/ Art from the J Paul Getty museum:\n",
-    "\n",
-    " * Here is a [zip file](https://drive.google.com/file/d/18kRKbq2dqAhhJ3DfZRnYcTBEUfYxe1YR/view?usp=sharing) with the PDF and the already extracted images. \n",
-    "* https://www.getty.edu/publications/resources/virtuallibrary/0892360224.pdf\n",
-    "\n",
-    "2/ 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.\n",
-    "\n",
-    "To supply this to extract the images:\n",
-    "```\n",
-    "extract_images_in_pdf=True\n",
-    "```\n",
-    "\n",
-    "\n",
-    "\n",
-    "If using this zip file, then you can simply process the text only with:\n",
-    "```\n",
-    "extract_images_in_pdf=False\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "9646b524-71a7-4b2a-bdc8-0b81f77e968f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Folder with pdf and extracted images\n",
-    "from pathlib import Path\n",
-    "\n",
-    "# replace with actual path to images\n",
-    "path = Path(\"../art\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "77f096ab-a933-41d0-8f4e-1efc83998fc3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "path.resolve()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bc4839c0-8773-4a07-ba59-5364501269b2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Extract images, tables, and chunk text\n",
-    "from unstructured.partition.pdf import partition_pdf\n",
-    "\n",
-    "raw_pdf_elements = partition_pdf(\n",
-    "    filename=str(path.resolve()) + \"/getty.pdf\",\n",
-    "    extract_images_in_pdf=False,\n",
-    "    infer_table_structure=True,\n",
-    "    chunking_strategy=\"by_title\",\n",
-    "    max_characters=4000,\n",
-    "    new_after_n_chars=3800,\n",
-    "    combine_text_under_n_chars=2000,\n",
-    "    image_output_dir_path=path,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "969545ad",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Categorize text elements by type\n",
-    "tables = []\n",
-    "texts = []\n",
-    "for element in raw_pdf_elements:\n",
-    "    if \"unstructured.documents.elements.Table\" in str(type(element)):\n",
-    "        tables.append(str(element))\n",
-    "    elif \"unstructured.documents.elements.CompositeElement\" in str(type(element)):\n",
-    "        texts.append(str(element))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5d8e6349-1547-4cbf-9c6f-491d8610ec10",
-   "metadata": {},
-   "source": [
-    "## Multi-modal embeddings with our document\n",
-    "\n",
-    "We will use [nomic-embed-vision-v1.5](https://huggingface.co/nomic-ai/nomic-embed-vision-v1.5) embeddings. This model is aligned \n",
-    "to [nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) allowing for multimodal semantic search and Multimodal RAG!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4bc15842-cb95-4f84-9eb5-656b0282a800",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "import uuid\n",
-    "\n",
-    "import chromadb\n",
-    "import numpy as np\n",
-    "from langchain_chroma import Chroma\n",
-    "from langchain_nomic import NomicEmbeddings\n",
-    "from PIL import Image as _PILImage\n",
-    "\n",
-    "# Create chroma\n",
-    "text_vectorstore = Chroma(\n",
-    "    collection_name=\"mm_rag_clip_photos_text\",\n",
-    "    embedding_function=NomicEmbeddings(\n",
-    "        vision_model=\"nomic-embed-vision-v1.5\", model=\"nomic-embed-text-v1.5\"\n",
-    "    ),\n",
-    ")\n",
-    "image_vectorstore = Chroma(\n",
-    "    collection_name=\"mm_rag_clip_photos_image\",\n",
-    "    embedding_function=NomicEmbeddings(\n",
-    "        vision_model=\"nomic-embed-vision-v1.5\", model=\"nomic-embed-text-v1.5\"\n",
-    "    ),\n",
-    ")\n",
-    "\n",
-    "# Get image URIs with .jpg extension only\n",
-    "image_uris = sorted(\n",
-    "    [\n",
-    "        os.path.join(path, image_name)\n",
-    "        for image_name in os.listdir(path)\n",
-    "        if image_name.endswith(\".jpg\")\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "# Add images\n",
-    "image_vectorstore.add_images(uris=image_uris)\n",
-    "\n",
-    "# Add documents\n",
-    "text_vectorstore.add_texts(texts=texts)\n",
-    "\n",
-    "# Make retriever\n",
-    "image_retriever = image_vectorstore.as_retriever()\n",
-    "text_retriever = text_vectorstore.as_retriever()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "02a186d0-27e0-4820-8092-63b5349dd25d",
-   "metadata": {},
-   "source": [
-    "## RAG\n",
-    "\n",
-    "`vectorstore.add_images` will store / retrieve images as base64 encoded strings.\n",
-    "\n",
-    "These can be passed to [GPT-4V](https://platform.openai.com/docs/guides/vision)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "344f56a8-0dc3-433e-851c-3f7600c7a72b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import base64\n",
-    "import io\n",
-    "from io import BytesIO\n",
-    "\n",
-    "import numpy as np\n",
-    "from PIL import Image\n",
-    "\n",
-    "\n",
-    "def resize_base64_image(base64_string, size=(128, 128)):\n",
-    "    \"\"\"\n",
-    "    Resize an image encoded as a Base64 string.\n",
-    "\n",
-    "    Args:\n",
-    "    base64_string (str): Base64 string of the original image.\n",
-    "    size (tuple): Desired size of the image as (width, height).\n",
-    "\n",
-    "    Returns:\n",
-    "    str: Base64 string of the resized image.\n",
-    "    \"\"\"\n",
-    "    # Decode the Base64 string\n",
-    "    img_data = base64.b64decode(base64_string)\n",
-    "    img = Image.open(io.BytesIO(img_data))\n",
-    "\n",
-    "    # Resize the image\n",
-    "    resized_img = img.resize(size, Image.LANCZOS)\n",
-    "\n",
-    "    # Save the resized image to a bytes buffer\n",
-    "    buffered = io.BytesIO()\n",
-    "    resized_img.save(buffered, format=img.format)\n",
-    "\n",
-    "    # Encode the resized image to Base64\n",
-    "    return base64.b64encode(buffered.getvalue()).decode(\"utf-8\")\n",
-    "\n",
-    "\n",
-    "def is_base64(s):\n",
-    "    \"\"\"Check if a string is Base64 encoded\"\"\"\n",
-    "    try:\n",
-    "        return base64.b64encode(base64.b64decode(s)) == s.encode()\n",
-    "    except Exception:\n",
-    "        return False\n",
-    "\n",
-    "\n",
-    "def split_image_text_types(docs):\n",
-    "    \"\"\"Split numpy array images and texts\"\"\"\n",
-    "    images = []\n",
-    "    text = []\n",
-    "    for doc in docs:\n",
-    "        doc = doc.page_content  # Extract Document contents\n",
-    "        if is_base64(doc):\n",
-    "            # Resize image to avoid OAI server error\n",
-    "            images.append(\n",
-    "                resize_base64_image(doc, size=(250, 250))\n",
-    "            )  # base64 encoded str\n",
-    "        else:\n",
-    "            text.append(doc)\n",
-    "    return {\"images\": images, \"texts\": text}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "23a2c1d8-fea6-4152-b184-3172dd46c735",
-   "metadata": {},
-   "source": [
-    "Currently, we format the inputs using a `RunnableLambda` while we add image support to `ChatPromptTemplates`.\n",
-    "\n",
-    "Our runnable follows the classic RAG flow - \n",
-    "\n",
-    "* We first compute the context (both \"texts\" and \"images\" in this case) and the question (just a RunnablePassthrough here) \n",
-    "* Then we pass this into our prompt template, which is a custom function that formats the message for the gpt-4-vision-preview model. \n",
-    "* And finally we parse the output as a string."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5d8919dc-c238-4746-86ba-45d940a7d260",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4c93fab3-74c4-4f1d-958a-0bc4cdd0797e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from operator import itemgetter\n",
-    "\n",
-    "from langchain_core.messages import HumanMessage, SystemMessage\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.runnables import RunnableLambda, RunnablePassthrough\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "\n",
-    "def prompt_func(data_dict):\n",
-    "    # Joining the context texts into a single string\n",
-    "    formatted_texts = \"\\n\".join(data_dict[\"text_context\"][\"texts\"])\n",
-    "    messages = []\n",
-    "\n",
-    "    # Adding image(s) to the messages if present\n",
-    "    if data_dict[\"image_context\"][\"images\"]:\n",
-    "        image_message = {\n",
-    "            \"type\": \"image_url\",\n",
-    "            \"image_url\": {\n",
-    "                \"url\": f\"data:image/jpeg;base64,{data_dict['image_context']['images'][0]}\"\n",
-    "            },\n",
-    "        }\n",
-    "        messages.append(image_message)\n",
-    "\n",
-    "    # Adding the text message for analysis\n",
-    "    text_message = {\n",
-    "        \"type\": \"text\",\n",
-    "        \"text\": (\n",
-    "            \"As an expert art critic and historian, your task is to analyze and interpret images, \"\n",
-    "            \"considering their historical and cultural significance. Alongside the images, you will be \"\n",
-    "            \"provided with related text to offer context. Both will be retrieved from a vectorstore based \"\n",
-    "            \"on user-input keywords. Please use your extensive knowledge and analytical skills to provide a \"\n",
-    "            \"comprehensive summary that includes:\\n\"\n",
-    "            \"- A detailed description of the visual elements in the image.\\n\"\n",
-    "            \"- The historical and cultural context of the image.\\n\"\n",
-    "            \"- An interpretation of the image's symbolism and meaning.\\n\"\n",
-    "            \"- Connections between the image and the related text.\\n\\n\"\n",
-    "            f\"User-provided keywords: {data_dict['question']}\\n\\n\"\n",
-    "            \"Text and / or tables:\\n\"\n",
-    "            f\"{formatted_texts}\"\n",
-    "        ),\n",
-    "    }\n",
-    "    messages.append(text_message)\n",
-    "\n",
-    "    return [HumanMessage(content=messages)]\n",
-    "\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0, model=\"gpt-4-vision-preview\", max_tokens=1024)\n",
-    "\n",
-    "# RAG pipeline\n",
-    "chain = (\n",
-    "    {\n",
-    "        \"text_context\": text_retriever | RunnableLambda(split_image_text_types),\n",
-    "        \"image_context\": image_retriever | RunnableLambda(split_image_text_types),\n",
-    "        \"question\": RunnablePassthrough(),\n",
-    "    }\n",
-    "    | RunnableLambda(prompt_func)\n",
-    "    | model\n",
-    "    | StrOutputParser()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1566096d-97c2-4ddc-ba4a-6ef88c525e4e",
-   "metadata": {},
-   "source": [
-    "## Test retrieval and run RAG"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "90121e56-674b-473b-871d-6e4753fd0c45",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from IPython.display import HTML, display\n",
-    "\n",
-    "\n",
-    "def plt_img_base64(img_base64):\n",
-    "    # Create an HTML img tag with the base64 string as the source\n",
-    "    image_html = f'<img src=\"data:image/jpeg;base64,{img_base64}\" />'\n",
-    "\n",
-    "    # Display the image by rendering the HTML\n",
-    "    display(HTML(image_html))\n",
-    "\n",
-    "\n",
-    "docs = text_retriever.invoke(\"Women with children\", k=5)\n",
-    "for doc in docs:\n",
-    "    if is_base64(doc.page_content):\n",
-    "        plt_img_base64(doc.page_content)\n",
-    "    else:\n",
-    "        print(doc.page_content)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "44eaa532-f035-4c04-b578-02339d42554c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = image_retriever.invoke(\"Women with children\", k=5)\n",
-    "for doc in docs:\n",
-    "    if is_base64(doc.page_content):\n",
-    "        plt_img_base64(doc.page_content)\n",
-    "    else:\n",
-    "        print(doc.page_content)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "69fb15fd-76fc-49b4-806d-c4db2990027d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain.invoke(\"Women with children\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "227f08b8-e732-4089-b65c-6eb6f9e48f15",
-   "metadata": {},
-   "source": [
-    "We can see the images retrieved in the LangSmith trace:\n",
-    "\n",
-    "LangSmith [trace](https://smith.langchain.com/public/69c558a5-49dc-4c60-a49b-3adbb70f74c5/r/e872c2c8-528c-468f-aefd-8b5cd730a673)."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/openai_functions_retrieval_qa.ipynb

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

cookbook/optimization.ipynb

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

cookbook/oracleai_demo.ipynb

@@ -86,7 +86,8 @@
     "\n",
     "import oracledb\n",
     "\n",
-    "# Update with your username, password, hostname, and service_name\n",
+    "# please update with your username, password, hostname and service_name\n",
+    "# please make sure this user has sufficient privileges to perform all below\n",
     "username = \"\"\n",
     "password = \"\"\n",
     "dsn = \"\"\n",
@@ -96,45 +97,40 @@
     "    print(\"Connection successful!\")\n",
     "\n",
     "    cursor = conn.cursor()\n",
-    "    try:\n",
-    "        cursor.execute(\n",
-    "            \"\"\"\n",
-    "            begin\n",
-    "                -- Drop user\n",
-    "                begin\n",
-    "                    execute immediate 'drop user testuser cascade';\n",
-    "                exception\n",
-    "                    when others then\n",
-    "                        dbms_output.put_line('Error dropping user: ' || SQLERRM);\n",
-    "                end;\n",
-    "                \n",
-    "                -- Create user and grant privileges\n",
-    "                execute immediate 'create user testuser identified by testuser';\n",
-    "                execute immediate 'grant connect, unlimited tablespace, create credential, create procedure, create any index to testuser';\n",
-    "                execute immediate 'create or replace directory DEMO_PY_DIR as ''/scratch/hroy/view_storage/hroy_devstorage/demo/orachain''';\n",
-    "                execute immediate 'grant read, write on directory DEMO_PY_DIR to public';\n",
-    "                execute immediate 'grant create mining model to testuser';\n",
-    "                \n",
-    "                -- Network access\n",
-    "                begin\n",
-    "                    DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(\n",
-    "                        host => '*',\n",
-    "                        ace => xs$ace_type(privilege_list => xs$name_list('connect'),\n",
-    "                                           principal_name => 'testuser',\n",
-    "                                           principal_type => xs_acl.ptype_db)\n",
-    "                    );\n",
-    "                end;\n",
-    "            end;\n",
-    "            \"\"\"\n",
-    "        )\n",
-    "        print(\"User setup done!\")\n",
-    "    except Exception as e:\n",
-    "        print(f\"User setup failed with error: {e}\")\n",
-    "    finally:\n",
-    "        cursor.close()\n",
+    "    cursor.execute(\n",
+    "        \"\"\"\n",
+    "    begin\n",
+    "        -- drop user\n",
+    "        begin\n",
+    "            execute immediate 'drop user testuser cascade';\n",
+    "        exception\n",
+    "            when others then\n",
+    "                dbms_output.put_line('Error setting up user.');\n",
+    "        end;\n",
+    "        execute immediate 'create user testuser identified by testuser';\n",
+    "        execute immediate 'grant connect, unlimited tablespace, create credential, create procedure, create any index to testuser';\n",
+    "        execute immediate 'create or replace directory DEMO_PY_DIR as ''/scratch/hroy/view_storage/hroy_devstorage/demo/orachain''';\n",
+    "        execute immediate 'grant read, write on directory DEMO_PY_DIR to public';\n",
+    "        execute immediate 'grant create mining model to testuser';\n",
+    "\n",
+    "        -- network access\n",
+    "        begin\n",
+    "            DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(\n",
+    "                host => '*',\n",
+    "                ace => xs$ace_type(privilege_list => xs$name_list('connect'),\n",
+    "                                principal_name => 'testuser',\n",
+    "                                principal_type => xs_acl.ptype_db));\n",
+    "        end;\n",
+    "    end;\n",
+    "    \"\"\"\n",
+    "    )\n",
+    "    print(\"User setup done!\")\n",
+    "    cursor.close()\n",
     "    conn.close()\n",
     "except Exception as e:\n",
-    "    print(f\"Connection failed with error: {e}\")\n",
+    "    print(\"User setup failed!\")\n",
+    "    cursor.close()\n",
+    "    conn.close()\n",
     "    sys.exit(1)"
    ]
   },
@@ -530,6 +526,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "***Note:*** Currently, OracleEmbeddings processes each embedding generation request individually, without batching, by calling REST endpoints separately for each request. This method could potentially lead to exceeding the maximum request per minute quota set by some providers. However, we are actively working to enhance this process by implementing request batching, which will allow multiple embedding requests to be combined into fewer API calls, thereby optimizing our use of provider resources and adhering to their request limits. This update is expected to be rolled out soon, eliminating the current limitation.\n",
+    "\n",
     "***Note:*** Users may need to configure a proxy to utilize third-party embedding generation providers, excluding the 'database' provider that utilizes an ONNX model."
    ]
   },

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

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

cookbook/rag_with_quantized_embeddings.ipynb

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

cookbook/sql_db_qa.mdx

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

cookbook/together_ai.ipynb

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

docs/Makefile

@@ -13,7 +13,7 @@ OUTPUT_NEW_DOCS_DIR = $(OUTPUT_NEW_DIR)/docs
 
 PYTHON = .venv/bin/python
 
-PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm|couchbase" | tr '\n' ' ')
+PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm" | tr '\n' ' ')
 
 PORT ?= 3001
 
@@ -35,15 +35,11 @@ generate-files:
 	mkdir -p $(INTERMEDIATE_DIR)
 	cp -r $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
 	mkdir -p $(INTERMEDIATE_DIR)/templates
+	cp ../templates/docs/INDEX.md $(INTERMEDIATE_DIR)/templates/index.md
+	cp ../cookbook/README.md $(INTERMEDIATE_DIR)/cookbook.mdx
 
 	$(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/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
@@ -65,7 +61,7 @@ render:
 	$(PYTHON) scripts/notebook_convert.py $(INTERMEDIATE_DIR) $(OUTPUT_NEW_DOCS_DIR)
 
 md-sync:
-	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --include="*/_category_.yml" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
+	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
 
 generate-references:
 	$(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(OUTPUT_NEW_DOCS_DIR)

docs/api_reference/conf.py

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

docs/api_reference/create_api_rst.py

@@ -10,21 +10,12 @@ 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",
-    "RunnablePydantic",
-    "RunnableNonPydantic",
-]
+ClassKind = Literal["TypedDict", "Regular", "Pydantic", "enum"]
 
 
 class ClassInfo(TypedDict):
@@ -78,36 +69,8 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
             continue
 
         if inspect.isclass(type_):
-            # The type of the class is used to select a template
-            # 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
+            if type(type_) == typing._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):
@@ -165,11 +128,11 @@ def _load_package_modules(
     of the modules/packages are part of the package vs. 3rd party or built-in.
 
     Parameters:
-        package_directory (Union[str, Path]): Path to the package directory.
-        submodule (Optional[str]): Optional name of submodule to load.
+        package_directory: Path to the package directory.
+        submodule: Optional name of submodule to load.
 
     Returns:
-        Dict[str, ModuleMembers]: A dictionary where keys are module names and values are ModuleMembers objects.
+        list: A list of loaded module objects.
     """
     package_path = (
         Path(package_directory)
@@ -288,10 +251,6 @@ 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"
 

docs/api_reference/templates/class.rst

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

docs/api_reference/templates/pydantic.rst

@@ -15,8 +15,6 @@
     :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

@@ -1,40 +0,0 @@
-: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

@@ -1,24 +0,0 @@
-: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

@@ -2,129 +2,132 @@
 {%- 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">
-                {%- 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 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>
-        <div id="sk-page-content-wrapper">
-            <div class="sk-page-content container-fluid body px-md-3" role="main">
-                {% block body %}{% endblock %}
+            {%- 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>
-            <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>
+            {%- elif meta and meta['globalsidebartoc']|tobool %}
+            <div class="sk-sidebar-toc sk-sidebar-global-toc">
+              {{ toctree(maxdepth=2, titles_only=True) }}
             </div>
-        </div>
+            {%- else %}
+            <div class="sk-sidebar-toc">
+              {{ toc }}
+            </div>
+            {%- endif %}
+      </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/docs/additional_resources/arxiv_references.mdx

@@ -2,154 +2,32 @@
             
 LangChain implements the latest research in the field of Natural Language Processing.
 This page contains `arXiv` papers referenced in the LangChain Documentation, API Reference,
- Templates, and Cookbooks.
-
-From the opposite direction, scientists use LangChain in research and reference LangChain in the research papers. 
-Here you find [such papers](https://arxiv.org/search/?query=langchain&searchtype=all&source=header).
+and Templates.
 
 ## Summary
 
 | arXiv id / Title | Authors | Published date 🔻 | LangChain Documentation|
 |------------------|---------|-------------------|------------------------|
-| `2402.03620v1` [Self-Discover: Large Language Models Self-Compose Reasoning Structures](http://arxiv.org/abs/2402.03620v1) | Pei Zhou, Jay Pujara, Xiang Ren,  et al. | 2024-02-06 | `Cookbook:` [self-discover](https://github.com/langchain-ai/langchain/blob/master/cookbook/self-discover.ipynb)
-| `2401.18059v1` [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](http://arxiv.org/abs/2401.18059v1) | Parth Sarthi, Salman Abdullah, Aditi Tuli,  et al. | 2024-01-31 | `Cookbook:` [RAPTOR](https://github.com/langchain-ai/langchain/blob/master/cookbook/RAPTOR.ipynb)
-| `2401.15884v2` [Corrective Retrieval Augmented Generation](http://arxiv.org/abs/2401.15884v2) | Shi-Qi Yan, Jia-Chen Gu, Yun Zhu,  et al. | 2024-01-29 | `Cookbook:` [langgraph_crag](https://github.com/langchain-ai/langchain/blob/master/cookbook/langgraph_crag.ipynb)
-| `2401.04088v1` [Mixtral of Experts](http://arxiv.org/abs/2401.04088v1) | Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux,  et al. | 2024-01-08 | `Cookbook:` [together_ai](https://github.com/langchain-ai/langchain/blob/master/cookbook/together_ai.ipynb)
 | `2312.06648v2` [Dense X Retrieval: What Retrieval Granularity Should We Use?](http://arxiv.org/abs/2312.06648v2) | Tong Chen, Hongwei Wang, Sihao Chen,  et al. | 2023-12-11 | `Template:` [propositional-retrieval](https://python.langchain.com/docs/templates/propositional-retrieval)
 | `2311.09210v1` [Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models](http://arxiv.org/abs/2311.09210v1) | Wenhao Yu, Hongming Zhang, Xiaoman Pan,  et al. | 2023-11-15 | `Template:` [chain-of-note-wiki](https://python.langchain.com/docs/templates/chain-of-note-wiki)
-| `2310.11511v1` [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](http://arxiv.org/abs/2310.11511v1) | Akari Asai, Zeqiu Wu, Yizhong Wang,  et al. | 2023-10-17 | `Cookbook:` [langgraph_self_rag](https://github.com/langchain-ai/langchain/blob/master/cookbook/langgraph_self_rag.ipynb)
-| `2310.06117v2` [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](http://arxiv.org/abs/2310.06117v2) | Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen,  et al. | 2023-10-09 | `Template:` [stepback-qa-prompting](https://python.langchain.com/docs/templates/stepback-qa-prompting), `Cookbook:` [stepback-qa](https://github.com/langchain-ai/langchain/blob/master/cookbook/stepback-qa.ipynb)
-| `2307.09288v2` [Llama 2: Open Foundation and Fine-Tuned Chat Models](http://arxiv.org/abs/2307.09288v2) | Hugo Touvron, Louis Martin, Kevin Stone,  et al. | 2023-07-18 | `Cookbook:` [Semi_Structured_RAG](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_Structured_RAG.ipynb)
-| `2305.14283v3` [Query Rewriting for Retrieval-Augmented Large Language Models](http://arxiv.org/abs/2305.14283v3) | Xinbei Ma, Yeyun Gong, Pengcheng He,  et al. | 2023-05-23 | `Template:` [rewrite-retrieve-read](https://python.langchain.com/docs/templates/rewrite-retrieve-read), `Cookbook:` [rewrite](https://github.com/langchain-ai/langchain/blob/master/cookbook/rewrite.ipynb)
-| `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:` [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)
+| `2310.06117v2` [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](http://arxiv.org/abs/2310.06117v2) | Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen,  et al. | 2023-10-09 | `Template:` [stepback-qa-prompting](https://python.langchain.com/docs/templates/stepback-qa-prompting)
+| `2305.14283v3` [Query Rewriting for Retrieval-Augmented Large Language Models](http://arxiv.org/abs/2305.14283v3) | Xinbei Ma, Yeyun Gong, Pengcheng He,  et al. | 2023-05-23 | `Template:` [rewrite-retrieve-read](https://python.langchain.com/docs/templates/rewrite-retrieve-read)
+| `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)
+| `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)
 | `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...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)
+| `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.llms...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.llms...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.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint)
+| `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.chains...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)
 | `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)
+| `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.example_selectors...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.pal_chain...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)
 | `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...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)
+| `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.embeddings...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.utilities...SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), [langchain_community.utilities...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL)
+| `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.llms...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.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint)
 | `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...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)
+| `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.llms...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.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint)
 | `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
-
-- **arXiv id:** 2402.03620v1
-- **Title:** Self-Discover: Large Language Models Self-Compose Reasoning Structures
-- **Authors:** Pei Zhou, Jay Pujara, Xiang Ren,  et al.
-- **Published Date:** 2024-02-06
-- **URL:** http://arxiv.org/abs/2402.03620v1
-- **LangChain:**
-
-   - **Cookbook:** [self-discover](https://github.com/langchain-ai/langchain/blob/master/cookbook/self-discover.ipynb)
-
-**Abstract:** We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the
-task-intrinsic reasoning structures to tackle complex reasoning problems that
-are challenging for typical prompting methods. Core to the framework is a
-self-discovery process where LLMs select multiple atomic reasoning modules such
-as critical thinking and step-by-step thinking, and compose them into an
-explicit reasoning structure for LLMs to follow during decoding. SELF-DISCOVER
-substantially improves GPT-4 and PaLM 2's performance on challenging reasoning
-benchmarks such as BigBench-Hard, grounded agent reasoning, and MATH, by as
-much as 32% compared to Chain of Thought (CoT). Furthermore, SELF-DISCOVER
-outperforms inference-intensive methods such as CoT-Self-Consistency by more
-than 20%, while requiring 10-40x fewer inference compute. Finally, we show that
-the self-discovered reasoning structures are universally applicable across
-model families: from PaLM 2-L to GPT-4, and from GPT-4 to Llama2, and share
-commonalities with human reasoning patterns.
-                
-## RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
-
-- **arXiv id:** 2401.18059v1
-- **Title:** RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
-- **Authors:** Parth Sarthi, Salman Abdullah, Aditi Tuli,  et al.
-- **Published Date:** 2024-01-31
-- **URL:** http://arxiv.org/abs/2401.18059v1
-- **LangChain:**
-
-   - **Cookbook:** [RAPTOR](https://github.com/langchain-ai/langchain/blob/master/cookbook/RAPTOR.ipynb)
-
-**Abstract:** Retrieval-augmented language models can better adapt to changes in world
-state and incorporate long-tail knowledge. However, most existing methods
-retrieve only short contiguous chunks from a retrieval corpus, limiting
-holistic understanding of the overall document context. We introduce the novel
-approach of recursively embedding, clustering, and summarizing chunks of text,
-constructing a tree with differing levels of summarization from the bottom up.
-At inference time, our RAPTOR model retrieves from this tree, integrating
-information across lengthy documents at different levels of abstraction.
-Controlled experiments show that retrieval with recursive summaries offers
-significant improvements over traditional retrieval-augmented LMs on several
-tasks. On question-answering tasks that involve complex, multi-step reasoning,
-we show state-of-the-art results; for example, by coupling RAPTOR retrieval
-with the use of GPT-4, we can improve the best performance on the QuALITY
-benchmark by 20% in absolute accuracy.
-                
-## Corrective Retrieval Augmented Generation
-
-- **arXiv id:** 2401.15884v2
-- **Title:** Corrective Retrieval Augmented Generation
-- **Authors:** Shi-Qi Yan, Jia-Chen Gu, Yun Zhu,  et al.
-- **Published Date:** 2024-01-29
-- **URL:** http://arxiv.org/abs/2401.15884v2
-- **LangChain:**
-
-   - **Cookbook:** [langgraph_crag](https://github.com/langchain-ai/langchain/blob/master/cookbook/langgraph_crag.ipynb)
-
-**Abstract:** Large language models (LLMs) inevitably exhibit hallucinations since the
-accuracy of generated texts cannot be secured solely by the parametric
-knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a
-practicable complement to LLMs, it relies heavily on the relevance of retrieved
-documents, raising concerns about how the model behaves if retrieval goes
-wrong. To this end, we propose the Corrective Retrieval Augmented Generation
-(CRAG) to improve the robustness of generation. Specifically, a lightweight
-retrieval evaluator is designed to assess the overall quality of retrieved
-documents for a query, returning a confidence degree based on which different
-knowledge retrieval actions can be triggered. Since retrieval from static and
-limited corpora can only return sub-optimal documents, large-scale web searches
-are utilized as an extension for augmenting the retrieval results. Besides, a
-decompose-then-recompose algorithm is designed for retrieved documents to
-selectively focus on key information and filter out irrelevant information in
-them. CRAG is plug-and-play and can be seamlessly coupled with various
-RAG-based approaches. Experiments on four datasets covering short- and
-long-form generation tasks show that CRAG can significantly improve the
-performance of RAG-based approaches.
-                
-## Mixtral of Experts
-
-- **arXiv id:** 2401.04088v1
-- **Title:** Mixtral of Experts
-- **Authors:** Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux,  et al.
-- **Published Date:** 2024-01-08
-- **URL:** http://arxiv.org/abs/2401.04088v1
-- **LangChain:**
-
-   - **Cookbook:** [together_ai](https://github.com/langchain-ai/langchain/blob/master/cookbook/together_ai.ipynb)
-
-**Abstract:** We introduce Mixtral 8x7B, a Sparse Mixture of Experts (SMoE) language model.
-Mixtral has the same architecture as Mistral 7B, with the difference that each
-layer is composed of 8 feedforward blocks (i.e. experts). For every token, at
-each layer, a router network selects two experts to process the current state
-and combine their outputs. Even though each token only sees two experts, the
-selected experts can be different at each timestep. As a result, each token has
-access to 47B parameters, but only uses 13B active parameters during inference.
-Mixtral was trained with a context size of 32k tokens and it outperforms or
-matches Llama 2 70B and GPT-3.5 across all evaluated benchmarks. In particular,
-Mixtral vastly outperforms Llama 2 70B on mathematics, code generation, and
-multilingual benchmarks. We also provide a model fine-tuned to follow
-instructions, Mixtral 8x7B - Instruct, that surpasses GPT-3.5 Turbo,
-Claude-2.1, Gemini Pro, and Llama 2 70B - chat model on human benchmarks. Both
-the base and instruct models are released under the Apache 2.0 license.
-                
 ## Dense X Retrieval: What Retrieval Granularity Should We Use?
 
 - **arXiv id:** 2312.06648v2
@@ -213,39 +91,6 @@ average improvement of +7.9 in EM score given entirely noisy retrieved
 documents and +10.5 in rejection rates for real-time questions that fall
 outside the pre-training knowledge scope.
                 
-## Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
-
-- **arXiv id:** 2310.11511v1
-- **Title:** Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
-- **Authors:** Akari Asai, Zeqiu Wu, Yizhong Wang,  et al.
-- **Published Date:** 2023-10-17
-- **URL:** http://arxiv.org/abs/2310.11511v1
-- **LangChain:**
-
-   - **Cookbook:** [langgraph_self_rag](https://github.com/langchain-ai/langchain/blob/master/cookbook/langgraph_self_rag.ipynb)
-
-**Abstract:** Despite their remarkable capabilities, large language models (LLMs) often
-produce responses containing factual inaccuracies due to their sole reliance on
-the parametric knowledge they encapsulate. Retrieval-Augmented Generation
-(RAG), an ad hoc approach that augments LMs with retrieval of relevant
-knowledge, decreases such issues. However, indiscriminately retrieving and
-incorporating a fixed number of retrieved passages, regardless of whether
-retrieval is necessary, or passages are relevant, diminishes LM versatility or
-can lead to unhelpful response generation. We introduce a new framework called
-Self-Reflective Retrieval-Augmented Generation (Self-RAG) that enhances an LM's
-quality and factuality through retrieval and self-reflection. Our framework
-trains a single arbitrary LM that adaptively retrieves passages on-demand, and
-generates and reflects on retrieved passages and its own generations using
-special tokens, called reflection tokens. Generating reflection tokens makes
-the LM controllable during the inference phase, enabling it to tailor its
-behavior to diverse task requirements. Experiments show that Self-RAG (7B and
-13B parameters) significantly outperforms state-of-the-art LLMs and
-retrieval-augmented models on a diverse set of tasks. Specifically, Self-RAG
-outperforms ChatGPT and retrieval-augmented Llama2-chat on Open-domain QA,
-reasoning and fact verification tasks, and it shows significant gains in
-improving factuality and citation accuracy for long-form generations relative
-to these models.
-                
 ## Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
 
 - **arXiv id:** 2310.06117v2
@@ -256,7 +101,6 @@ to these models.
 - **LangChain:**
 
    - **Template:** [stepback-qa-prompting](https://python.langchain.com/docs/templates/stepback-qa-prompting)
-   - **Cookbook:** [stepback-qa](https://github.com/langchain-ai/langchain/blob/master/cookbook/stepback-qa.ipynb)
 
 **Abstract:** We present Step-Back Prompting, a simple prompting technique that enables
 LLMs to do abstractions to derive high-level concepts and first principles from
@@ -269,27 +113,6 @@ including STEM, Knowledge QA, and Multi-Hop Reasoning. For instance, Step-Back
 Prompting improves PaLM-2L performance on MMLU (Physics and Chemistry) by 7%
 and 11% respectively, TimeQA by 27%, and MuSiQue by 7%.
                 
-## Llama 2: Open Foundation and Fine-Tuned Chat Models
-
-- **arXiv id:** 2307.09288v2
-- **Title:** Llama 2: Open Foundation and Fine-Tuned Chat Models
-- **Authors:** Hugo Touvron, Louis Martin, Kevin Stone,  et al.
-- **Published Date:** 2023-07-18
-- **URL:** http://arxiv.org/abs/2307.09288v2
-- **LangChain:**
-
-   - **Cookbook:** [Semi_Structured_RAG](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_Structured_RAG.ipynb)
-
-**Abstract:** In this work, we develop and release Llama 2, a collection of pretrained and
-fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70
-billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for
-dialogue use cases. Our models outperform open-source chat models on most
-benchmarks we tested, and based on our human evaluations for helpfulness and
-safety, may be a suitable substitute for closed-source models. We provide a
-detailed description of our approach to fine-tuning and safety improvements of
-Llama 2-Chat in order to enable the community to build on our work and
-contribute to the responsible development of LLMs.
-                
 ## Query Rewriting for Retrieval-Augmented Large Language Models
 
 - **arXiv id:** 2305.14283v3
@@ -300,7 +123,6 @@ contribute to the responsible development of LLMs.
 - **LangChain:**
 
    - **Template:** [rewrite-retrieve-read](https://python.langchain.com/docs/templates/rewrite-retrieve-read)
-   - **Cookbook:** [rewrite](https://github.com/langchain-ai/langchain/blob/master/cookbook/rewrite.ipynb)
 
 **Abstract:** Large Language Models (LLMs) play powerful, black-box readers in the
 retrieve-then-read pipeline, making remarkable progress in knowledge-intensive
@@ -330,7 +152,6 @@ for retrieval-augmented LLM.
 - **LangChain:**
 
    - **API Reference:** [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)
 
 **Abstract:** In this paper, we introduce the Tree-of-Thought (ToT) framework, a novel
 approach aimed at improving the problem-solving capabilities of auto-regressive
@@ -350,132 +171,6 @@ significantly increase the success rate of Sudoku puzzle solving. Our
 implementation of the ToT-based Sudoku solver is available on GitHub:
 \url{https://github.com/jieyilong/tree-of-thought-puzzle-solver}.
                 
-## Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
-
-- **arXiv id:** 2305.04091v3
-- **Title:** Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
-- **Authors:** Lei Wang, Wanyu Xu, Yihuai Lan,  et al.
-- **Published Date:** 2023-05-06
-- **URL:** http://arxiv.org/abs/2305.04091v3
-- **LangChain:**
-
-   - **Cookbook:** [plan_and_execute_agent](https://github.com/langchain-ai/langchain/blob/master/cookbook/plan_and_execute_agent.ipynb)
-
-**Abstract:** Large language models (LLMs) have recently been shown to deliver impressive
-performance in various NLP tasks. To tackle multi-step reasoning tasks,
-few-shot chain-of-thought (CoT) prompting includes a few manually crafted
-step-by-step reasoning demonstrations which enable LLMs to explicitly generate
-reasoning steps and improve their reasoning task accuracy. To eliminate the
-manual effort, Zero-shot-CoT concatenates the target problem statement with
-"Let's think step by step" as an input prompt to LLMs. Despite the success of
-Zero-shot-CoT, it still suffers from three pitfalls: calculation errors,
-missing-step errors, and semantic misunderstanding errors. To address the
-missing-step errors, we propose Plan-and-Solve (PS) Prompting. It consists of
-two components: first, devising a plan to divide the entire task into smaller
-subtasks, and then carrying out the subtasks according to the plan. To address
-the calculation errors and improve the quality of generated reasoning steps, we
-extend PS prompting with more detailed instructions and derive PS+ prompting.
-We evaluate our proposed prompting strategy on ten datasets across three
-reasoning problems. The experimental results over GPT-3 show that our proposed
-zero-shot prompting consistently outperforms Zero-shot-CoT across all datasets
-by a large margin, is comparable to or exceeds Zero-shot-Program-of-Thought
-Prompting, and has comparable performance with 8-shot CoT prompting on the math
-reasoning problem. The code can be found at
-https://github.com/AGI-Edgerunners/Plan-and-Solve-Prompting.
-                
-## Visual Instruction Tuning
-
-- **arXiv id:** 2304.08485v2
-- **Title:** Visual Instruction Tuning
-- **Authors:** Haotian Liu, Chunyuan Li, Qingyang Wu,  et al.
-- **Published Date:** 2023-04-17
-- **URL:** http://arxiv.org/abs/2304.08485v2
-- **LangChain:**
-
-   - **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)
-
-**Abstract:** Instruction tuning large language models (LLMs) using machine-generated
-instruction-following data has improved zero-shot capabilities on new tasks,
-but the idea is less explored in the multimodal field. In this paper, we
-present the first attempt to use language-only GPT-4 to generate multimodal
-language-image instruction-following data. By instruction tuning on such
-generated data, we introduce LLaVA: Large Language and Vision Assistant, an
-end-to-end trained large multimodal model that connects a vision encoder and
-LLM for general-purpose visual and language understanding.Our early experiments
-show that LLaVA demonstrates impressive multimodel chat abilities, sometimes
-exhibiting the behaviors of multimodal GPT-4 on unseen images/instructions, and
-yields a 85.1% relative score compared with GPT-4 on a synthetic multimodal
-instruction-following dataset. When fine-tuned on Science QA, the synergy of
-LLaVA and GPT-4 achieves a new state-of-the-art accuracy of 92.53%. We make
-GPT-4 generated visual instruction tuning data, our model and code base
-publicly available.
-                
-## Generative Agents: Interactive Simulacra of Human Behavior
-
-- **arXiv id:** 2304.03442v2
-- **Title:** Generative Agents: Interactive Simulacra of Human Behavior
-- **Authors:** Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai,  et al.
-- **Published Date:** 2023-04-07
-- **URL:** http://arxiv.org/abs/2304.03442v2
-- **LangChain:**
-
-   - **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
-communication to prototyping tools. In this paper, we introduce generative
-agents--computational software agents that simulate believable human behavior.
-Generative agents wake up, cook breakfast, and head to work; artists paint,
-while authors write; they form opinions, notice each other, and initiate
-conversations; they remember and reflect on days past as they plan the next
-day. To enable generative agents, we describe an architecture that extends a
-large language model to store a complete record of the agent's experiences
-using natural language, synthesize those memories over time into higher-level
-reflections, and retrieve them dynamically to plan behavior. We instantiate
-generative agents to populate an interactive sandbox environment inspired by
-The Sims, where end users can interact with a small town of twenty five agents
-using natural language. In an evaluation, these generative agents produce
-believable individual and emergent social behaviors: for example, starting with
-only a single user-specified notion that one agent wants to throw a Valentine's
-Day party, the agents autonomously spread invitations to the party over the
-next two days, make new acquaintances, ask each other out on dates to the
-party, and coordinate to show up for the party together at the right time. We
-demonstrate through ablation that the components of our agent
-architecture--observation, planning, and reflection--each contribute critically
-to the believability of agent behavior. By fusing large language models with
-computational, interactive agents, this work introduces architectural and
-interaction patterns for enabling believable simulations of human behavior.
-                
-## CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
-
-- **arXiv id:** 2303.17760v2
-- **Title:** CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
-- **Authors:** Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani,  et al.
-- **Published Date:** 2023-03-31
-- **URL:** http://arxiv.org/abs/2303.17760v2
-- **LangChain:**
-
-   - **Cookbook:** [camel_role_playing](https://github.com/langchain-ai/langchain/blob/master/cookbook/camel_role_playing.ipynb)
-
-**Abstract:** The rapid advancement of chat-based language models has led to remarkable
-progress in complex task-solving. However, their success heavily relies on
-human input to guide the conversation, which can be challenging and
-time-consuming. This paper explores the potential of building scalable
-techniques to facilitate autonomous cooperation among communicative agents, and
-provides insight into their "cognitive" processes. To address the challenges of
-achieving autonomous cooperation, we propose a novel communicative agent
-framework named role-playing. Our approach involves using inception prompting
-to guide chat agents toward task completion while maintaining consistency with
-human intentions. We showcase how role-playing can be used to generate
-conversational data for studying the behaviors and capabilities of a society of
-agents, providing a valuable resource for investigating conversational language
-models. In particular, we conduct comprehensive studies on
-instruction-following cooperation in multi-agent settings. Our contributions
-include introducing a novel communicative agent framework, offering a scalable
-approach for studying the cooperative behaviors and capabilities of multi-agent
-systems, and open-sourcing our library to support research on communicative
-agents and beyond: https://github.com/camel-ai/camel.
-                
 ## HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
 
 - **arXiv id:** 2303.17580v4
@@ -486,7 +181,6 @@ agents and beyond: https://github.com/camel-ai/camel.
 - **LangChain:**
 
    - **API Reference:** [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)
 
 **Abstract:** Solving complicated AI tasks with different domains and modalities is a key
 step toward artificial general intelligence. While there are numerous AI models
@@ -541,7 +235,7 @@ more than 1/1,000th the compute of GPT-4.
 - **URL:** http://arxiv.org/abs/2301.10226v4
 - **LangChain:**
 
-   - **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)
+   - **API Reference:** [langchain_community.llms...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.llms...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.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint)
 
 **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
@@ -566,9 +260,8 @@ family, and discuss robustness and security.
 - **URL:** http://arxiv.org/abs/2212.10496v1
 - **LangChain:**
 
-   - **API Reference:** [langchain...HypotheticalDocumentEmbedder](https://api.python.langchain.com/en/latest/chains/langchain.chains.hyde.base.HypotheticalDocumentEmbedder.html#langchain.chains.hyde.base.HypotheticalDocumentEmbedder)
+   - **API Reference:** [langchain.chains...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)
 
 **Abstract:** While dense retrieval has been shown effective and efficient across tasks and
 languages, it remains difficult to create effective fully zero-shot dense
@@ -630,7 +323,7 @@ further work on logical fallacy identification.
 - **URL:** http://arxiv.org/abs/2211.13892v2
 - **LangChain:**
 
-   - **API Reference:** [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)
+   - **API Reference:** [langchain_core.example_selectors...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)
 
 **Abstract:** Large language models (LLMs) have exhibited remarkable capabilities in
 learning from explanations in prompts, but there has been limited understanding
@@ -658,8 +351,7 @@ performance across three real-world tasks on multiple LLMs.
 - **URL:** http://arxiv.org/abs/2211.10435v2
 - **LangChain:**
 
-   - **API Reference:** [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)
+   - **API Reference:** [langchain_experimental.pal_chain...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)
 
 **Abstract:** Large language models (LLMs) have recently demonstrated an impressive ability
 to perform arithmetic and symbolic reasoning tasks, when provided with a few
@@ -684,41 +376,6 @@ 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
@@ -756,7 +413,7 @@ TensorFlow, JAX, and integrate with numerous MLOps tools.
 - **URL:** http://arxiv.org/abs/2205.12654v1
 - **LangChain:**
 
-   - **API Reference:** [langchain_community...LaserEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain_community.embeddings.laser.LaserEmbeddings.html#langchain_community.embeddings.laser.LaserEmbeddings)
+   - **API Reference:** [langchain_community.embeddings...LaserEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain_community.embeddings.laser.LaserEmbeddings.html#langchain_community.embeddings.laser.LaserEmbeddings)
 
 **Abstract:** Scaling multilingual representation learning beyond the hundred most frequent
 languages is challenging, in particular to cover the long tail of low-resource
@@ -785,7 +442,7 @@ encoders, mine bitexts, and validate the bitexts by training NMT systems.
 - **URL:** http://arxiv.org/abs/2204.00498v1
 - **LangChain:**
 
-   - **API Reference:** [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)
+   - **API Reference:** [langchain_community.utilities...SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), [langchain_community.utilities...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL)
 
 **Abstract:** We perform an empirical evaluation of Text-to-SQL capabilities of the Codex
 language model. We find that, without any finetuning, Codex is a strong
@@ -804,7 +461,7 @@ few-shot examples.
 - **URL:** http://arxiv.org/abs/2202.00666v5
 - **LangChain:**
 
-   - **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)
+   - **API Reference:** [langchain_community.llms...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.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint)
 
 **Abstract:** Today's probabilistic language generators fall short when it comes to
 producing coherent and fluent text despite the fact that the underlying models
@@ -868,7 +525,7 @@ https://github.com/OpenAI/CLIP.
 - **URL:** http://arxiv.org/abs/1909.05858v2
 - **LangChain:**
 
-   - **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)
+   - **API Reference:** [langchain_community.llms...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.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint)
 
 **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

@@ -11,7 +11,6 @@
 ### [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
 
@@ -46,6 +45,7 @@
 - [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/contributing/code.mdx

@@ -1,9 +1,36 @@
-# Setup
+---
+sidebar_position: 1
+---
+# Contribute Code
 
-This guide walks through how to run the repository locally and check in your first code.
+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.
 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.
 
@@ -14,7 +41,7 @@ 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).
@@ -32,7 +59,7 @@ 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):
 
@@ -52,9 +79,9 @@ 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
 
-**Note:** In `langchain`, `langchain-community`, and `langchain-experimental`, some test dependencies are optional. See the following section about optional dependencies.
+_In `langchain`, `langchain-community`, and `langchain-experimental`, some test dependencies are optional; see 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.
@@ -91,11 +118,11 @@ 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/).
 
@@ -147,7 +174,7 @@ 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.
@@ -179,7 +206,9 @@ ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogy
 
 `langchain-core` and partner packages **do not use** optional dependencies in this way.
 
-You'll notice that `pyproject.toml` and `poetry.lock` are **not** touched when you add optional dependencies below.
+You only need to add a new dependency if a **unit test** relies on the package.
+If your package is only required for **integration tests**, then you can skip these
+steps and leave all pyproject.toml and poetry.lock files alone.
 
 If you're adding a new dependency to Langchain, assume that it will be an optional dependency, and
 that most users won't have it installed.
@@ -187,12 +216,20 @@ that most users won't have it installed.
 Users who do not have the dependency installed should be able to **import** your code without
 any side effects (no warnings, no errors, no exceptions).
 
-To introduce the dependency to a library, please do the following:
+To introduce the dependency to the pyproject.toml file correctly, please do the following:
 
-1. Open extended_testing_deps.txt and add the dependency
-2. Add a unit test that the very least attempts to import the new code. Ideally, the unit
+1. Add the dependency to the main group as an optional dependency
+  ```bash
+  poetry add --optional [package_name]
+  ```
+2. Open pyproject.toml and add the dependency to the `extended_testing` extra
+3. Relock the poetry file to update the extra.
+  ```bash
+  poetry lock --no-update
+  ```
+4. Add a unit test that the very least attempts to import the new code. Ideally, the unit
 test makes use of lightweight fixtures to test the logic of the code.
-3. Please use the `@pytest.mark.requires(package_name)` decorator for any unit tests that require the dependency.
+5. Please use the `@pytest.mark.requires(package_name)` decorator for any tests that require the dependency.
 
 ## Adding a Jupyter Notebook
 

docs/docs/contributing/code/guidelines.mdx

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

@@ -1,6 +0,0 @@
-# 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/documentation/_category_.yml

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

docs/docs/contributing/documentation/index.mdx

@@ -1,7 +0,0 @@
-# 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/style_guide.mdx

@@ -1,8 +1,10 @@
 ---
-sidebar_class_name: "hidden"
+sidebar_label: "Style guide"
 ---
 
-# Documentation Style Guide
+# LangChain Documentation Style Guide
+
+## Introduction
 
 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
@@ -10,139 +12,116 @@ organization and structure.
 
 ## Philosophy
 
-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).
+LangChain's documentation aspires to follow the [Diataxis framework](https://diataxis.fr).
+Under this framework, all documentation falls under one of four categories:
 
-### 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.
+- **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.
 
 Each category serves a distinct purpose and requires a specific approach to writing and structuring the content.
 
-## General guidelines
+## 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
 
 Here are some other guidelines you should think about when writing and organizing documentation.
 
-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
+### Linking 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!
 
-### Be concise
+### Conciseness
 
 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.
@@ -151,10 +130,9 @@ 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 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
+- 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.

docs/docs/contributing/documentation/technical_logistics.mdx

@@ -1,8 +1,4 @@
----
-sidebar_class_name: "hidden"
----
-
-# Setup
+# Technical logistics
 
 LangChain documentation consists of two components:
 
@@ -16,6 +12,8 @@ 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/).
 
@@ -31,7 +29,7 @@ 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
-and then built using [Docusaurus 2](https://docusaurus.io/).
+using [Quarto](https://quarto.org) and then built using [Docusaurus 2](https://docusaurus.io/).
 
 Feel free to make contributions to the main documentation! 🥰
 
@@ -50,6 +48,10 @@ 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
@@ -69,6 +71,8 @@ make docs_clean
 make api_docs_clean
 ```
 
+
+
 Next, you can build the documentation as outlined below:
 
 ```bash

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/): Help improve our docs, including this one!
-- [**Code**](/docs/contributing/code/): Help us write code, fix bugs, or improve our infrastructure.
+- [**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.
 - [**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

@@ -1,7 +1,6 @@
 ---
 sidebar_position: 5
 ---
-
 # Contribute Integrations
 
 To begin, make sure you have all the dependencies outlined in guide on [Contributing Code](/docs/contributing/code/).
@@ -11,7 +10,7 @@ There are a few different places you can contribute integrations for LangChain:
 - **Community**: For lighter-weight integrations that are primarily maintained by LangChain and the Open Source Community.
 - **Partner Packages**: For independent packages that are co-maintained by LangChain and a partner.
 
-For the most part, **new integrations should be added to the Community package**. Partner packages require more maintenance as separate packages, so please confirm with the LangChain team before creating a new partner package.
+For the most part, new integrations should be added to the Community package. Partner packages require more maintenance as separate packages, so please confirm with the LangChain team before creating a new partner package.
 
 In the following sections, we'll walk through how to contribute to each of these packages from a fake company, `Parrot Link AI`.
 
@@ -60,10 +59,6 @@ And add documentation to:
 
 ## Partner package in LangChain repo
 
-:::caution
-Before starting a **partner** package, please confirm your intent with the LangChain team. Partner packages require more maintenance as separate packages, so we will close PRs that add new partner packages without prior discussion. See the above section for how to add a community integration.
-:::
-
 Partner packages can be hosted in the `LangChain` monorepo or in an external repo.
 
 Partner package in the `LangChain` repo is placed in `libs/partners/{partner}` 

docs/docs/contributing/repo_structure.mdx

@@ -7,7 +7,6 @@ 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:
 
@@ -16,22 +15,12 @@ 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
-│   │   ├── langchain
+│   ├── langchain # Main package
 │   │   ├── 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)
-│   ├── 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
+│   ├── langchain-community # Third-party integrations
+│   ├── langchain-core # Base interfaces for key abstractions
+│   ├── langchain-experimental # Experimental components and chains
 │   ├── partners
 │       ├── langchain-partner-1
 │       ├── langchain-partner-2
@@ -52,7 +41,7 @@ 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/) guidelines to learn how to contribute to the documentation.
+See the [documentation](/docs/contributing/documentation/style_guide) guidelines to learn how to contribute to the documentation.
 
 ## Code
 
@@ -60,6 +49,6 @@ The `/libs` directory contains the code for the LangChain packages.
 
 To learn more about how to contribute code see the following guidelines:
 
-- [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.
+- [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.

docs/docs/contributing/testing.mdx

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 6
+sidebar_position: 2
 ---
 
 # 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 list(filter(None, lines))  # Remove empty lines\n",
+    "        return lines\n",
     "\n",
     "\n",
     "output_parser = LineListOutputParser()\n",

docs/docs/how_to/agent_executor.ipynb

@@ -15,18 +15,18 @@
    "id": "f4c03f40-1328-412d-8a48-1db0cd481b77",
    "metadata": {},
    "source": [
-    "# Build an Agent with AgentExecutor (Legacy)\n",
-    "\n",
-    ":::{.callout-important}\n",
-    "This section will cover building with the legacy LangChain AgentExecutor. These are fine for getting started, but past a certain point, you will likely want flexibility and control that they do not offer. For working with more advanced agents, we'd recommend checking out [LangGraph Agents](/docs/concepts/#langgraph) or the [migration guide](/docs/how_to/migrate_agent/)\n",
-    ":::\n",
+    "# Build an Agent\n",
     "\n",
     "By themselves, language models can't take actions - they just output text.\n",
     "A big use case for LangChain is creating **agents**.\n",
-    "Agents are systems that use an LLM as a reasoning engine to determine which actions to take and what the inputs to those actions should be.\n",
-    "The results of those actions can then be fed back into the agent and it determines whether more actions are needed, or whether it is okay to finish.\n",
+    "Agents are systems that use an LLM as a reasoning enginer to determine which actions to take and what the inputs to those actions should be.\n",
+    "The results of those actions can then be fed back into the agent and it determine whether more actions are needed, or whether it is okay to finish.\n",
     "\n",
-    "In this tutorial, we will build an agent that can interact with multiple different tools: one being a local database, the other being a search engine. You will be able to ask this agent questions, watch it call tools, and have conversations with it.\n",
+    "In this tutorial we will build an agent that can interact with multiple different tools: one being a local database, the other being a search engine. You will be able to ask this agent questions, watch it call tools, and have conversations with it.\n",
+    "\n",
+    ":::{.callout-important}\n",
+    "This section will cover building with LangChain Agents. LangChain Agents are fine for getting started, but past a certain point you will likely want flexibility and control that they do not offer. For working with more advanced agents, we'd reccommend checking out [LangGraph](/docs/concepts/#langgraph)\n",
+    ":::\n",
     "\n",
     "## Concepts\n",
     "\n",
@@ -34,7 +34,7 @@
     "- Using [language models](/docs/concepts/#chat-models), in particular their tool calling ability\n",
     "- Creating a [Retriever](/docs/concepts/#retrievers) to expose specific information to our agent\n",
     "- Using a Search [Tool](/docs/concepts/#tools) to look up things online\n",
-    "- [`Chat History`](/docs/concepts/#chat-history), which allows a chatbot to \"remember\" past interactions and take them into account when responding to follow-up questions. \n",
+    "- [`Chat History`](/docs/concepts/#chat-history), which allows a chatbot to \"remember\" past interactions and take them into account when responding to followup questions. \n",
     "- Debugging and tracing your application using [LangSmith](/docs/concepts/#langsmith)\n",
     "\n",
     "## Setup\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

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

docs/docs/how_to/character_text_splitter.ipynb

@@ -1,19 +1,5 @@
 {
  "cells": [
-  {
-   "cell_type": "raw",
-   "id": "f781411d",
-   "metadata": {
-    "vscode": {
-     "languageId": "raw"
-    }
-   },
-   "source": [
-    "---\n",
-    "keywords: [charactertextsplitter]\n",
-    "---"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "c3ee8d00",

docs/docs/how_to/chat_model_rate_limiting.ipynb

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

docs/docs/how_to/chat_models_universal_init.ipynb

@@ -1,340 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "cfdf4f09-8125-4ed1-8063-6feed57da8a3",
-   "metadata": {},
-   "source": [
-    "# 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",
-    ":::tip Supported models\n",
-    "\n",
-    "See the [init_chat_model()](https://api.python.langchain.com/en/latest/chat_models/langchain.chat_models.base.init_chat_model.html) API reference for a full list of supported integrations.\n",
-    "\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",
-    ":::"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "165b0de6-9ae3-4e3d-aa98-4fc8a97c4a06",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain>=0.2.8 langchain-openai langchain-anthropic langchain-google-vertexai"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ea2c9f57-a796-45f8-b6f4-3efd3f361a9b",
-   "metadata": {},
-   "source": [
-    "## Basic usage"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "79e14913-803c-4382-9009-5c6af3d75d35",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "GPT-4o: I'm an AI created by OpenAI, and I don't have a personal name. You can call me Assistant! How can I help you today?\n",
-      "\n",
-      "Claude Opus: My name is Claude. It's nice to meet you!\n",
-      "\n",
-      "Gemini 1.5: I am a large language model, trained by Google. I do not have a name. \n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain.chat_models import init_chat_model\n",
-    "\n",
-    "# Returns a langchain_openai.ChatOpenAI instance.\n",
-    "gpt_4o = init_chat_model(\"gpt-4o\", model_provider=\"openai\", temperature=0)\n",
-    "# Returns a langchain_anthropic.ChatAnthropic instance.\n",
-    "claude_opus = init_chat_model(\n",
-    "    \"claude-3-opus-20240229\", model_provider=\"anthropic\", temperature=0\n",
-    ")\n",
-    "# Returns a langchain_google_vertexai.ChatVertexAI instance.\n",
-    "gemini_15 = init_chat_model(\n",
-    "    \"gemini-1.5-pro\", model_provider=\"google_vertexai\", temperature=0\n",
-    ")\n",
-    "\n",
-    "# Since all model integrations implement the ChatModel interface, you can use them in the same way.\n",
-    "print(\"GPT-4o: \" + gpt_4o.invoke(\"what's your name\").content + \"\\n\")\n",
-    "print(\"Claude Opus: \" + claude_opus.invoke(\"what's your name\").content + \"\\n\")\n",
-    "print(\"Gemini 1.5: \" + gemini_15.invoke(\"what's your name\").content + \"\\n\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f811f219-5e78-4b62-b495-915d52a22532",
-   "metadata": {},
-   "source": [
-    "## Inferring model provider\n",
-    "\n",
-    "For common and distinct model names `init_chat_model()` will attempt to infer the model provider. See the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain.chat_models.base.init_chat_model.html) for a full list of inference behavior. E.g. any model that starts with `gpt-3...` or `gpt-4...` will be inferred as using model provider `openai`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "0378ccc6-95bc-4d50-be50-fccc193f0a71",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "gpt_4o = init_chat_model(\"gpt-4o\", temperature=0)\n",
-    "claude_opus = init_chat_model(\"claude-3-opus-20240229\", temperature=0)\n",
-    "gemini_15 = init_chat_model(\"gemini-1.5-pro\", temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "476a44db-c50d-4846-951d-0f1c9ba8bbaa",
-   "metadata": {},
-   "source": [
-    "## Creating a configurable model\n",
-    "\n",
-    "You can also create a runtime-configurable model by specifying `configurable_fields`. If you don't specify a `model` value, then \"model\" and \"model_provider\" be configurable by default."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "6c037f27-12d7-4e83-811e-4245c0e3ba58",
-   "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": {
-  "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": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/how_to/chat_token_usage_tracking.ipynb

@@ -14,51 +14,35 @@
     "\n",
     ":::\n",
     "\n",
-    "Tracking token usage to calculate cost is an important part of putting your app in production. This guide goes over how to obtain this information from your LangChain model calls.\n",
-    "\n",
-    "This guide requires `langchain-openai >= 0.1.9`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "9c7d1338-dd1b-4d06-b33d-d5cffc49fd6a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install --upgrade --quiet langchain langchain-openai"
+    "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."
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "598ae1e2-a52d-4459-81fd-cdc68b06742a",
+   "id": "1a55e87a-3291-4e7f-8e8e-4c69b0854384",
    "metadata": {},
    "source": [
-    "## Using LangSmith\n",
+    "## Using AIMessage.response_metadata\n",
     "\n",
-    "You can use [LangSmith](https://www.langchain.com/langsmith) to help track token usage in your LLM application. See the [LangSmith quick start guide](https://docs.smith.langchain.com/).\n",
-    "\n",
-    "## Using AIMessage.usage_metadata\n",
-    "\n",
-    "A number of model providers return token usage information as part of the chat generation response. When available, this information will be included on the `AIMessage` objects produced by the corresponding model.\n",
-    "\n",
-    "LangChain `AIMessage` objects include a [usage_metadata](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessage.html#langchain_core.messages.ai.AIMessage.usage_metadata) attribute. When populated, this attribute will be a [UsageMetadata](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.UsageMetadata.html) dictionary with standard keys (e.g., `\"input_tokens\"` and `\"output_tokens\"`).\n",
-    "\n",
-    "Examples:\n",
-    "\n",
-    "**OpenAI**:"
+    "A number of model providers return token usage information as part of the chat generation response. When available, this is included in the [`AIMessage.response_metadata`](/docs/how_to/response_metadata) field. Here's an example with OpenAI:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "b39bf807-4125-4db4-bbf7-28a46afff6b4",
+   "id": "467ccdeb-6b62-45e5-816e-167cd24d2586",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}"
+       "{'token_usage': {'completion_tokens': 225,\n",
+       "  'prompt_tokens': 17,\n",
+       "  'total_tokens': 242},\n",
+       " 'model_name': 'gpt-4-turbo',\n",
+       " 'system_fingerprint': 'fp_76f018034d',\n",
+       " 'finish_reason': 'stop',\n",
+       " 'logprobs': None}"
       ]
      },
      "execution_count": 1,
@@ -67,33 +51,37 @@
     }
    ],
    "source": [
-    "# # !pip install -qU langchain-openai\n",
+    "# !pip install -qU langchain-openai\n",
     "\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
-    "openai_response = llm.invoke(\"hello\")\n",
-    "openai_response.usage_metadata"
+    "llm = ChatOpenAI(model=\"gpt-4-turbo\")\n",
+    "msg = llm.invoke([(\"human\", \"What's the oldest known example of cuneiform\")])\n",
+    "msg.response_metadata"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "2299c44a-2fe6-4d52-a6a2-99ff6d231c73",
+   "id": "9d5026e9-3ad4-41e6-9946-9f1a26f4a21f",
    "metadata": {},
    "source": [
-    "**Anthropic**:"
+    "And here's an example with Anthropic:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "9c82ff80-ec4e-4049-b019-5f0bbd7df82a",
+   "id": "145404f1-e088-4824-b468-236c486a9903",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'input_tokens': 8, 'output_tokens': 12, 'total_tokens': 20}"
+       "{'id': 'msg_01P61rdHbapEo6h3fjpfpCQT',\n",
+       " 'model': 'claude-3-sonnet-20240229',\n",
+       " 'stop_reason': 'end_turn',\n",
+       " 'stop_sequence': None,\n",
+       " 'usage': {'input_tokens': 17, 'output_tokens': 306}}"
       ]
      },
      "execution_count": 2,
@@ -106,222 +94,9 @@
     "\n",
     "from langchain_anthropic import ChatAnthropic\n",
     "\n",
-    "llm = ChatAnthropic(model=\"claude-3-haiku-20240307\")\n",
-    "anthropic_response = llm.invoke(\"hello\")\n",
-    "anthropic_response.usage_metadata"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6d4efc15-ba9f-4b3d-9278-8e01f99f263f",
-   "metadata": {},
-   "source": [
-    "### Using AIMessage.response_metadata\n",
-    "\n",
-    "Metadata from the model response is also included in the AIMessage [response_metadata](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessage.html#langchain_core.messages.ai.AIMessage.response_metadata) attribute. These data are typically not standardized. Note that different providers adopt different conventions for representing token counts:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "f156f9da-21f2-4c81-a714-54cbf9ad393e",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "OpenAI: {'completion_tokens': 9, 'prompt_tokens': 8, 'total_tokens': 17}\n",
-      "\n",
-      "Anthropic: {'input_tokens': 8, 'output_tokens': 12}\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(f'OpenAI: {openai_response.response_metadata[\"token_usage\"]}\\n')\n",
-    "print(f'Anthropic: {anthropic_response.response_metadata[\"usage\"]}')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b4ef2c43-0ff6-49eb-9782-e4070c9da8d7",
-   "metadata": {},
-   "source": [
-    "### Streaming\n",
-    "\n",
-    "Some providers support token count metadata in a streaming context.\n",
-    "\n",
-    "#### OpenAI\n",
-    "\n",
-    "For example, OpenAI will return a message [chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html) at the end of a stream with token usage information. This behavior is supported by `langchain-openai >= 0.1.9` and can be enabled by setting `stream_usage=True`. This attribute can also be set when `ChatOpenAI` is instantiated.\n",
-    "\n",
-    "```{=mdx}\n",
-    ":::note\n",
-    "By default, the last message chunk in a stream will include a `\"finish_reason\"` in the message's `response_metadata` attribute. If we include token usage in streaming mode, an additional chunk containing usage metadata will be added to the end of the stream, such that `\"finish_reason\"` appears on the second to last message chunk.\n",
-    ":::\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "07f0c872-6b6c-4fed-a129-9b5a858505be",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content='' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content='Hello' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content='!' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' How' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' can' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' I' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' assist' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' you' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content=' today' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content='?' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content='' response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-3.5-turbo-0125'} id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
-      "content='' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}\n"
-     ]
-    }
-   ],
-   "source": [
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
-    "\n",
-    "aggregate = None\n",
-    "for chunk in llm.stream(\"hello\", stream_usage=True):\n",
-    "    print(chunk)\n",
-    "    aggregate = chunk if aggregate is None else aggregate + chunk"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "dd809ded-8b13-4d5f-be5e-277b79d51802",
-   "metadata": {},
-   "source": [
-    "Note that the usage metadata will be included in the sum of the individual message chunks:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "3db7bc03-a7d4-4704-92ab-f8ba92ef59ae",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Hello! How can I assist you today?\n",
-      "{'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(aggregate.content)\n",
-    "print(aggregate.usage_metadata)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7dba63e8-0ed7-4533-8f0f-78e19c38a25c",
-   "metadata": {},
-   "source": [
-    "To disable streaming token counts for OpenAI, set `stream_usage` to False, or omit it from the parameters:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "67117f2b-ce68-4c1e-9556-2d3849f90e1b",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content='' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content='Hello' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content='!' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' How' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' can' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' I' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' assist' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' you' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content=' today' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content='?' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
-      "content='' response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-3.5-turbo-0125'} id='run-8e758550-94b0-4cca-a298-57482793c25d'\n"
-     ]
-    }
-   ],
-   "source": [
-    "aggregate = None\n",
-    "for chunk in llm.stream(\"hello\"):\n",
-    "    print(chunk)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6a5d9617-be3a-419a-9276-de9c29fa50ae",
-   "metadata": {},
-   "source": [
-    "You can also enable streaming token usage by setting `stream_usage` when instantiating the chat model. This can be useful when incorporating chat models into LangChain [chains](/docs/concepts#langchain-expression-language-lcel): usage metadata can be monitored when [streaming intermediate steps](/docs/how_to/streaming#using-stream-events) or using tracing software such as [LangSmith](https://docs.smith.langchain.com/).\n",
-    "\n",
-    "See the below example, where we return output structured to a desired schema, but can still observe token usage streamed from intermediate steps."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "0b1523d8-127e-4314-82fa-bd97aca37f9a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Token usage: {'input_tokens': 79, 'output_tokens': 23, 'total_tokens': 102}\n",
-      "\n",
-      "setup='Why was the math book sad?' punchline='Because it had too many problems.'\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "\n",
-    "class Joke(BaseModel):\n",
-    "    \"\"\"Joke to tell user.\"\"\"\n",
-    "\n",
-    "    setup: str = Field(description=\"question to set up a joke\")\n",
-    "    punchline: str = Field(description=\"answer to resolve the joke\")\n",
-    "\n",
-    "\n",
-    "llm = ChatOpenAI(\n",
-    "    model=\"gpt-3.5-turbo-0125\",\n",
-    "    stream_usage=True,\n",
-    ")\n",
-    "# Under the hood, .with_structured_output binds tools to the\n",
-    "# chat model and appends a parser.\n",
-    "structured_llm = llm.with_structured_output(Joke)\n",
-    "\n",
-    "async for event in structured_llm.astream_events(\"Tell me a joke\", version=\"v2\"):\n",
-    "    if event[\"event\"] == \"on_chat_model_end\":\n",
-    "        print(f'Token usage: {event[\"data\"][\"output\"].usage_metadata}\\n')\n",
-    "    elif event[\"event\"] == \"on_chain_end\":\n",
-    "        print(event[\"data\"][\"output\"])\n",
-    "    else:\n",
-    "        pass"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2bc8d313-4bef-463e-89a5-236d8bb6ab2f",
-   "metadata": {},
-   "source": [
-    "Token usage is also visible in the corresponding [LangSmith trace](https://smith.langchain.com/public/fe6513d5-7212-4045-82e0-fefa28bc7656/r) in the payload from the chat model."
+    "llm = ChatAnthropic(model=\"claude-3-sonnet-20240229\")\n",
+    "msg = llm.invoke([(\"human\", \"What's the oldest known example of cuneiform\")])\n",
+    "msg.response_metadata"
    ]
   },
   {
@@ -340,19 +115,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "b04a4486-72fd-48ce-8f9e-5d281b441195",
+   "execution_count": 5,
+   "id": "31667d54",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Tokens Used: 27\n",
+      "Tokens Used: 26\n",
       "\tPrompt Tokens: 11\n",
-      "\tCompletion Tokens: 16\n",
+      "\tCompletion Tokens: 15\n",
       "Successful Requests: 1\n",
-      "Total Cost (USD): $2.95e-05\n"
+      "Total Cost (USD): $0.00056\n"
      ]
     }
    ],
@@ -361,11 +136,7 @@
     "\n",
     "from langchain_community.callbacks.manager import get_openai_callback\n",
     "\n",
-    "llm = ChatOpenAI(\n",
-    "    model=\"gpt-3.5-turbo-0125\",\n",
-    "    temperature=0,\n",
-    "    stream_usage=True,\n",
-    ")\n",
+    "llm = ChatOpenAI(model=\"gpt-4-turbo\", temperature=0)\n",
     "\n",
     "with get_openai_callback() as cb:\n",
     "    result = llm.invoke(\"Tell me a joke\")\n",
@@ -382,15 +153,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
-   "id": "05f22a1d-b021-490f-8840-f628a07459f2",
+   "execution_count": 6,
+   "id": "e09420f4",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "54\n"
+      "52\n"
      ]
     }
    ],
@@ -401,31 +172,6 @@
     "    print(cb.total_tokens)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "c00c9158-7bb4-4279-88e6-ea70f46e6ac2",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Tokens Used: 27\n",
-      "\tPrompt Tokens: 11\n",
-      "\tCompletion Tokens: 16\n",
-      "Successful Requests: 1\n",
-      "Total Cost (USD): $2.95e-05\n"
-     ]
-    }
-   ],
-   "source": [
-    "with get_openai_callback() as cb:\n",
-    "    for chunk in llm.stream(\"Tell me a joke\"):\n",
-    "        pass\n",
-    "    print(cb)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "d8186e7b",
@@ -436,7 +182,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 17,
    "id": "5d1125c6",
    "metadata": {},
    "outputs": [],
@@ -453,13 +199,27 @@
     ")\n",
     "tools = load_tools([\"wikipedia\"])\n",
     "agent = create_tool_calling_agent(llm, tools, prompt)\n",
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
+    "agent_executor = AgentExecutor(\n",
+    "    agent=agent, tools=tools, verbose=True, stream_runnable=False\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9c1ae74d-8300-4041-9ff4-66093ee592b1",
+   "metadata": {},
+   "source": [
+    "```{=mdx}\n",
+    ":::note\n",
+    "We have to set `stream_runnable=False` for token counting to work. 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. However, OpenAI does not return token counts when streaming model responses, so we need to turn off the underlying streaming.\n",
+    ":::\n",
+    "```"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
-   "id": "3950d88b-8bfb-4294-b75b-e6fd421e633c",
+   "execution_count": 18,
+   "id": "2f98c536",
    "metadata": {},
    "outputs": [
     {
@@ -470,45 +230,46 @@
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
       "\u001b[32;1m\u001b[1;3m\n",
-      "Invoking: `wikipedia` with `{'query': 'hummingbird scientific name'}`\n",
+      "Invoking: `wikipedia` with `Hummingbird`\n",
       "\n",
       "\n",
       "\u001b[0m\u001b[36;1m\u001b[1;3mPage: Hummingbird\n",
-      "Summary: Hummingbirds are birds native to the Americas and comprise the biological family Trochilidae. With approximately 366 species and 113 genera, they occur from Alaska to Tierra del Fuego, but most species are found in Central and South America. As of 2024, 21 hummingbird species are listed as endangered or critically endangered, with numerous species declining in population.\n",
-      "Hummingbirds have varied specialized characteristics to enable rapid, maneuverable flight: exceptional metabolic capacity, adaptations to high altitude, sensitive visual and communication abilities, and long-distance migration in some species. Among all birds, male hummingbirds have the widest diversity of plumage color, particularly in blues, greens, and purples. Hummingbirds are the smallest mature birds, measuring 7.5–13 cm (3–5 in) in length. The smallest is the 5 cm (2.0 in) bee hummingbird, which weighs less than 2.0 g (0.07 oz), and the largest is the 23 cm (9 in) giant hummingbird, weighing 18–24 grams (0.63–0.85 oz). Noted for long beaks, hummingbirds are specialized for feeding on flower nectar, but all species also consume small insects.\n",
+      "Summary: Hummingbirds are birds native to the Americas and comprise the biological family Trochilidae. With approximately 366 species and 113 genera, they occur from Alaska to Tierra del Fuego, but most species are found in Central and South America. As of 2024, 21 hummingbird species are listed as endangered or critically endangered, with numerous species declining in population.Hummingbirds have varied specialized characteristics to enable rapid, maneuverable flight: exceptional metabolic capacity, adaptations to high altitude, sensitive visual and communication abilities, and long-distance migration in some species. Among all birds, male hummingbirds have the widest diversity of plumage color, particularly in blues, greens, and purples. Hummingbirds are the smallest mature birds, measuring 7.5–13 cm (3–5 in) in length. The smallest is the 5 cm (2.0 in) bee hummingbird, which weighs less than 2.0 g (0.07 oz), and the largest is the 23 cm (9 in) giant hummingbird, weighing 18–24 grams (0.63–0.85 oz). Noted for long beaks, hummingbirds are specialized for feeding on flower nectar, but all species also consume small insects.\n",
       "They are known as hummingbirds because of the humming sound created by their beating wings, which flap at high frequencies audible to other birds and humans. They hover at rapid wing-flapping rates, which vary from around 12 beats per second in the largest species to 80 per second in small hummingbirds.\n",
       "Hummingbirds have the highest mass-specific metabolic rate of any homeothermic animal. To conserve energy when food is scarce and at night when not foraging, they can enter torpor, a state similar to hibernation, and slow their metabolic rate to 1⁄15 of its normal rate. While most hummingbirds do not migrate, the rufous hummingbird has one of the longest migrations among birds, traveling twice per year between Alaska and Mexico, a distance of about 3,900 miles (6,300 km).\n",
       "Hummingbirds split from their sister group, the swifts and treeswifts, around 42 million years ago. The oldest known fossil hummingbird is Eurotrochilus, from the Rupelian Stage of Early Oligocene Europe.\n",
       "\n",
-      "Page: Rufous hummingbird\n",
-      "Summary: The rufous hummingbird (Selasphorus rufus) is a small hummingbird, about 8 cm (3.1 in) long with a long, straight and slender bill. These birds are known for their extraordinary flight skills, flying 2,000 mi (3,200 km) during their migratory transits. It is one of nine species in the genus Selasphorus.\n",
       "\n",
       "\n",
+      "Page: Bee hummingbird\n",
+      "Summary: The bee hummingbird, zunzuncito or Helena hummingbird (Mellisuga helenae) is a species of hummingbird, native to the island of Cuba in the Caribbean. It is the smallest known bird. The bee hummingbird feeds on nectar of flowers and bugs found in Cuba.\n",
       "\n",
-      "Page: Allen's hummingbird\n",
-      "Summary: Allen's hummingbird (Selasphorus sasin) is a species of hummingbird that breeds in the western United States. It is one of seven species in the genus Selasphorus.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
-      "Invoking: `wikipedia` with `{'query': 'fastest bird species'}`\n",
+      "Page: Hummingbird cake\n",
+      "Summary: Hummingbird cake is a banana-pineapple spice cake originating in Jamaica and a popular dessert in the southern United States since the 1970s. Ingredients include flour, sugar, salt, vegetable oil, ripe banana, pineapple, cinnamon, pecans, vanilla extract, eggs, and leavening agent. It is often served with cream cheese frosting.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
+      "Invoking: `wikipedia` with `Fastest bird`\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",
-      "Page: Fastest animals\n",
+      "\u001b[0m\u001b[36;1m\u001b[1;3mPage: Fastest animals\n",
       "Summary: This is a list of the fastest animals in the world, by types of animal.\n",
       "\n",
-      "Page: Falcon\n",
-      "Summary: Falcons () are birds of prey in the genus Falco, which includes about 40 species. Falcons are widely distributed on all continents of the world except Antarctica, though closely related raptors did occur there in the Eocene.\n",
-      "Adult falcons have thin, tapered wings, which enable them to fly at high speed and change direction rapidly. Fledgling falcons, in their first year of flying, have longer flight feathers, which make their configuration more like that of a general-purpose bird such as a broad wing. This makes flying easier while learning the exceptional skills required to be effective hunters as adults.\n",
-      "The falcons are the largest genus in the Falconinae subfamily of Falconidae, which itself also includes another subfamily comprising caracaras and a few other species. All these birds kill with their beaks, using a tomial \"tooth\" on the side of their beaks—unlike the hawks, eagles, and other birds of prey in the Accipitridae, which use their feet.\n",
-      "The largest falcon is the gyrfalcon at up to 65 cm in length.  The smallest falcon species is the pygmy falcon, which measures just 20 cm.  As with hawks and owls, falcons exhibit sexual dimorphism, with the females typically larger than the males, thus allowing a wider range of prey species.\n",
-      "Some small falcons with long, narrow wings are called \"hobbies\" and some which hover while hunting are called \"kestrels\".\n",
-      "As is the case with many birds of prey, falcons have exceptional powers of vision; the visual acuity of one species has been measured at 2.6 times that of a normal human. Peregrine falcons have been recorded diving at speeds of 320 km/h (200 mph), making them the fastest-moving creatures on Earth; the fastest recorded dive attained a vertical speed of 390 km/h (240 mph).\u001b[0m\u001b[32;1m\u001b[1;3mThe scientific name for a hummingbird is Trochilidae. The fastest bird species in level flight is the common swift, which holds the record for the fastest confirmed level flight by a bird at 111.5 km/h (69.3 mph). The peregrine falcon is known to exceed speeds of 320 km/h (200 mph) in its dives, making it the fastest bird in terms of diving speed.\u001b[0m\n",
+      "\n",
+      "\n",
+      "Page: 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, 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",
+      "Page: Ostrich\n",
+      "Summary: Ostriches are large flightless birds. They are the heaviest and largest living birds, with adult common ostriches weighing anywhere between 63.5 and 145 kilograms and laying the largest eggs of any living land animal. With the ability to run at 70 km/h (43.5 mph), they are the fastest birds on land. They are farmed worldwide, with significant industries in the Philippines and in Namibia. Ostrich leather is a lucrative commodity, and the large feathers are used as plumes for the decoration of ceremonial headgear. Ostrich eggs have been used by humans for millennia.\n",
+      "Ostriches are of the genus Struthio in the order Struthioniformes, part of the infra-class Palaeognathae, a diverse group of flightless birds also known as ratites that includes the emus, rheas, cassowaries, kiwis and the extinct elephant birds and moas. There are two living species of ostrich: the common ostrich, native to large areas of sub-Saharan Africa, and the Somali ostrich, native to the Horn of Africa.  The common ostrich was historically native to the Arabian Peninsula, and ostriches were present across Asia as far east as China and Mongolia during the Late Pleistocene and possibly into the Holocene.\u001b[0m\u001b[32;1m\u001b[1;3m### Hummingbird's Scientific Name\n",
+      "The scientific name for the bee hummingbird, which is the smallest known bird and a species of hummingbird, is **Mellisuga helenae**. It is native to Cuba.\n",
+      "\n",
+      "### Fastest Bird Species\n",
+      "The fastest bird in terms of airspeed is the **peregrine falcon**, which can exceed speeds of 320 km/h (200 mph) during its diving flight. In level flight, the fastest confirmed speed is held by the **common swift**, which can fly at 111.5 km/h (69.3 mph).\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n",
-      "Total Tokens: 1675\n",
-      "Prompt Tokens: 1538\n",
-      "Completion Tokens: 137\n",
-      "Total Cost (USD): $0.0009745000000000001\n"
+      "Total Tokens: 1583\n",
+      "Prompt Tokens: 1412\n",
+      "Completion Tokens: 171\n",
+      "Total Cost (USD): $0.019250000000000003\n"
      ]
     }
    ],
@@ -537,19 +298,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
-   "id": "1837c807-136a-49d8-9c33-060e58dc16d2",
+   "execution_count": 1,
+   "id": "4a3eced5-2ff7-49a7-a48b-768af8658323",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Tokens Used: 96\n",
-      "\tPrompt Tokens: 26\n",
-      "\tCompletion Tokens: 70\n",
+      "Tokens Used: 0\n",
+      "\tPrompt Tokens: 0\n",
+      "\tCompletion Tokens: 0\n",
       "Successful Requests: 2\n",
-      "Total Cost (USD): $0.001888\n"
+      "Total Cost (USD): $0.0\n"
      ]
     }
    ],
@@ -603,7 +364,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/how_to/chatbots_memory.ipynb

@@ -71,13 +71,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "chat = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")"
+    "chat = ChatOpenAI(model=\"gpt-3.5-turbo-1106\")"
    ]
   },
   {
@@ -95,15 +95,19 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "I said \"J'adore la programmation,\" which means \"I love programming\" in French.\n"
-     ]
+     "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"
     }
    ],
    "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.messages import AIMessage, HumanMessage\n",
+    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
     "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
@@ -111,25 +115,23 @@
     "            \"system\",\n",
     "            \"You are a helpful assistant. Answer all questions to the best of your ability.\",\n",
     "        ),\n",
-    "        (\"placeholder\", \"{messages}\"),\n",
+    "        MessagesPlaceholder(variable_name=\"messages\"),\n",
     "    ]\n",
     ")\n",
     "\n",
     "chain = prompt | chat\n",
     "\n",
-    "ai_msg = chain.invoke(\n",
+    "chain.invoke(\n",
     "    {\n",
     "        \"messages\": [\n",
-    "            (\n",
-    "                \"human\",\n",
-    "                \"Translate this sentence from English to French: I love programming.\",\n",
+    "            HumanMessage(\n",
+    "                content=\"Translate this sentence from English to French: I love programming.\"\n",
     "            ),\n",
-    "            (\"ai\", \"J'adore la programmation.\"),\n",
-    "            (\"human\", \"What did you just say?\"),\n",
+    "            AIMessage(content=\"J'adore la programmation.\"),\n",
+    "            HumanMessage(content=\"What did you just say?\"),\n",
     "        ],\n",
     "    }\n",
-    ")\n",
-    "print(ai_msg.content)"
+    ")"
    ]
   },
   {
@@ -191,7 +193,7 @@
     {
      "data": {
       "text/plain": [
-       "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})"
+       "AIMessage(content='You asked me to translate the sentence \"I love programming\" from English to French.')"
       ]
      },
      "execution_count": 5,
@@ -248,7 +250,7 @@
     "            \"system\",\n",
     "            \"You are a helpful assistant. Answer all questions to the best of your ability.\",\n",
     "        ),\n",
-    "        (\"placeholder\", \"{chat_history}\"),\n",
+    "        MessagesPlaceholder(variable_name=\"chat_history\"),\n",
     "        (\"human\", \"{input}\"),\n",
     "    ]\n",
     ")\n",
@@ -302,17 +304,10 @@
    "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='\"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})"
+       "AIMessage(content='The translation of \"I love programming\" in French is \"J\\'adore la programmation.\"')"
       ]
      },
      "execution_count": 8,
@@ -332,17 +327,10 @@
    "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 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})"
+       "AIMessage(content='You just asked me to translate the sentence \"I love programming\" from English to French.')"
       ]
      },
      "execution_count": 9,
@@ -366,12 +354,12 @@
     "\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 trim the historic messages before passing them to the model. 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 to only load and store the most recent `n` messages. Let's use an example history with some preloaded messages:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -383,7 +371,7 @@
        " AIMessage(content='Fine thanks!')]"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -408,28 +396,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 11,
    "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.', 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})"
+       "AIMessage(content='Your name is Nemo.')"
       ]
      },
-     "execution_count": 22,
+     "execution_count": 11,
      "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",
@@ -449,33 +443,34 @@
    "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 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:"
+    "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:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 12,
    "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",
-    "trimmer = trim_messages(strategy=\"last\", max_tokens=2, token_counter=len)\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",
     "\n",
     "chain_with_trimming = (\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",
+    "    RunnablePassthrough.assign(messages_trimmed=trim_messages)\n",
+    "    | chain_with_message_history\n",
     ")"
    ]
   },
@@ -488,29 +483,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 13,
    "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 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})"
+       "AIMessage(content=\"P. Sherman's address is 42 Wallaby Way, Sydney.\")"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chain_with_trimmed_history.invoke(\n",
+    "chain_with_trimming.invoke(\n",
     "    {\"input\": \"Where does P. Sherman live?\"},\n",
     "    {\"configurable\": {\"session_id\": \"unused\"}},\n",
     ")"
@@ -518,23 +506,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[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=\"What's my name?\"),\n",
+       " AIMessage(content='Your name is Nemo.'),\n",
        " HumanMessage(content='Where does P. Sherman live?'),\n",
-       " 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})]"
+       " AIMessage(content=\"P. Sherman's address is 42 Wallaby Way, Sydney.\")]"
       ]
      },
-     "execution_count": 25,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -552,39 +536,48 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 15,
    "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, 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})"
+       "AIMessage(content=\"I'm sorry, I don't have access to your personal information.\")"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chain_with_trimmed_history.invoke(\n",
+    "chain_with_trimming.invoke(\n",
     "    {\"input\": \"What is my name?\"},\n",
     "    {\"configurable\": {\"session_id\": \"unused\"}},\n",
     ")"
    ]
   },
   {
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": 16,
    "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": [
-    "Check out our [how to guide on trimming messages](/docs/how_to/trim_messages/) for more."
+    "demo_ephemeral_chat_history.messages"
    ]
   },
   {
@@ -645,7 +638,7 @@
     "            \"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",
-    "        (\"placeholder\", \"{chat_history}\"),\n",
+    "        MessagesPlaceholder(variable_name=\"chat_history\"),\n",
     "        (\"user\", \"{input}\"),\n",
     "    ]\n",
     ")\n",
@@ -679,7 +672,7 @@
     "        return False\n",
     "    summarization_prompt = ChatPromptTemplate.from_messages(\n",
     "        [\n",
-    "            (\"placeholder\", \"{chat_history}\"),\n",
+    "            MessagesPlaceholder(variable_name=\"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",
@@ -779,9 +772,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 2
 }

docs/docs/how_to/code_splitter.ipynb

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

docs/docs/how_to/configure.ipynb

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

docs/docs/how_to/contextual_compression.ipynb

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

docs/docs/how_to/convert_runnable_to_tool.ipynb

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

docs/docs/how_to/custom_chat_model.ipynb

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

docs/docs/how_to/custom_tools.ipynb

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

docs/docs/how_to/document_loader_html.ipynb

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

docs/docs/how_to/document_loader_markdown.ipynb

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