update bind_tools in community

Thank you for contributing to LangChain!

- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
  - Example: "community: add foobar LLM"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.

.github/ISSUE_TEMPLATE/config.yml

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

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

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

.github/scripts/check_diff.py

@@ -1,11 +1,12 @@
+import glob
 import json
-import sys
 import os
-from typing import Dict, List, Set
-
+import re
+import sys
 import tomllib
 from collections import defaultdict
-import glob
+from typing import Dict, List, Set
+
 
 LANGCHAIN_DIRS = [
     "libs/core",
@@ -15,8 +16,13 @@ LANGCHAIN_DIRS = [
     "libs/experimental",
 ]
 
+
 def all_package_dirs() -> Set[str]:
-    return {"/".join(path.split("/")[:-1]) for path in glob.glob("./libs/**/pyproject.toml", recursive=True)}
+    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:
@@ -26,9 +32,9 @@ def dependents_graph() -> dict:
         if "template" in path:
             continue
         with open(path, "rb") as f:
-            pyproject = tomllib.load(f)['tool']['poetry']
+            pyproject = tomllib.load(f)["tool"]["poetry"]
         pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
-        for dep in pyproject['dependencies']:
+        for dep in pyproject["dependencies"]:
             if "langchain" in dep:
                 dependents[dep].add(pkg_dir)
     return dependents
@@ -47,6 +53,44 @@ def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
     return list(updated)
 
 
+def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
+    min_python = "3.8"
+    max_python = "3.12"
+
+    # custom logic for specific directories
+    if dir_ == "libs/partners/milvus":
+        # milvus poetry doesn't allow 3.12 because they
+        # declare deps in funny way
+        max_python = "3.11"
+
+    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:]
 
@@ -120,14 +164,23 @@ if __name__ == "__main__":
 
     dependents = dependents_graph()
 
-    outputs = {
-        "dirs-to-lint": add_dependents(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
-        ),
-        "dirs-to-test": add_dependents(dirs_to_run["test"] | dirs_to_run["extended-test"], dependents),
-        "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
-        "docs-edited": "true" if docs_edited else "",
+    # we now have dirs_by_job
+    # todo: clean this up
+
+    map_job_to_configs = {
+        job: _get_configs_for_multi_dirs(job, dirs_to_run, dependents)
+        for job in [
+            "lint",
+            "test",
+            "extended-tests",
+            "compile-integration-tests",
+            "dependencies",
+        ]
     }
-    for key, value in outputs.items():
+    map_job_to_configs["test-doc-imports"] = (
+        [{"python-version": "3.12"}] if docs_edited else []
+    )
+
+    for key, value in map_job_to_configs.items():
         json_output = json.dumps(value)
         print(f"{key}={json_output}")

.github/scripts/get_min_versions.py

@@ -74,6 +74,4 @@ if __name__ == "__main__":
     # Call the function to get the minimum versions
     min_versions = get_min_version_from_toml(toml_file)
 
-    print(
-        " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
-    )
+    print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))

.github/workflows/_compile_integration_test.yml

@@ -7,6 +7,10 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -25,14 +29,14 @@ jobs:
           - "3.10"
           - "3.11"
           - "3.12"
-    name: "poetry run pytest -m compile tests/integration_tests #${{ matrix.python-version }}"
+    name: "poetry run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: compile-integration

.github/workflows/_dependencies.yml

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

.github/workflows/_integration_test.yml

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

.github/workflows/_lint.yml

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

.github/workflows/_release.yml

@@ -122,7 +122,6 @@ jobs:
           fi
           {
             echo 'release-body<<EOF'
-            echo "# Release $TAG"
             echo $PREAMBLE
             echo
             git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR

.github/workflows/_test.yml

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

.github/workflows/_test_doc_imports.yml

@@ -2,6 +2,11 @@ name: test_doc_imports
 
 on:
   workflow_call:
+    inputs:
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -13,14 +18,14 @@ jobs:
       matrix:
         python-version:
           - "3.12"
-    name: "check doc imports #${{ matrix.python-version }}"
+    name: "check doc imports #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           cache-key: core
 

.github/workflows/check_diffs.yml

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

.github/workflows/scheduled_test.yml

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

README.md

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

docs/docs/concepts.mdx

@@ -85,8 +85,13 @@ Input and output schemas give every LCEL chain Pydantic and JSONSchema schemas i
 As your chains get more and more complex, it becomes increasingly important to understand what exactly is happening at every step.
 With LCEL, **all** steps are automatically logged to [LangSmith](https://docs.smith.langchain.com/) for maximum observability and debuggability.
 
-[**Seamless LangServe deployment**](/docs/langserve)
-Any chain created with LCEL can be easily deployed using [LangServe](/docs/langserve).
+LCEL aims to provide consistency around behavior and customization over legacy subclassed chains such as `LLMChain` and
+`ConversationalRetrievalChain`. Many of these legacy chains hide important details like prompts, and as a wider variety
+of viable models emerge, customization has become more and more important.
+
+If you are currently using one of these legacy chains, please see [this guide for guidance on how to migrate](/docs/how_to/migrate_chains/).
+
+For guides on how to do specific tasks with LCEL, check out [the relevant how-to guides](/docs/how_to/#langchain-expression-language-lcel).
 
 ### Runnable interface
 <span data-heading-keywords="invoke,runnable"></span>
@@ -516,6 +521,8 @@ Generally, when designing tools to be used by a chat model or LLM, it is importa
 
 For specifics on how to use tools, see the [relevant how-to guides here](/docs/how_to/#tools).
 
+To use an existing pre-built tool, see [here](docs/integrations/tools/) for a list of pre-built tools. 
+
 ### Toolkits
 
 Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.
@@ -776,14 +783,54 @@ a few ways to get structured output from models in LangChain.
 
 #### `.with_structured_output()`
 
-For convenience, some LangChain chat models support a `.with_structured_output()` method.
-This method only requires a schema as input, and returns a dict or Pydantic object.
+For convenience, some LangChain chat models support a [`.with_structured_output()`](/docs/how_to/structured_output/#the-with_structured_output-method)
+method. This method only requires a schema as input, and returns a dict or Pydantic object.
 Generally, this method is only present on models that support one of the more advanced methods described below,
 and will use one of them under the hood. It takes care of importing a suitable output parser and
 formatting the schema in the right format for the model.
 
+Here's an example:
+
+```python
+from typing import Optional
+
+from langchain_core.pydantic_v1 import BaseModel, Field
+
+
+class Joke(BaseModel):
+    """Joke to tell user."""
+
+    setup: str = Field(description="The setup of the joke")
+    punchline: str = Field(description="The punchline to the joke")
+    rating: Optional[int] = Field(description="How funny the joke is, from 1 to 10")
+
+structured_llm = llm.with_structured_output(Joke)
+
+structured_llm.invoke("Tell me a joke about cats")
+```
+
+```
+Joke(setup='Why was the cat sitting on the computer?', punchline='To keep an eye on the mouse!', rating=None)
+
+```
+
+We recommend this method as a starting point when working with structured output:
+
+- It uses other model-specific features under the hood, without the need to import an output parser.
+- For the models that use tool calling, no special prompting is needed.
+- If multiple underlying techniques are supported, you can supply a `method` parameter to
+[toggle which one is used](/docs/how_to/structured_output/#advanced-specifying-the-method-for-structuring-outputs).
+
+You may want or need to use other techiniques if:
+
+- The chat model you are using does not support tool calling.
+- You are working with very complex schemas and the model is having trouble generating outputs that conform.
+
 For more information, check out this [how-to guide](/docs/how_to/structured_output/#the-with_structured_output-method).
 
+You can also check out [this table](/docs/integrations/chat/#advanced-features) for a list of models that support
+`with_structured_output()`.
+
 #### Raw prompting
 
 The most intuitive way to get a model to structure output is to ask nicely.
@@ -806,9 +853,8 @@ for smooth parsing can be surprisingly difficult and model-specific.
 Some may be better at interpreting [JSON schema](https://json-schema.org/), others may be best with TypeScript definitions,
 and still others may prefer XML.
 
-While we'll next go over some ways that you can take advantage of features offered by
-model providers to increase reliability, prompting techniques remain important for tuning your
-results no matter what method you choose.
+While features offered by model providers may increase reliability, prompting techniques remain important for tuning your
+results no matter which method you choose.
 
 #### JSON mode
 <span data-heading-keywords="json mode"></span>
@@ -818,10 +864,11 @@ Some models, such as [Mistral](/docs/integrations/chat/mistralai/), [OpenAI](/do
 support a feature called **JSON mode**, usually enabled via config.
 
 When enabled, JSON mode will constrain the model's output to always be some sort of valid JSON.
-Often they require some custom prompting, but it's usually much less burdensome and along the lines of,
-`"you must always return JSON"`, and the [output is easier to parse](/docs/how_to/output_parser_json/).
+Often they require some custom prompting, but it's usually much less burdensome than completely raw prompting and
+more along the lines of, `"you must always return JSON"`. The [output also generally easier to parse](/docs/how_to/output_parser_json/).
 
-It's also generally simpler and more commonly available than tool calling.
+It's also generally simpler to use directly and more commonly available than tool calling, and can give
+more flexibility around prompting and shaping results than tool calling.
 
 Here's an example:
 
@@ -975,7 +1022,7 @@ See our [blog post overview](https://blog.langchain.dev/query-construction/) and
 
 #### Indexing
 
-Fouth, consider the design of your document index. A simple and powerful idea is to **decouple the documents that you index for retrieval from the documents that you pass to the LLM for generation.** Indexing frequently uses embedding models with vector stores, which [compress the semantic information in documents to fixed-size vectors](/docs/concepts/#embedding-models).
+Fourth, consider the design of your document index. A simple and powerful idea is to **decouple the documents that you index for retrieval from the documents that you pass to the LLM for generation.** Indexing frequently uses embedding models with vector stores, which [compress the semantic information in documents to fixed-size vectors](/docs/concepts/#embedding-models).
 
 Many RAG approaches focus on splitting documents into chunks and retrieving some number based on similarity to an input question for the LLM. But chunk size and chunk number can be difficult to set and affect results if they do not provide full context for the LLM to answer a question. Furthermore, LLMs are increasingly capable of processing millions of tokens. 
 
@@ -1083,7 +1130,7 @@ Table columns:
 | Token    | [many classes](/docs/how_to/split_by_token/)                                                                                                                                  | Tokens                                                                                                          |               | Splits text on tokens. There exist a few different ways to measure tokens.                                                                                                                                                                                                   |
 | Character  | [CharacterTextSplitter](/docs/how_to/character_text_splitter/)                                                                                                                | A user defined character                                                                                        |               | Splits text based on a user defined character. One of the simpler methods.                                                                                                                                                                                                   |
 | Semantic Chunker (Experimental) | [SemanticChunker](/docs/how_to/semantic-chunker/)                                                                                                                             | Sentences                                                                                                       |               | First splits on sentences. Then combines ones next to each other if they are semantically similar enough. Taken from [Greg Kamradt](https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb) |
-| Integration: AI21 Semantic | [AI21SemanticTextSplitter](/docs/integrations/document_transformers/ai21_semantic_text_splitter/)                                                                                                                    |    ✅           | Identifies distinct topics that form coherent pieces of text and splits along those.                                                                                                                                                                                         |
+| Integration: AI21 Semantic | [AI21SemanticTextSplitter](/docs/integrations/document_transformers/ai21_semantic_text_splitter/)                                                                                                 |                  |    ✅           | Identifies distinct topics that form coherent pieces of text and splits along those.                                                                                                                                                                                         |
 
 ### Evaluation
 <span data-heading-keywords="evaluation,evaluate"></span>

docs/docs/contributing/integrations.mdx

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

docs/docs/how_to/chat_token_usage_tracking.ipynb

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

docs/docs/how_to/convert_runnable_to_tool.ipynb

@@ -0,0 +1,541 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "9a8bceb3-95bd-4496-bb9e-57655136e070",
+   "metadata": {},
+   "source": [
+    "# How to use 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, we can add typing information via [Runnable.with_types](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.with_types):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "eb102705-89b7-48dc-9158-d36d5f98ae8e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "as_tool = runnable.with_types(input_type=Args).as_tool(\n",
+    "    name=\"My tool\",\n",
+    "    description=\"Explanation of when to use tool.\",\n",
+    ")"
+   ]
+  },
+  {
+   "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",
+    "<ChatModelTabs\n",
+    "  customVarName=\"llm\"\n",
+    "/>\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/dynamic_chain.ipynb

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

docs/docs/how_to/index.mdx

@@ -43,6 +43,7 @@ This highlights functionality that is core to using LangChain.
 - [How to: create a dynamic (self-constructing) chain](/docs/how_to/dynamic_chain/)
 - [How to: inspect runnables](/docs/how_to/inspect)
 - [How to: add fallbacks to a runnable](/docs/how_to/fallbacks)
+- [How to: migrate chains to LCEL](/docs/how_to/migrate_chains)
 
 ## Components
 
@@ -84,7 +85,7 @@ These are the core building blocks you can use when building applications.
 - [How to: stream tool calls](/docs/how_to/tool_streaming)
 - [How to: few shot prompt tool behavior](/docs/how_to/tools_few_shot)
 - [How to: bind model-specific formated tools](/docs/how_to/tools_model_specific)
-- [How to: force specific tool call](/docs/how_to/tool_choice)
+- [How to: force a specific tool call](/docs/how_to/tool_choice)
 - [How to: init any model in one line](/docs/how_to/chat_models_universal_init/)
 
 ### Messages
@@ -182,10 +183,11 @@ Indexing is the process of keeping your vectorstore in-sync with the underlying
 
 ### Tools
 
-LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to pass to the language model) as well as the implementation of the function to call.
+LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to pass to the language model) as well as the implementation of the function to call. Refer [here](/docs/integrations/tools/) for a list of pre-buit tools. 
 
 - [How to: create custom tools](/docs/how_to/custom_tools)
 - [How to: use built-in tools and built-in toolkits](/docs/how_to/tools_builtin)
+- [How to: convert Runnables to tools](/docs/how_to/convert_runnable_to_tool)
 - [How to: use chat model to call tools](/docs/how_to/tool_calling)
 - [How to: pass tool results back to model](/docs/how_to/tool_results_pass_to_model)
 - [How to: add ad-hoc tool calling capability to LLMs and chat models](/docs/how_to/tools_prompting)
@@ -193,6 +195,7 @@ LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to p
 - [How to: add a human in the loop to tool usage](/docs/how_to/tools_human)
 - [How to: handle errors when calling tools](/docs/how_to/tools_error)
 - [How to: disable parallel tool calling](/docs/how_to/tool_choice)
+- [How to: stream events from within a tool](/docs/how_to/tool_stream_events)
 
 ### Multimodal
 
@@ -204,7 +207,7 @@ LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to p
 
 :::note
 
-For in depth how-to guides for agents, please check out [LangGraph](https://github.com/langchain-ai/langgraph) documentation.
+For in depth how-to guides for agents, please check out [LangGraph](https://langchain-ai.github.io/langgraph/) documentation.
 
 :::
 

docs/docs/how_to/indexing.ipynb

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

docs/docs/how_to/migrate_agent.ipynb

@@ -351,7 +351,15 @@
    "id": "68df3a09",
    "metadata": {},
    "source": [
-    "## Memory\n",
+    "## Memory"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "96e7ffc8",
+   "metadata": {},
+   "source": [
+    "### In LangChain\n",
     "\n",
     "With LangChain's [AgentExecutor](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.iter), you could add chat [Memory](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.memory) so it can engage in a multi-turn conversation."
    ]
@@ -439,7 +447,7 @@
    "id": "c2a5a32f",
    "metadata": {},
    "source": [
-    "#### In LangGraph\n",
+    "### In LangGraph\n",
     "\n",
     "Memory is just [persistence](https://langchain-ai.github.io/langgraph/how-tos/persistence/), aka [checkpointing](https://langchain-ai.github.io/langgraph/reference/checkpoints/).\n",
     "\n",
@@ -510,6 +518,8 @@
    "source": [
     "## Iterating through steps\n",
     "\n",
+    "### In LangChain\n",
+    "\n",
     "With LangChain's [AgentExecutor](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.iter), you could iterate over the steps using the [stream](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.stream) (or async `astream`) methods or the [iter](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.iter) method. LangGraph supports stepwise iteration using [stream](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.stream) "
    ]
   },
@@ -568,7 +578,7 @@
    "id": "46ccbcbf",
    "metadata": {},
    "source": [
-    "#### In LangGraph\n",
+    "### In LangGraph\n",
     "\n",
     "In LangGraph, things are handled natively using [stream](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.graph.CompiledGraph.stream) or the asynchronous `astream` method."
    ]
@@ -619,6 +629,8 @@
    "source": [
     "## `return_intermediate_steps`\n",
     "\n",
+    "### In LangChain\n",
+    "\n",
     "Setting this parameter on AgentExecutor allows users to access intermediate_steps, which pairs agent actions (e.g., tool invocations) with their outcomes.\n"
    ]
   },
@@ -647,6 +659,8 @@
    "id": "594f7567-302f-4fa8-85bb-025ac8322162",
    "metadata": {},
    "source": [
+    "### In LangGraph\n",
+    "\n",
     "By default the [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) in LangGraph appends all messages to the central state. Therefore, it is easy to see any intermediate steps by just looking at the full state."
    ]
   },
@@ -687,11 +701,9 @@
    "source": [
     "## `max_iterations`\n",
     "\n",
-    "`AgentExecutor` implements a `max_iterations` parameter, whereas this is controlled via `recursion_limit` in LangGraph.\n",
+    "### In LangChain\n",
     "\n",
-    "Note that in AgentExecutor, an \"iteration\" includes a full turn of tool invocation and execution. In LangGraph, each step contributes to the recursion limit, so we will need to multiply by two (and add one) to get equivalent results.\n",
-    "\n",
-    "If the recursion limit is reached, LangGraph raises a specific exception type, that we can catch and manage similarly to AgentExecutor."
+    "`AgentExecutor` implements a `max_iterations` parameter, allowing users to abort a run that exceeds a specified number of iterations."
    ]
   },
   {
@@ -769,6 +781,20 @@
     "agent_executor.invoke({\"input\": query})"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "dd3a933f",
+   "metadata": {},
+   "source": [
+    "### In LangGraph\n",
+    "\n",
+    "In LangGraph this is controlled via `recursion_limit` configuration parameter.\n",
+    "\n",
+    "Note that in `AgentExecutor`, an \"iteration\" includes a full turn of tool invocation and execution. In LangGraph, each step contributes to the recursion limit, so we will need to multiply by two (and add one) to get equivalent results.\n",
+    "\n",
+    "If the recursion limit is reached, LangGraph raises a specific exception type, that we can catch and manage similarly to AgentExecutor."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 16,
@@ -814,6 +840,8 @@
    "source": [
     "## `max_execution_time`\n",
     "\n",
+    "### In LangChain\n",
+    "\n",
     "`AgentExecutor` implements a `max_execution_time` parameter, allowing users to abort a run that exceeds a total time limit."
    ]
   },
@@ -880,6 +908,8 @@
    "id": "d02eb025",
    "metadata": {},
    "source": [
+    "### In LangGraph\n",
+    "\n",
     "With LangGraph's react agent, you can control timeouts on two levels. \n",
     "\n",
     "You can set a `step_timeout` to bound each **step**:"
@@ -968,6 +998,8 @@
    "source": [
     "## `early_stopping_method`\n",
     "\n",
+    "### In LangChain\n",
+    "\n",
     "With LangChain's [AgentExecutor](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.iter), you could configure an [early_stopping_method](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.early_stopping_method) to either return a string saying \"Agent stopped due to iteration limit or time limit.\" (`\"force\"`) or prompt the LLM a final time to respond (`\"generate\"`)."
    ]
   },
@@ -1028,7 +1060,7 @@
    "id": "706e05c4",
    "metadata": {},
    "source": [
-    "#### In LangGraph\n",
+    "### In LangGraph\n",
     "\n",
     "In LangGraph, you can explicitly handle the response behavior outside the agent, since the full state can be accessed."
    ]
@@ -1077,6 +1109,8 @@
    "source": [
     "## `trim_intermediate_steps`\n",
     "\n",
+    "### In LangChain\n",
+    "\n",
     "With LangChain's [AgentExecutor](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor), you could trim the intermediate steps of long-running agents using [trim_intermediate_steps](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor.trim_intermediate_steps), which is either an integer (indicating the agent should keep the last N steps) or a custom function.\n",
     "\n",
     "For instance, we could trim the value so the agent only sees the most recent intermediate step."
@@ -1180,7 +1214,7 @@
    "id": "3d450c5a",
    "metadata": {},
    "source": [
-    "#### In LangGraph\n",
+    "### In LangGraph\n",
     "\n",
     "We can use the [`messages_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) just as before when passing in [prompt templates](#prompt-templates)."
    ]

docs/docs/how_to/migrate_chains.ipynb

@@ -0,0 +1,798 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f331037f-be3f-4782-856f-d55dab952488",
+   "metadata": {},
+   "source": [
+    "# How to migrate chains to LCEL\n",
+    "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "- [LangChain Expression Language](/docs/concepts#langchain-expression-language-lcel)\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "LCEL is designed to streamline the process of building useful apps with LLMs and combining related components. It does this by providing:\n",
+    "\n",
+    "1. **A unified interface**: Every LCEL object implements the `Runnable` interface, which defines a common set of invocation methods (`invoke`, `batch`, `stream`, `ainvoke`, ...). This makes it possible to also automatically and consistently support useful operations like streaming of intermediate steps and batching, since every chain composed of LCEL objects is itself an LCEL object.\n",
+    "2. **Composition primitives**: LCEL provides a number of primitives that make it easy to compose chains, parallelize components, add fallbacks, dynamically configure chain internals, and more.\n",
+    "\n",
+    "LangChain maintains a number of legacy abstractions. Many of these can be reimplemented via short combinations of LCEL primitives. Doing so confers some general advantages:\n",
+    "\n",
+    "- The resulting chains typically implement the full `Runnable` interface, including streaming and asynchronous support where appropriate;\n",
+    "- The chains may be more easily extended or modified;\n",
+    "- The parameters of the chain are typically surfaced for easier customization (e.g., prompts) over previous versions, which tended to be subclasses and had opaque parameters and internals.\n",
+    "\n",
+    "The LCEL implementations can be slightly more verbose, but there are significant benefits in transparency and customizability.\n",
+    "\n",
+    "In this guide we review LCEL implementations of common legacy abstractions. Where appropriate, we link out to separate guides with more detail."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b99b47ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet langchain-community langchain langchain-openai faiss-cpu"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "717c8673",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3621b62-a037-42b8-8faa-59575608bb8b",
+   "metadata": {},
+   "source": [
+    "## `LLMChain`\n",
+    "<span data-heading-keywords=\"llmchain\"></span>\n",
+    "\n",
+    "[`LLMChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.llm.LLMChain.html) combined a prompt template, LLM, and output parser into a class.\n",
+    "\n",
+    "Some advantages of switching to the LCEL implementation are:\n",
+    "\n",
+    "- Clarity around contents and parameters. The legacy `LLMChain` contains a default output parser and other options.\n",
+    "- Easier streaming. `LLMChain` only supports streaming via callbacks.\n",
+    "- Easier access to raw message outputs if desired. `LLMChain` only exposes these via a parameter or via callback.\n",
+    "\n",
+    "import { ColumnContainer, Column } from \"@theme/Columns\";\n",
+    "\n",
+    "<ColumnContainer>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### Legacy\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "e628905c-430e-4e4a-9d7c-c91d2f42052e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'adjective': 'funny',\n",
+       " 'text': \"Why couldn't the bicycle find its way home?\\n\\nBecause it lost its bearings!\"}"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chains import LLMChain\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"user\", \"Tell me a {adjective} joke\")],\n",
+    ")\n",
+    "\n",
+    "chain = LLMChain(llm=ChatOpenAI(), prompt=prompt)\n",
+    "\n",
+    "chain({\"adjective\": \"funny\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cdc3b527-c09e-4c77-9711-c3cc4506cd95",
+   "metadata": {},
+   "source": [
+    "\n",
+    "</Column>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### LCEL\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "0d2a7cf8-1bc7-405c-bb0d-f2ab2ba3b6ab",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why couldn't the bicycle stand up by itself?\\n\\nBecause it was two tired!\""
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"user\", \"Tell me a {adjective} joke\")],\n",
+    ")\n",
+    "\n",
+    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
+    "\n",
+    "chain.invoke({\"adjective\": \"funny\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3c0b0513-77b8-4371-a20e-3e487cec7e7f",
+   "metadata": {},
+   "source": [
+    "\n",
+    "</Column>\n",
+    "</ColumnContainer>\n",
+    "\n",
+    "Note that `LLMChain` by default returns a `dict` containing both the input and the output. If this behavior is desired, we can replicate it using another LCEL primitive, [`RunnablePassthrough`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.passthrough.RunnablePassthrough.html):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "529206c5-abbe-4213-9e6c-3b8586c8000d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'adjective': 'funny',\n",
+       " 'text': \"Why couldn't the bicycle stand up by itself?\\n\\nBecause it was two tired!\"}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "outer_chain = RunnablePassthrough().assign(text=chain)\n",
+    "\n",
+    "outer_chain.invoke({\"adjective\": \"funny\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "29d2e26c-2854-4971-9c2b-613450993921",
+   "metadata": {},
+   "source": [
+    "See [this tutorial](/docs/tutorials/llm_chain) for more detail on building with prompt templates, LLMs, and output parsers."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "00df631d-5121-4918-94aa-b88acce9b769",
+   "metadata": {},
+   "source": [
+    "## `ConversationChain`\n",
+    "<span data-heading-keywords=\"conversationchain\"></span>\n",
+    "\n",
+    "[`ConversationChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.conversation.base.ConversationChain.html) incorporates a memory of previous messages to sustain a stateful conversation.\n",
+    "\n",
+    "Some advantages of switching to the LCEL implementation are:\n",
+    "\n",
+    "- Innate support for threads/separate sessions. To make this work with `ConversationChain`, you'd need to instantiate a separate memory class outside the chain.\n",
+    "- More explicit parameters. `ConversationChain` contains a hidden default prompt, which can cause confusion.\n",
+    "- Streaming support. `ConversationChain` only supports streaming via callbacks.\n",
+    "\n",
+    "`RunnableWithMessageHistory` implements sessions via configuration parameters. It should be instantiated with a callable that returns a [chat message history](https://api.python.langchain.com/en/latest/chat_history/langchain_core.chat_history.BaseChatMessageHistory.html). By default, it expects this function to take a single argument `session_id`.\n",
+    "\n",
+    "<ColumnContainer>\n",
+    "<Column>\n",
+    "\n",
+    "#### Legacy\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "4f2cc6dc-d70a-4c13-9258-452f14290da6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input': 'how are you?',\n",
+       " 'history': '',\n",
+       " 'response': \"Arrr, I be doin' well, me matey! Just sailin' the high seas in search of treasure and adventure. How can I assist ye today?\"}"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chains import ConversationChain\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "template = \"\"\"\n",
+    "You are a pirate. Answer the following questions as best you can.\n",
+    "Chat history: {history}\n",
+    "Question: {input}\n",
+    "\"\"\"\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(template)\n",
+    "\n",
+    "memory = ConversationBufferMemory()\n",
+    "\n",
+    "chain = ConversationChain(\n",
+    "    llm=ChatOpenAI(),\n",
+    "    memory=memory,\n",
+    "    prompt=prompt,\n",
+    ")\n",
+    "\n",
+    "chain({\"input\": \"how are you?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f8e36b0e-c7dc-4130-a51b-189d4b756c7f",
+   "metadata": {},
+   "source": [
+    "</Column>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### LCEL\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "173e1a9c-2a18-4669-b0de-136f39197786",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Arr, matey! I be sailin' the high seas with me crew, searchin' for buried treasure and adventure! How be ye doin' on this fine day?\""
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.chat_history import InMemoryChatMessageHistory\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", \"You are a pirate. Answer the following questions as best you can.\"),\n",
+    "        (\"placeholder\", \"{chat_history}\"),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "history = InMemoryChatMessageHistory()\n",
+    "\n",
+    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
+    "\n",
+    "wrapped_chain = RunnableWithMessageHistory(chain, lambda x: history)\n",
+    "\n",
+    "wrapped_chain.invoke(\n",
+    "    {\"input\": \"how are you?\"},\n",
+    "    config={\"configurable\": {\"session_id\": \"42\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b386ce6-895e-442c-88f3-7bec0ab9f401",
+   "metadata": {},
+   "source": [
+    "\n",
+    "</Column>\n",
+    "</ColumnContainer>\n",
+    "\n",
+    "The above example uses the same `history` for all sessions. The example below shows how to use a different chat history for each session."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "4e05994f-1fbc-4699-bf2e-62cb0e4deeb8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Ahoy there! What be ye wantin' from this old pirate?\", response_metadata={'token_usage': {'completion_tokens': 15, 'prompt_tokens': 29, 'total_tokens': 44}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-1846d5f5-0dda-43b6-bb49-864e541f9c29-0', usage_metadata={'input_tokens': 29, 'output_tokens': 15, 'total_tokens': 44})"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.chat_history import BaseChatMessageHistory\n",
+    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
+    "\n",
+    "store = {}\n",
+    "\n",
+    "\n",
+    "def get_session_history(session_id: str) -> BaseChatMessageHistory:\n",
+    "    if session_id not in store:\n",
+    "        store[session_id] = InMemoryChatMessageHistory()\n",
+    "    return store[session_id]\n",
+    "\n",
+    "\n",
+    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
+    "\n",
+    "wrapped_chain = RunnableWithMessageHistory(chain, get_session_history)\n",
+    "\n",
+    "wrapped_chain.invoke(\"Hello!\", config={\"configurable\": {\"session_id\": \"abc123\"}})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c36ebecb",
+   "metadata": {},
+   "source": [
+    "See [this tutorial](/docs/tutorials/chatbot) for a more end-to-end guide on building with [`RunnableWithMessageHistory`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html).\n",
+    "\n",
+    "## `RetrievalQA`\n",
+    "<span data-heading-keywords=\"retrievalqa\"></span>\n",
+    "\n",
+    "The [`RetrievalQA`](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval_qa.base.RetrievalQA.html) chain performed natural-language question answering over a data source using retrieval-augmented generation.\n",
+    "\n",
+    "Some advantages of switching to the LCEL implementation are:\n",
+    "\n",
+    "- Easier customizability. Details such as the prompt and how documents are formatted are only configurable via specific parameters in the `RetrievalQA` chain.\n",
+    "- More easily return source documents.\n",
+    "- Support for runnable methods like streaming and async operations.\n",
+    "\n",
+    "Now let's look at them side-by-side. We'll use the same ingestion code to load a [blog post by Lilian Weng](https://lilianweng.github.io/posts/2023-06-23-agent/) on autonomous agents into a local vector store:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "1efbe16e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load docs\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_community.document_loaders import WebBaseLoader\n",
+    "from langchain_community.vectorstores import FAISS\n",
+    "from langchain_openai.chat_models import ChatOpenAI\n",
+    "from langchain_openai.embeddings import OpenAIEmbeddings\n",
+    "\n",
+    "loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n",
+    "data = loader.load()\n",
+    "\n",
+    "# Split\n",
+    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
+    "all_splits = text_splitter.split_documents(data)\n",
+    "\n",
+    "# Store splits\n",
+    "vectorstore = FAISS.from_documents(documents=all_splits, embedding=OpenAIEmbeddings())\n",
+    "\n",
+    "# LLM\n",
+    "llm = ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c7e16438",
+   "metadata": {},
+   "source": [
+    "<ColumnContainer>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### Legacy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "43bf55a0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'query': 'What are autonomous agents?',\n",
+       " 'result': 'Autonomous agents are LLM-empowered agents that handle autonomous design, planning, and performance of complex tasks, such as scientific experiments. These agents can browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other LLMs. They are capable of reasoning and planning ahead for complicated tasks by breaking them down into smaller steps.'}"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain import hub\n",
+    "from langchain.chains import RetrievalQA\n",
+    "\n",
+    "# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt\n",
+    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
+    "\n",
+    "qa_chain = RetrievalQA.from_llm(\n",
+    "    llm, retriever=vectorstore.as_retriever(), prompt=prompt\n",
+    ")\n",
+    "\n",
+    "qa_chain(\"What are autonomous agents?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "081948e5",
+   "metadata": {},
+   "source": [
+    "</Column>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### LCEL\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "9efcc931",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Autonomous agents are agents that can handle autonomous design, planning, and performance of complex tasks, such as scientific experiments. They can browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other language model models. These agents use reasoning steps to develop solutions to specific tasks, like creating a novel anticancer drug.'"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain import hub\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt\n",
+    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
+    "\n",
+    "\n",
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
+    "\n",
+    "\n",
+    "qa_chain = (\n",
+    "    {\n",
+    "        \"context\": vectorstore.as_retriever() | format_docs,\n",
+    "        \"question\": RunnablePassthrough(),\n",
+    "    }\n",
+    "    | prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "qa_chain.invoke(\"What are autonomous agents?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d6f44fe8",
+   "metadata": {},
+   "source": [
+    "</Column>\n",
+    "</ColumnContainer>\n",
+    "\n",
+    "The LCEL implementation exposes the internals of what's happening around retrieving, formatting documents, and passing them through a prompt to the LLM, but it is more verbose. You can customize and wrap this composition logic in a helper function, or use the higher-level [`create_retrieval_chain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html) and [`create_stuff_documents_chain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.combine_documents.stuff.create_stuff_documents_chain.html) helper method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "5fe42761",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input': 'What are autonomous agents?',\n",
+       " 'context': [Document(page_content='Boiko et al. (2023) also looked into LLM-empowered agents for scientific discovery, to handle autonomous design, planning, and performance of complex scientific experiments. This agent can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs and leverage other LLMs.\\nFor example, when requested to \"develop a novel anticancer drug\", the model came up with the following reasoning steps:', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
+       "  Document(page_content='Weng, Lilian. (Jun 2023). “LLM-powered Autonomous Agents”. Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
+       "  Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
+       "  Document(page_content=\"LLM Powered Autonomous Agents | Lil'Log\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nLil'Log\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nPosts\\n\\n\\n\\n\\nArchive\\n\\n\\n\\n\\nSearch\\n\\n\\n\\n\\nTags\\n\\n\\n\\n\\nFAQ\\n\\n\\n\\n\\nemojisearch.app\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n      LLM Powered Autonomous Agents\\n    \\nDate: June 23, 2023  |  Estimated Reading Time: 31 min  |  Author: Lilian Weng\\n\\n\\n \\n\\n\\nTable of Contents\\n\\n\\n\\nAgent System Overview\\n\\nComponent One: Planning\\n\\nTask Decomposition\\n\\nSelf-Reflection\\n\\n\\nComponent Two: Memory\\n\\nTypes of Memory\\n\\nMaximum Inner Product Search (MIPS)\", metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'})],\n",
+       " 'answer': 'Autonomous agents are entities that can operate independently, making decisions and taking actions without direct human intervention. These agents can perform tasks such as planning, executing complex experiments, and leveraging various tools and resources to achieve objectives. In the context provided, LLM-powered autonomous agents are specifically designed for scientific discovery, capable of handling tasks like designing novel anticancer drugs through reasoning steps.'}"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain import hub\n",
+    "from langchain.chains import create_retrieval_chain\n",
+    "from langchain.chains.combine_documents import create_stuff_documents_chain\n",
+    "\n",
+    "# See full prompt at https://smith.langchain.com/hub/langchain-ai/retrieval-qa-chat\n",
+    "retrieval_qa_chat_prompt = hub.pull(\"langchain-ai/retrieval-qa-chat\")\n",
+    "\n",
+    "combine_docs_chain = create_stuff_documents_chain(llm, retrieval_qa_chat_prompt)\n",
+    "rag_chain = create_retrieval_chain(vectorstore.as_retriever(), combine_docs_chain)\n",
+    "\n",
+    "rag_chain.invoke({\"input\": \"What are autonomous agents?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2772f4e9",
+   "metadata": {},
+   "source": [
+    "## `ConversationalRetrievalChain`\n",
+    "<span data-heading-keywords=\"conversationalretrievalchain\"></span>\n",
+    "\n",
+    "The [`ConversationalRetrievalChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.conversational_retrieval.base.ConversationalRetrievalChain.html) was an all-in one way that combined retrieval-augmented generation with chat history, allowing you to \"chat with\" your documents.\n",
+    "\n",
+    "Advantages of switching to the LCEL implementation are similar to the `RetrievalQA` section above:\n",
+    "\n",
+    "- Clearer internals. The `ConversationalRetrievalChain` chain hides an entire question rephrasing step which dereferences the initial query against the chat history.\n",
+    "  - This means the class contains two sets of configurable prompts, LLMs, etc.\n",
+    "- More easily return source documents.\n",
+    "- Support for runnable methods like streaming and async operations.\n",
+    "\n",
+    "Here are side-by-side implementations with custom prompts. We'll reuse the loaded documents and vector store from the previous section:"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8bc06416",
+   "metadata": {},
+   "source": [
+    "<ColumnContainer>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### Legacy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "54eb9576",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'What are autonomous agents?',\n",
+       " 'chat_history': '',\n",
+       " 'answer': 'Autonomous agents are powered by Large Language Models (LLMs) to handle tasks like scientific discovery and complex experiments autonomously. These agents can browse the internet, read documentation, execute code, and leverage other LLMs to perform tasks. They can reason and plan ahead to decompose complicated tasks into manageable steps.'}"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chains import ConversationalRetrievalChain\n",
+    "\n",
+    "condense_question_template = \"\"\"\n",
+    "Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.\n",
+    "\n",
+    "Chat History:\n",
+    "{chat_history}\n",
+    "Follow Up Input: {question}\n",
+    "Standalone question:\"\"\"\n",
+    "\n",
+    "condense_question_prompt = ChatPromptTemplate.from_template(condense_question_template)\n",
+    "\n",
+    "qa_template = \"\"\"\n",
+    "You are an assistant for question-answering tasks.\n",
+    "Use the following pieces of retrieved context to answer\n",
+    "the question. If you don't know the answer, say that you\n",
+    "don't know. Use three sentences maximum and keep the\n",
+    "answer concise.\n",
+    "\n",
+    "Chat History:\n",
+    "{chat_history}\n",
+    "\n",
+    "Other context:\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "\"\"\"\n",
+    "\n",
+    "qa_prompt = ChatPromptTemplate.from_template(qa_template)\n",
+    "\n",
+    "convo_qa_chain = ConversationalRetrievalChain.from_llm(\n",
+    "    llm,\n",
+    "    vectorstore.as_retriever(),\n",
+    "    condense_question_prompt=condense_question_prompt,\n",
+    "    combine_docs_chain_kwargs={\n",
+    "        \"prompt\": qa_prompt,\n",
+    "    },\n",
+    ")\n",
+    "\n",
+    "convo_qa_chain(\n",
+    "    {\n",
+    "        \"question\": \"What are autonomous agents?\",\n",
+    "        \"chat_history\": \"\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "43a8a23c",
+   "metadata": {},
+   "source": [
+    "</Column>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### LCEL\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "c884b138",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input': 'What are autonomous agents?',\n",
+       " 'chat_history': [],\n",
+       " 'context': [Document(page_content='Boiko et al. (2023) also looked into LLM-empowered agents for scientific discovery, to handle autonomous design, planning, and performance of complex scientific experiments. This agent can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs and leverage other LLMs.\\nFor example, when requested to \"develop a novel anticancer drug\", the model came up with the following reasoning steps:', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
+       "  Document(page_content='Weng, Lilian. (Jun 2023). “LLM-powered Autonomous Agents”. Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
+       "  Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
+       "  Document(page_content='Or\\n@article{weng2023agent,\\n  title   = \"LLM-powered Autonomous Agents\",\\n  author  = \"Weng, Lilian\",\\n  journal = \"lilianweng.github.io\",\\n  year    = \"2023\",\\n  month   = \"Jun\",\\n  url     = \"https://lilianweng.github.io/posts/2023-06-23-agent/\"\\n}\\nReferences#\\n[1] Wei et al. “Chain of thought prompting elicits reasoning in large language models.” NeurIPS 2022\\n[2] Yao et al. “Tree of Thoughts: Dliberate Problem Solving with Large Language Models.” arXiv preprint arXiv:2305.10601 (2023).', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'})],\n",
+       " 'answer': 'Autonomous agents are entities capable of acting independently, making decisions, and performing tasks without direct human intervention. These agents can interact with their environment, perceive information, and take actions based on their goals or objectives. They often use artificial intelligence techniques to navigate and accomplish tasks in complex or dynamic environments.'}"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chains import create_history_aware_retriever, create_retrieval_chain\n",
+    "\n",
+    "condense_question_system_template = (\n",
+    "    \"Given a chat history and the latest user question \"\n",
+    "    \"which might reference context in the chat history, \"\n",
+    "    \"formulate a standalone question which can be understood \"\n",
+    "    \"without the chat history. Do NOT answer the question, \"\n",
+    "    \"just reformulate it if needed and otherwise return it as is.\"\n",
+    ")\n",
+    "\n",
+    "condense_question_prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", condense_question_system_template),\n",
+    "        (\"placeholder\", \"{chat_history}\"),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "history_aware_retriever = create_history_aware_retriever(\n",
+    "    llm, vectorstore.as_retriever(), condense_question_prompt\n",
+    ")\n",
+    "\n",
+    "system_prompt = (\n",
+    "    \"You are an assistant for question-answering tasks. \"\n",
+    "    \"Use the following pieces of retrieved context to answer \"\n",
+    "    \"the question. If you don't know the answer, say that you \"\n",
+    "    \"don't know. Use three sentences maximum and keep the \"\n",
+    "    \"answer concise.\"\n",
+    "    \"\\n\\n\"\n",
+    "    \"{context}\"\n",
+    ")\n",
+    "\n",
+    "qa_prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", system_prompt),\n",
+    "        (\"placeholder\", \"{chat_history}\"),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "qa_chain = create_stuff_documents_chain(llm, qa_prompt)\n",
+    "\n",
+    "convo_qa_chain = create_retrieval_chain(history_aware_retriever, qa_chain)\n",
+    "\n",
+    "convo_qa_chain.invoke(\n",
+    "    {\n",
+    "        \"input\": \"What are autonomous agents?\",\n",
+    "        \"chat_history\": [],\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2717810",
+   "metadata": {},
+   "source": [
+    "</Column>\n",
+    "\n",
+    "</ColumnContainer>\n",
+    "\n",
+    "## Next steps\n",
+    "\n",
+    "You've now seen how to migrate existing usage of some legacy chains to LCEL.\n",
+    "\n",
+    "Next, check out the [LCEL conceptual docs](/docs/concepts/#langchain-expression-language-lcel) for more background information."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/structured_output.ipynb

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

docs/docs/how_to/tool_choice.ipynb

@@ -6,6 +6,14 @@
    "source": [
     "# How to force tool calling behavior\n",
     "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "- [Chat models](/docs/concepts/#chat-models)\n",
+    "- [LangChain Tools](/docs/concepts/#tools)\n",
+    "- [How to use a model to call tools](/docs/how_to/tool_calling)\n",
+    ":::\n",
+    "\n",
     "In order to force our LLM to spelect a specific tool, we can use the `tool_choice` parameter to ensure certain behavior. First, let's define our model and tools:"
    ]
   },

docs/docs/how_to/tool_runtime.ipynb

@@ -12,7 +12,7 @@
     "- [Chat models](/docs/concepts/#chat-models)\n",
     "- [LangChain Tools](/docs/concepts/#tools)\n",
     "- [How to create tools](/docs/how_to/custom_tools)\n",
-    "- [How to use a model to call tools](https://python.langchain.com/v0.2/docs/how_to/tool_calling)\n",
+    "- [How to use a model to call tools](/docs/how_to/tool_calling)\n",
     ":::\n",
     "\n",
     ":::{.callout-info} Supported models\n",

docs/docs/how_to/tool_stream_events.ipynb

@@ -0,0 +1,286 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to stream events from within a tool\n",
+    "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "- [LangChain Tools](/docs/concepts/#tools)\n",
+    "- [Using stream events](/docs/how_to/streaming/#using-stream-events)\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "If you have tools that call LLMs, retrievers, or other runnables, you may want to access internal events from those runnables. This guide shows you a few ways you can do this using the `astream_events()` method.\n",
+    "\n",
+    ":::caution\n",
+    "LangChain cannot automatically propagate callbacks to child runnables if you are running async code in python<=3.10.\n",
+    "    \n",
+    "This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
+    ":::\n",
+    "\n",
+    "We'll define a custom tool below that calls a chain that summarizes its input in a special way by prompting an LLM to return only 10 words, then reversing the output:\n",
+    "\n",
+    "```{=mdx}\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs customVarName=\"model\" />\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "%pip install -qU langchain langchain_anthropic\n",
+    "\n",
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_anthropic import ChatAnthropic\n",
+    "\n",
+    "if \"ANTHROPIC_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"ANTHROPIC_API_KEY\"] = getpass()\n",
+    "\n",
+    "model = ChatAnthropic(model=\"claude-3-5-sonnet-20240620\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def special_summarization_tool(long_text: str) -> str:\n",
+    "    \"\"\"A tool that summarizes input text using advanced techniques.\"\"\"\n",
+    "    prompt = ChatPromptTemplate.from_template(\n",
+    "        \"You are an expert writer. Summarize the following text in 10 words or less:\\n\\n{long_text}\"\n",
+    "    )\n",
+    "\n",
+    "    def reverse(x: str):\n",
+    "        return x[::-1]\n",
+    "\n",
+    "    chain = prompt | model | StrOutputParser() | reverse\n",
+    "    summary = chain.invoke({\"long_text\": long_text})\n",
+    "    return summary"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If you just invoke the tool directly, you can see that you only get the final response:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'.yad noitaudarg rof tiftuo sesoohc yrraB ;scisyhp seifed eeB'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "LONG_TEXT = \"\"\"\n",
+    "NARRATOR:\n",
+    "(Black screen with text; The sound of buzzing bees can be heard)\n",
+    "According to all known laws of aviation, there is no way a bee should be able to fly. Its wings are too small to get its fat little body off the ground. The bee, of course, flies anyway because bees don't care what humans think is impossible.\n",
+    "BARRY BENSON:\n",
+    "(Barry is picking out a shirt)\n",
+    "Yellow, black. Yellow, black. Yellow, black. Yellow, black. Ooh, black and yellow! Let's shake it up a little.\n",
+    "JANET BENSON:\n",
+    "Barry! Breakfast is ready!\n",
+    "BARRY:\n",
+    "Coming! Hang on a second.\n",
+    "\"\"\"\n",
+    "\n",
+    "special_summarization_tool.invoke({\"long_text\": LONG_TEXT})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If you wanted to access the raw output from the chat model, you could use the [`astream_events()`](/docs/how_to/streaming/#using-stream-events) method and look for `on_chat_model_end` events:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'event': 'on_chat_model_end', 'data': {'output': AIMessage(content='Bee defies physics; Barry chooses outfit for graduation day.', response_metadata={'stop_reason': 'end_turn', 'stop_sequence': None}, id='run-195c0986-2ffa-43a3-9366-f2f96c42fe57', usage_metadata={'input_tokens': 182, 'output_tokens': 16, 'total_tokens': 198}), 'input': {'messages': [[HumanMessage(content=\"You are an expert writer. Summarize the following text in 10 words or less:\\n\\n\\nNARRATOR:\\n(Black screen with text; The sound of buzzing bees can be heard)\\nAccording to all known laws of aviation, there is no way a bee should be able to fly. Its wings are too small to get its fat little body off the ground. The bee, of course, flies anyway because bees don't care what humans think is impossible.\\nBARRY BENSON:\\n(Barry is picking out a shirt)\\nYellow, black. Yellow, black. Yellow, black. Yellow, black. Ooh, black and yellow! Let's shake it up a little.\\nJANET BENSON:\\nBarry! Breakfast is ready!\\nBARRY:\\nComing! Hang on a second.\\n\")]]}}, 'run_id': '195c0986-2ffa-43a3-9366-f2f96c42fe57', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['370919df-1bc3-43ae-aab2-8e112a4ddf47', 'de535624-278b-4927-9393-6d0cac3248df']}\n"
+     ]
+    }
+   ],
+   "source": [
+    "stream = special_summarization_tool.astream_events(\n",
+    "    {\"long_text\": LONG_TEXT}, version=\"v2\"\n",
+    ")\n",
+    "\n",
+    "async for event in stream:\n",
+    "    if event[\"event\"] == \"on_chat_model_end\":\n",
+    "        print(event)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And you can see that you get the raw response from the chat model.\n",
+    "\n",
+    "`astream_events()` will automatically call internal runnables in a chain with streaming enabled if possible, so if you wanted to a stream of tokens as they are generated from the chat model, you could simply filter our calls to look for `on_chat_model_stream` events with no other changes:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', usage_metadata={'input_tokens': 182, 'output_tokens': 0, 'total_tokens': 182})}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='Bee', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3')}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' def', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3')}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='ies physics', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3')}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=';', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3')}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' Barry', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3')}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' cho', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3')}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='oses outfit', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3')}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' for', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3')}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' graduation', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3')}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' day', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3')}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='.', id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3')}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='', response_metadata={'stop_reason': 'end_turn', 'stop_sequence': None}, id='run-cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', usage_metadata={'input_tokens': 0, 'output_tokens': 16, 'total_tokens': 16})}, 'run_id': 'cd8c1bd9-64d8-463c-a4d7-4bceed7911b3', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['8ddd1325-07c4-4213-8a2f-4462db8c6c70', '9f8654b4-b3f6-414e-b41d-dd201342a2fa']}\n"
+     ]
+    }
+   ],
+   "source": [
+    "stream = special_summarization_tool.astream_events(\n",
+    "    {\"long_text\": LONG_TEXT}, version=\"v2\"\n",
+    ")\n",
+    "\n",
+    "async for event in stream:\n",
+    "    if event[\"event\"] == \"on_chat_model_stream\":\n",
+    "        print(event)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note that you still have access to the final tool response as well. You can access it by looking for an `on_tool_end` event.\n",
+    "\n",
+    "To make events your tool emits easier to identify, you can also add identifiers to runnables using the `with_config()` method. `run_name` will apply to only to the runnable you attach it to, while `tags` will be inherited by runnables called within your initial runnable.\n",
+    "\n",
+    "Let's redeclare the tool with a tag, then run it with `astream_events()` with some filters. You should only see streamed events from the chat model and the final tool output:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630', usage_metadata={'input_tokens': 182, 'output_tokens': 0, 'total_tokens': 182})}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='Bee', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630')}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' def', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630')}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='ies physics', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630')}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=';', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630')}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' Barry', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630')}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' cho', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630')}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='oses outfit', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630')}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' for', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630')}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' graduation', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630')}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' day', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630')}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='.', id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630')}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='', response_metadata={'stop_reason': 'end_turn', 'stop_sequence': None}, id='run-696f4fc8-6c6f-46a0-8c82-e2e3f7625630', usage_metadata={'input_tokens': 0, 'output_tokens': 16, 'total_tokens': 16})}, 'run_id': '696f4fc8-6c6f-46a0-8c82-e2e3f7625630', 'name': 'ChatAnthropic', 'tags': ['seq:step:2', 'bee_movie'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['49d9d7d3-2b02-4964-a6c5-12f57a063146', '8922d0e3-4199-4ba5-9a7a-fc4f2fca3e72']}\n",
+      "{'event': 'on_tool_end', 'data': {'output': '.yad noitaudarg rof tiftuo sesoohc yrraB ;scisyhp seifed eeB'}, 'run_id': '49d9d7d3-2b02-4964-a6c5-12f57a063146', 'name': 'special_summarization_tool', 'tags': ['bee_movie'], 'metadata': {}, 'parent_ids': []}\n"
+     ]
+    }
+   ],
+   "source": [
+    "tagged_tool = special_summarization_tool.with_config({\"tags\": [\"bee_movie\"]})\n",
+    "\n",
+    "stream = tagged_tool.astream_events(\n",
+    "    {\"long_text\": LONG_TEXT}, version=\"v2\", include_tags=[\"bee_movie\"]\n",
+    ")\n",
+    "\n",
+    "async for event in stream:\n",
+    "    event_type = event[\"event\"]\n",
+    "    if event_type == \"on_chat_model_stream\" or event_type == \"on_tool_end\":\n",
+    "        print(event)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "Now you've learned how to stream events from within a tool. Next, you can learn more about how to use tools:\n",
+    "\n",
+    "- Bind [model-specific tools](/docs/how_to/tools_model_specific/)\n",
+    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)\n",
+    "- Pass [tool results back to a model](/docs/how_to/tool_results_pass_to_model)\n",
+    "\n",
+    "You can also check out some more specific uses of tool calling:\n",
+    "\n",
+    "- Building [tool-using chains and agents](/docs/how_to#tools)\n",
+    "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tools_error.ipynb

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

docs/docs/integrations/chat/fireworks.ipynb

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

docs/docs/integrations/chat/ibm_watsonx.ipynb

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

docs/docs/integrations/chat/llamacpp.ipynb

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

docs/docs/integrations/document_loaders/airbyte_cdk.ipynb

@@ -1,5 +1,19 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "bd931196",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_gong.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "344fc5a3",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_hubspot.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "a792e839",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_json.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "61c2629c",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_salesforce.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "e329385c",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_shopify.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "3169f380",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_stripe.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "87552e5a",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_typeform.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "9a10cdcc",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_zendesk_support.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "41200199",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/llm_caching.ipynb

@@ -2147,6 +2147,32 @@
     "llm(\"Tell me one joke\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## SingleStoreDB Semantic Cache\n",
+    "You can use [SingleStoreDB](https://python.langchain.com/docs/integrations/vectorstores/singlestoredb/) as a semantic cache to cache prompts and responses."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d82f1bdc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.cache import SingleStoreDBSemanticCache\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "set_llm_cache(\n",
+    "    SingleStoreDBSemanticCache(\n",
+    "        embedding=OpenAIEmbeddings(),\n",
+    "        host=\"root:pass@localhost:3306/db\",\n",
+    "    )\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "ae1f5e1c-085e-4998-9f2d-b5867d2c3d5b",
@@ -2178,7 +2204,7 @@
    "source": [
     "**Cache** classes are implemented by inheriting the [BaseCache](https://api.python.langchain.com/en/latest/caches/langchain_core.caches.BaseCache.html) class.\n",
     "\n",
-    "This table lists all 20 derived classes with links to the API Reference.\n",
+    "This table lists all 21 derived classes with links to the API Reference.\n",
     "\n",
     "\n",
     "| Namespace 🔻 | Class |\n",
@@ -2195,6 +2221,7 @@
     "| langchain_community.cache | [MomentoCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.MomentoCache.html) |\n",
     "| langchain_community.cache | [OpenSearchSemanticCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.OpenSearchSemanticCache.html) |\n",
     "| langchain_community.cache | [RedisSemanticCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.RedisSemanticCache.html) |\n",
+    "| langchain_community.cache | [SingleStoreDBSemanticCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.SingleStoreDBSemanticCache.html) |\n",
     "| langchain_community.cache | [SQLAlchemyCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.SQLAlchemyCache.html) |\n",
     "| langchain_community.cache | [SQLAlchemyMd5Cache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.SQLAlchemyMd5Cache.html) |\n",
     "| langchain_community.cache | [UpstashRedisCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.UpstashRedisCache.html) |\n",

docs/docs/integrations/llms/gpt4all.ipynb

@@ -14,21 +14,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  gpt4all > /dev/null"
+    "%pip install --upgrade --quiet langchain-community gpt4all"
    ]
   },
   {
@@ -47,9 +39,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.chains import LLMChain\n",
     "from langchain_community.llms import GPT4All\n",
-    "from langchain_core.callbacks import StreamingStdOutCallbackHandler\n",
     "from langchain_core.prompts import PromptTemplate"
    ]
   },
@@ -92,64 +82,79 @@
     "\n",
     "For more info, visit https://github.com/nomic-ai/gpt4all.\n",
     "\n",
-    "---"
+    "---\n",
+    "\n",
+    "This integration does not yet support streaming in chunks via the [`.stream()`](https://python.langchain.com/v0.2/docs/how_to/streaming/) method. The below example uses a callback handler with `streaming=True`:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
     "local_path = (\n",
-    "    \"./models/ggml-gpt4all-l13b-snoozy.bin\"  # replace with your desired local file path\n",
+    "    \"./models/Meta-Llama-3-8B-Instruct.Q4_0.gguf\"  # replace with your local file path\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Token:  Justin\n",
+      "Token:  Bieber\n",
+      "Token:  was\n",
+      "Token:  born\n",
+      "Token:  on\n",
+      "Token:  March\n",
+      "Token:  \n",
+      "Token: 1\n",
+      "Token: ,\n",
+      "Token:  \n"
+     ]
+    }
+   ],
    "source": [
-    "# Callbacks support token-wise streaming\n",
-    "callbacks = [StreamingStdOutCallbackHandler()]\n",
+    "from langchain_core.callbacks import BaseCallbackHandler\n",
+    "\n",
+    "count = 0\n",
+    "\n",
+    "\n",
+    "class MyCustomHandler(BaseCallbackHandler):\n",
+    "    def on_llm_new_token(self, token: str, **kwargs) -> None:\n",
+    "        global count\n",
+    "        if count < 10:\n",
+    "            print(f\"Token: {token}\")\n",
+    "            count += 1\n",
+    "\n",
     "\n",
     "# Verbose is required to pass to the callback manager\n",
-    "llm = GPT4All(model=local_path, callbacks=callbacks, verbose=True)\n",
+    "llm = GPT4All(model=local_path, callbacks=[MyCustomHandler()], streaming=True)\n",
     "\n",
     "# If you want to use a custom model add the backend parameter\n",
     "# Check https://docs.gpt4all.io/gpt4all_python.html for supported backends\n",
-    "llm = GPT4All(model=local_path, backend=\"gptj\", callbacks=callbacks, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "# llm = GPT4All(model=local_path, backend=\"gptj\", callbacks=callbacks, streaming=True)\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "\n",
     "question = \"What NFL team won the Super Bowl in the year Justin Bieber was born?\"\n",
     "\n",
-    "llm_chain.run(question)"
+    "# Streamed tokens will be logged/aggregated via the passed callback\n",
+    "res = chain.invoke({\"question\": question})"
    ]
   },
   {
-   "attachments": {},
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
-   "source": [
-    "Justin Bieber was born on March 1, 1994. In 1994, The Cowboys won Super Bowl XXVIII."
-   ]
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

docs/docs/integrations/llms/huggingface_pipelines.ipynb

@@ -143,6 +143,25 @@
     "print(chain.invoke({\"question\": question}))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "5141dc4d",
+   "metadata": {},
+   "source": [
+    "Streaming repsonse."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f1819250-2db9-4143-b88a-12e92d4e2386",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for chunk in chain.stream(question):\n",
+    "    print(chunk, end=\"\", flush=True)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "dbbc3a37",

docs/docs/integrations/llms/openvino.ipynb

@@ -245,7 +245,7 @@
    "source": [
     "### Streaming\n",
     "\n",
-    "To get streaming of LLM output, you can create a Huggingface `TextIteratorStreamer` for `_forward_params`."
+    "You can use `stream` method to get a streaming of LLM output, "
    ]
   },
   {
@@ -255,24 +255,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from threading import Thread\n",
+    "generation_config = {\"skip_prompt\": True, \"pipeline_kwargs\": {\"max_new_tokens\": 100}}\n",
+    "chain = prompt | ov_llm.bind(**generation_config)\n",
     "\n",
-    "from transformers import TextIteratorStreamer\n",
-    "\n",
-    "streamer = TextIteratorStreamer(\n",
-    "    ov_llm.pipeline.tokenizer,\n",
-    "    timeout=30.0,\n",
-    "    skip_prompt=True,\n",
-    "    skip_special_tokens=True,\n",
-    ")\n",
-    "pipeline_kwargs = {\"pipeline_kwargs\": {\"streamer\": streamer, \"max_new_tokens\": 100}}\n",
-    "chain = prompt | ov_llm.bind(**pipeline_kwargs)\n",
-    "\n",
-    "t1 = Thread(target=chain.invoke, args=({\"question\": question},))\n",
-    "t1.start()\n",
-    "\n",
-    "for new_text in streamer:\n",
-    "    print(new_text, end=\"\", flush=True)"
+    "for chunk in chain.stream(question):\n",
+    "    print(chunk, end=\"\", flush=True)"
    ]
   },
   {

docs/docs/integrations/platforms/microsoft.mdx

@@ -223,9 +223,15 @@ See a [usage example](/docs/integrations/document_loaders/microsoft_onenote).
 from langchain_community.document_loaders.onenote import OneNoteLoader
 ```
 
-## Vector stores
+## AI Agent Memory System
 
-### Azure Cosmos DB MongoDB vCore
+[AI agent](https://learn.microsoft.com/en-us/azure/cosmos-db/ai-agents) needs robust memory systems that support multi-modality, offer strong operational performance, and enable agent memory sharing as well as separation.
+
+AI agents can rely on Azure Cosmos DB as a unified [memory system](https://learn.microsoft.com/en-us/azure/cosmos-db/ai-agents#memory-can-make-or-break-agents) solution, enjoying speed, scale, and simplicity. This service successfully [enabled OpenAI's ChatGPT service](https://www.youtube.com/watch?v=6IIUtEFKJec&t) to scale dynamically with high reliability and low maintenance. Powered by an atom-record-sequence engine, it is the world's first globally distributed [NoSQL](https://learn.microsoft.com/en-us/azure/cosmos-db/distributed-nosql), [relational](https://learn.microsoft.com/en-us/azure/cosmos-db/distributed-relational), and [vector database](https://learn.microsoft.com/en-us/azure/cosmos-db/vector-database) service that offers a serverless mode. 
+
+Below are two available Azure Cosmos DB APIs that can provide vector store functionalities.
+
+### Azure Cosmos DB for MongoDB (vCore)
 
 >[Azure Cosmos DB for MongoDB vCore](https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/) makes it easy to create a database with full native MongoDB support.
 > You can apply your MongoDB experience and continue to use your favorite MongoDB drivers, SDKs, and tools by pointing your application to the API for MongoDB vCore account's connection string.

docs/docs/integrations/providers/gpt4all.mdx

@@ -7,7 +7,7 @@ This page covers how to use the `GPT4All` wrapper within LangChain. The tutorial
 - Install the Python package with `pip install gpt4all`
 - Download a [GPT4All model](https://gpt4all.io/index.html) and place it in your desired directory
 
-In this example, We are using `mistral-7b-openorca.Q4_0.gguf`(Best overall fast chat model):
+In this example, we are using `mistral-7b-openorca.Q4_0.gguf`:
 
 ```bash
 mkdir models
@@ -30,7 +30,7 @@ model = GPT4All(model="./models/mistral-7b-openorca.Q4_0.gguf", n_threads=8)
 response = model.invoke("Once upon a time, ")
 ```
 
-You can also customize the generation parameters, such as n_predict, temp, top_p, top_k, and others.
+You can also customize the generation parameters, such as `n_predict`, `temp`, `top_p`, `top_k`, and others.
 
 To stream the model's predictions, add in a CallbackManager.
 
@@ -45,11 +45,11 @@ callbacks = [StreamingStdOutCallbackHandler()]
 model = GPT4All(model="./models/mistral-7b-openorca.Q4_0.gguf", n_threads=8)
 
 # Generate text. Tokens are streamed through the callback manager.
-model("Once upon a time, ", callbacks=callbacks)
+model.invoke("Once upon a time, ", callbacks=callbacks)
 ```
 
 ## Model File
 
-You can find links to model file downloads in the [https://gpt4all.io/](https://gpt4all.io/index.html).
+You can download model files from the GPT4All client. You can download the client from the [GPT4All](https://gpt4all.io/index.html) website.
 
 For a more detailed walkthrough of this, see [this notebook](/docs/integrations/llms/gpt4all)

docs/docs/integrations/providers/mlflow_tracking.ipynb

@@ -7,29 +7,19 @@
    "source": [
     "# MLflow\n",
     "\n",
-    ">[MLflow](https://www.mlflow.org/docs/latest/what-is-mlflow) is a versatile, expandable, open-source platform for managing workflows and artifacts across the machine learning lifecycle. It has built-in integrations with many popular ML libraries, but can be used with any library, algorithm, or deployment tool. It is designed to be extensible, so you can write plugins to support new workflows, libraries, and tools.\n",
+    ">[MLflow](https://mlflow.org/) is a versatile, open-source platform for managing workflows and artifacts across the machine learning lifecycle. It has built-in integrations with many popular ML libraries, but can be used with any library, algorithm, or deployment tool. It is designed to be extensible, so you can write plugins to support new workflows, libraries, and tools.\n",
     "\n",
-    "This notebook goes over how to track your LangChain experiments into your `MLflow Server`"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ea73efae-7182-4a89-a492-c865b1fcf981",
-   "metadata": {},
-   "source": [
-    "## External examples"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "97361a84-4e8f-45ba-b291-814cf73cd8f2",
-   "metadata": {},
-   "source": [
-    "`MLflow` provides [several examples](https://github.com/mlflow/mlflow/tree/master/examples/langchain) for the `LangChain` integration:\n",
-    "- [simple_chain](https://github.com/mlflow/mlflow/blob/master/examples/langchain/simple_chain.py)\n",
-    "- [simple_agent](https://github.com/mlflow/mlflow/blob/master/examples/langchain/simple_agent.py)\n",
-    "- [retriever_chain](https://github.com/mlflow/mlflow/blob/master/examples/langchain/retriever_chain.py)\n",
-    "- [retrieval_qa_chain](https://github.com/mlflow/mlflow/blob/master/examples/langchain/retrieval_qa_chain.py)\n"
+    "In the context of LangChain integration, MLflow provides the following capabilities:\n",
+    "\n",
+    "- **Experiment Tracking**: MLflow tracks and stores artifacts from your LangChain experiments, including models, code, prompts, metrics, and more.\n",
+    "- **Dependency Management**: MLflow automatically records model dependencies, ensuring consistency between development and production environments.\n",
+    "- **Model Evaluation** MLflow offers native capabilities for evaluating LangChain applications.\n",
+    "- **Tracing**: MLflow allows you to visually trace data flows through your LangChain chain, agent, retriever, or other components.\n",
+    "\n",
+    "\n",
+    "**Note**: The tracing capability is only available in MLflow versions 2.14.0 and later.\n",
+    "\n",
+    "This notebook demonstrates how to track your LangChain experiments using MLflow. For more information about this feature and to explore tutorials and examples of using LangChain with MLflow, please refer to the [MLflow documentation for LangChain integration](https://mlflow.org/docs/latest/llms/langchain/index.html)."
    ]
   },
   {
@@ -37,7 +27,37 @@
    "id": "e0cbd74b-1542-45a4-a72b-b2eedeffd2e0",
    "metadata": {},
    "source": [
-    "## Example"
+    "## Setup\n",
+    "\n",
+    "Install MLflow Python package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7fb27b941602401d91542211134fc71a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install google-search-results num"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "42406548",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install mlflow -qU"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e626bb4",
+   "metadata": {},
+   "source": [
+    "This example utilizes the OpenAI LLM. Feel free to skip the command below and proceed with a different LLM if desired."
    ]
   },
   {
@@ -47,142 +67,535 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  azureml-mlflow\n",
-    "%pip install --upgrade --quiet  pandas\n",
-    "%pip install --upgrade --quiet  textstat\n",
-    "%pip install --upgrade --quiet  spacy\n",
-    "%pip install --upgrade --quiet  langchain-openai\n",
-    "%pip install --upgrade --quiet  google-search-results\n",
-    "!python -m spacy download en_core_web_sm"
+    "%pip install langchain-openai -qU"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "bf8e1f5c",
+   "execution_count": 6,
+   "id": "7e87b21d",
    "metadata": {},
    "outputs": [],
    "source": [
     "import os\n",
     "\n",
+    "# Set MLflow tracking URI if you have MLflow Tracking Server running\n",
     "os.environ[\"MLFLOW_TRACKING_URI\"] = \"\"\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
-    "os.environ[\"SERPAPI_API_KEY\"] = \"\""
+    "os.environ[\"OPENAI_API_KEY\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "84616d96",
+   "metadata": {},
+   "source": [
+    "To begin, let's create a dedicated MLflow experiment in order track our model and artifacts. While you can opt to skip this step and use the default experiment, we strongly recommend organizing your runs and artifacts into separate experiments to avoid clutter and maintain a clean, structured workflow."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "fd49fd45",
+   "id": "155d2a6f",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.callbacks import MlflowCallbackHandler\n",
-    "from langchain_openai import OpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "578cac8c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\"\"\"Main function.\n",
+    "import mlflow\n",
     "\n",
-    "This function is used to try the callback handler.\n",
-    "Scenarios:\n",
-    "1. OpenAI LLM\n",
-    "2. Chain with multiple SubChains on multiple generations\n",
-    "3. Agent with Tools\n",
-    "\"\"\"\n",
-    "mlflow_callback = MlflowCallbackHandler()\n",
-    "llm = OpenAI(\n",
-    "    model_name=\"gpt-3.5-turbo\", temperature=0, callbacks=[mlflow_callback], verbose=True\n",
+    "mlflow.set_experiment(\"LangChain MLflow Integration\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "48accc76",
+   "metadata": {},
+   "source": [
+    "## Overview\n",
+    "\n",
+    "Integrate MLflow with your LangChain Application using one of the following methods:\n",
+    "\n",
+    "1. **Autologging**: Enable seamless tracking with the `mlflow.langchain.autolog()` command, our recommended first option for leveraging the LangChain MLflow integration.\n",
+    "2. **Manual Logging**: Use MLflow APIs to log LangChain chains and agents, providing fine-grained control over what to track in your experiment.\n",
+    "3. **Custom Callbacks**: Pass MLflow callbacks manually when invoking chains, allowing for semi-automated customization of your workload, such as tracking specific invocations."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c3f10055",
+   "metadata": {},
+   "source": [
+    "## Scenario 1: MLFlow Autologging"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "71118a27",
+   "metadata": {},
+   "source": [
+    "To get started with autologging, simply call `mlflow.langchain.autolog()`. In this example, we set the `log_models` parameter to `True`, which allows the chain definition and its dependency libraries to be recorded as an MLflow model, providing a comprehensive tracking experience."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "5b08145f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import mlflow\n",
+    "\n",
+    "mlflow.langchain.autolog(\n",
+    "    # These are optional configurations to control what information should be logged automatically (default: False)\n",
+    "    # For the full list of the arguments, refer to https://mlflow.org/docs/latest/llms/langchain/autologging.html#id1\n",
+    "    log_models=True,\n",
+    "    log_input_examples=True,\n",
+    "    log_model_signatures=True,\n",
     ")"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "9b20acae",
+   "cell_type": "markdown",
+   "id": "f0570c18",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "# SCENARIO 1 - LLM\n",
-    "llm_result = llm.generate([\"Tell me a joke\"])\n",
-    "\n",
-    "mlflow_callback.flush_tracker(llm)"
+    "### Define a Chain"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "8b872046",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains import LLMChain\n",
-    "from langchain_core.prompts import PromptTemplate"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 40,
    "id": "1b2627ef",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# SCENARIO 2 - Chain\n",
-    "template = \"\"\"You are a playwright. Given the title of play, it is your job to write a synopsis for that title.\n",
-    "Title: {title}\n",
-    "Playwright: This is a synopsis for the above play:\"\"\"\n",
-    "prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
-    "synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callbacks=[mlflow_callback])\n",
+    "from langchain.schema.output_parser import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "test_prompts = [\n",
-    "    {\n",
-    "        \"title\": \"documentary about good video games that push the boundary of game design\"\n",
-    "    },\n",
-    "]\n",
-    "synopsis_chain.apply(test_prompts)\n",
-    "mlflow_callback.flush_tracker(synopsis_chain)"
+    "llm = ChatOpenAI(model_name=\"gpt-4o\", temperature=0)\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "parser = StrOutputParser()\n",
+    "\n",
+    "chain = prompt | llm | parser"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a5b38bae",
+   "metadata": {},
+   "source": [
+    "### Invoke the Chain\n",
+    "\n",
+    "Note that this step may take a few seconds longer than usual, as MLflow runs several background tasks in the background to log models, traces, and artifacts to the tracking server."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "a1df4bc8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Ich liebe das Programmieren.'"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_input = {\n",
+    "    \"input_language\": \"English\",\n",
+    "    \"output_language\": \"German\",\n",
+    "    \"input\": \"I love programming.\",\n",
+    "}\n",
+    "\n",
+    "chain.invoke(test_input)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5173cdd4",
+   "metadata": {},
+   "source": [
+    "Take a moment to explore the MLflow Tracking UI, where you can gain a deeper understanding of what information are being logged.\n",
+    "* **Traces** -  Navigate to the \"Traces\" tab in the experiment and click the request ID link of the first row. The displayed trace tree visualizes the call stack of your chain invocation, providing you with a deep insight into how each component is executed within the chain.\n",
+    "* **MLflow Model** - As we set `log_model=True`, MLflow automatically creates an MLflow Run to track your chain definition. Navigate to the newest Run page and open the \"Artifacts\" tab, which lists file artifacts logged as an MLflow Model, including dependencies, input examples, model signatures, and more.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "36179573",
+   "metadata": {},
+   "source": [
+    "### Invoke the Logged Chain\n",
+    "\n",
+    "Next, let's load the model back and verify that we can reproduce the same prediction, ensuring consistency and reliability.\n",
+    "\n",
+    "There are two ways to load the model\n",
+    "1. `mlflow.langchain.load_model(MODEL_URI)` - This loads the model as the original LangChain object.\n",
+    "2. `mlflow.pyfunc.load_model(MODEL_URI)` - This loads the model within the `PythonModel` wrapper and encapsulates the prediction logic with the `predict()` API, which contains additional logic such as schema enforcement."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "a8e39d72",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Ich liebe Programmieren.'"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Replace YOUR_RUN_ID with the Run ID displayed on the MLflow UI\n",
+    "loaded_model = mlflow.langchain.load_model(\"runs:/{YOUR_RUN_ID}/model\")\n",
+    "loaded_model.invoke(test_input)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "9619356d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Ich liebe das Programmieren.']"
+      ]
+     },
+     "execution_count": 57,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pyfunc_model = mlflow.pyfunc.load_model(\"runs:/{YOUR_RUN_ID}/model\")\n",
+    "pyfunc_model.predict(test_input)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eb23a78c",
+   "metadata": {},
+   "source": [
+    "### Configure Autologging\n",
+    "\n",
+    "The `mlflow.langchain.autolog()` function offers several parameters that allow for fine-grained control over the artifacts logged to MLflow. For a comprehensive list of available configurations, please refer to the latest [MLflow LangChain Autologging Documentation](https://mlflow.org/docs/latest/llms/langchain/autologging.html)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1bf6bb02",
+   "metadata": {},
+   "source": [
+    "## Scenario 2: Manually Logging an Agent from Code"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6e447a02",
+   "metadata": {},
+   "source": [
+    "\n",
+    "#### Prerequisites\n",
+    "\n",
+    "This example uses `SerpAPI`, a search engine API, as a tool for the agent to retrieve Google Search results. LangChain is natively integrated with `SerpAPI`, allowing you to configure the tool for your agent with just one line of code.\n",
+    "\n",
+    "To get started:\n",
+    "\n",
+    "* Install the required Python package via pip: `pip install google-search-results numexpr`.\n",
+    "* Create an account at [SerpAPI's Official Website](https://serpapi.com/) and retrieve an API key.\n",
+    "* Set the API key in the environment variable: `os.environ[\"SERPAPI_API_KEY\"] = \"YOUR_API_KEY\"`\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d0c914e3",
+   "metadata": {},
+   "source": [
+    "### Define an Agent\n",
+    "\n",
+    "In this example, we will log the agent definition **as code**, rather than directly feeding the Python object and saving it in a serialized format. This approach offers several benefits:\n",
+    "\n",
+    "1. **No serialization required**: By saving the model as code, we avoid the need for serialization, which can be problematic when working with components that don't natively support it. This approach also eliminates the risk of incompatibility issues when deserializing the model in a different environment.\n",
+    "2. **Better transparency**: By inspecting the saved code file, you can gain valuable insights into what the model does. This is in contrast to serialized formats like pickle, where the model's behavior remains opaque until it's loaded back, potentially exposing security risks such as remote code execution.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9190a609",
+   "metadata": {},
+   "source": [
+    "First, create a separate `.py` file that defines the agent instance.\n",
+    "\n",
+    "In the interest of time, you can run the following cell to generate a Python file `agent.py`, which contains the agent definition code. In actual dev scenario, you would define it in another notebook or hand-crafted python script."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "id": "62b20e17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "script_content = \"\"\"\n",
+    "from langchain.agents import AgentType, initialize_agent, load_tools\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "import mlflow\n",
+    "\n",
+    "llm = ChatOpenAI(model_name=\"gpt-4o\", temperature=0)\n",
+    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
+    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION)\n",
+    "\n",
+    "# IMPORTANT: call set_model() to register the instance to be logged.\n",
+    "mlflow.models.set_model(agent)\n",
+    "\"\"\"\n",
+    "\n",
+    "with open(\"agent.py\", \"w\") as f:\n",
+    "    f.write(script_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "82a21f06",
+   "metadata": {},
+   "source": [
+    "### Log the Agent\n",
+    "\n",
+    "Return to the original notebook and run the following cell to log the agent you've defined in the `agent.py` file.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "cd5b8bcc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The agent is successfully logged to MLflow!\n"
+     ]
+    }
+   ],
+   "source": [
+    "question = \"How long would it take to drive to the Moon with F1 racing cars?\"\n",
+    "\n",
+    "with mlflow.start_run(run_name=\"search-math-agent\") as run:\n",
+    "    info = mlflow.langchain.log_model(\n",
+    "        lc_model=\"agent.py\",  # Specify the relative code path to the agent definition\n",
+    "        artifact_path=\"model\",\n",
+    "        input_example=question,\n",
+    "    )\n",
+    "\n",
+    "print(\"The agent is successfully logged to MLflow!\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b4687052",
+   "metadata": {},
+   "source": [
+    "Now, open the MLflow UI and navigate to the \"Artifacts\" tab in the Run detail page. You should see that the `agent.py` file has been successfully logged, along with other model artifacts, such as dependencies, input examples, and more."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9011db62",
+   "metadata": {},
+   "source": [
+    "### Invoke the Logged Agent\n",
+    "\n",
+    "Now load the agent back and invoke it. There are two ways to load the model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "b634b69d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Downloading artifacts: 100%|██████████| 10/10 [00:00<00:00, 331.57it/s]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "['It would take approximately 1194.5 hours to drive to the Moon with an F1 racing car.']"
+      ]
+     },
+     "execution_count": 53,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Let's turn on the autologging with default configuration, so we can see the trace for the agent invocation.\n",
+    "mlflow.langchain.autolog()\n",
+    "\n",
+    "# Load the model back\n",
+    "agent = mlflow.pyfunc.load_model(info.model_uri)\n",
+    "\n",
+    "# Invoke\n",
+    "agent.predict(question)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "30bf6133",
+   "metadata": {},
+   "source": [
+    "Navigate to the **\"Traces\"** tab in the experiment and click the request ID link of the first row. The trace visualizes how the agent operate multiple tasks within the single prediction call:\n",
+    "1. Determine what subtasks are required to answer the questions.\n",
+    "2. Search for the speed of an F1 racing car.\n",
+    "3. Search for the distance from Earth to Moon.\n",
+    "4. Compute the division using LLM."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cbd10f34",
+   "metadata": {},
+   "source": [
+    "## Scenario 3. Using MLflow Callbacks\n",
+    "\n",
+    "**MLflow Callbacks** provide a semi-automated way to track your LangChain application in MLflow. There are two primary callbacks available:\n",
+    "\n",
+    "1. **`MlflowLangchainTracer`:** Primarily used for generating traces, available in `mlflow >= 2.14.0`.\n",
+    "2. **`MLflowCallbackHandler`:** Logs metrics and artifacts to the MLflow tracking server."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d013d309",
+   "metadata": {},
+   "source": [
+    "### MlflowLangchainTracer\n",
+    "\n",
+    "When the chain or agent is invoked with the `MlflowLangchainTracer` callback, MLflow will automatically generate a trace for the call stack and log it to the MLflow tracking server.  The outcome is exactly same as `mlflow.langchain.autolog()`, but this is particularly useful when you want to only trace specific invocation. Autologging is applied to all invocation in the same notebook/script, on the other hand."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "e002823a",
-   "metadata": {
-    "id": "_jN73xcPVEpI"
-   },
+   "id": "46d48044",
+   "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.agents import AgentType, initialize_agent, load_tools"
+    "from mlflow.langchain.langchain_tracer import MlflowLangchainTracer\n",
+    "\n",
+    "mlflow_tracer = MlflowLangchainTracer()\n",
+    "\n",
+    "# This call generates a trace\n",
+    "chain.invoke(test_input, config={\"callbacks\": [mlflow_tracer]})\n",
+    "\n",
+    "# This call does not generate a trace\n",
+    "chain.invoke(test_input)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "acb6692c",
+   "metadata": {},
+   "source": [
+    "#### Where to Pass the Callback\n",
+    " LangChain supports two ways of passing callback instances: (1) Request time callbacks - pass them to the `invoke` method or bind with `with_config()` (2) Constructor callbacks - set them in the chain constructor. When using the `MlflowLangchainTracer` as a callback, you **must use request time callbacks**. Setting it in the constructor instead will only apply the callback to the top-level object, preventing it from being propagated to child components, resulting in incomplete traces. For more information on this behavior, please refer to [Callbacks Documentation](https://python.langchain.com/v0.2/docs/concepts/#callbacks) for more details.\n",
+    "\n",
+    "```python\n",
+    "# OK\n",
+    "chain.invoke(test_input, config={\"callbacks\": [mlflow_tracer]})\n",
+    "chain.with_config(callbacks=[mlflow_tracer])\n",
+    "# NG\n",
+    "chain = TheNameOfSomeChain(callbacks=[mlflow_tracer])\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d6a60ba7",
+   "metadata": {},
+   "source": [
+    "#### Supported Methods\n",
+    "\n",
+    "`MlflowLangchainTracer` supports the following invocation methods from the [Runnable Interfaces](https://python.langchain.com/v0.1/docs/expression_language/interface/).\n",
+    "-  Standard interfaces: `invoke`, `stream`, `batch`\n",
+    "-  Async interfaces: `astream`, `ainvoke`, `abatch`, `astream_log`, `astream_events`\n",
+    "\n",
+    "Other methods are not guaranteed to be fully compatible."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a72e8854",
+   "metadata": {},
+   "source": [
+    "### MlflowCallbackHandler\n",
+    "\n",
+    "`MlflowCallbackHandler` is a callback handler that resides in the LangChain Community code base.\n",
+    "\n",
+    "This callback can be passed for chain/agent invocation, but it must be explicitly finished by calling the `flush_tracker()` method.\n",
+    "\n",
+    "When a chain is invoked with the callback, it performs the following actions:\n",
+    "\n",
+    "1. Creates a new MLflow Run or retrieves an active one if available within the active MLflow Experiment.\n",
+    "2. Logs metrics such as the number of LLM calls, token usage, and other relevant metrics. If the chain/agent includes LLM call and you have `spacy` library installed, it logs text complexity metrics such as `flesch_kincaid_grade`.\n",
+    "3. Logs internal steps as a JSON file (this is a legacy version of traces).\n",
+    "4. Logs chain input and output as a Pandas Dataframe.\n",
+    "5. Calls the `flush_tracker()` method with a chain/agent instance, logging the chain/agent as an MLflow Model.\n"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "655bd47e",
-   "metadata": {
-    "id": "Gpq4rk6VT9cu"
-   },
+   "id": "b579aae1",
+   "metadata": {},
    "outputs": [],
    "source": [
-    "# SCENARIO 3 - Agent with Tools\n",
-    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callbacks=[mlflow_callback])\n",
-    "agent = initialize_agent(\n",
-    "    tools,\n",
-    "    llm,\n",
-    "    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
-    "    callbacks=[mlflow_callback],\n",
-    "    verbose=True,\n",
-    ")\n",
-    "agent.run(\n",
-    "    \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",
-    ")\n",
-    "mlflow_callback.flush_tracker(agent, finish=True)"
+    "from langchain_community.callbacks import MlflowCallbackHandler\n",
+    "\n",
+    "mlflow_callback = MlflowCallbackHandler()\n",
+    "\n",
+    "chain.invoke(\"What is LangChain callback?\", config={\"callbacks\": [mlflow_callback]})\n",
+    "\n",
+    "mlflow_callback.flush_tracker()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "84924e35",
+   "metadata": {},
+   "source": [
+    "## References\n",
+    "To learn more about the feature and visit tutorials and examples of using LangChain with MLflow, please refer to the [MLflow documentation for LangChain integration](https://mlflow.org/docs/latest/llms/langchain/index.html).\n",
+    "\n",
+    "`MLflow` also provides several [tutorials](https://mlflow.org/docs/latest/llms/langchain/index.html#getting-started-with-the-mlflow-langchain-flavor-tutorials-and-guides) and [examples](https://github.com/mlflow/mlflow/tree/master/examples/langchain) for the `LangChain` integration:\n",
+    "- [Quick Start](https://mlflow.org/docs/latest/llms/langchain/notebooks/langchain-quickstart.html)\n",
+    "- [RAG Tutorial](https://mlflow.org/docs/latest/llms/langchain/notebooks/langchain-retriever.html)\n",
+    "- [Agent Example](https://github.com/mlflow/mlflow/blob/master/examples/langchain/simple_agent.py)"
    ]
   }
  ],
@@ -191,9 +604,9 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "tracing",
    "language": "python",
-   "name": "python3"
+   "name": "tracing"
   },
   "language_info": {
    "codemirror_mode": {
@@ -205,7 +618,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,

docs/docs/integrations/providers/pebblo/pebblo_retrieval_qa.ipynb

@@ -60,6 +60,7 @@
     "**PebbloRetrievalQA chain supports the following vector databases:**\n",
     "- Qdrant\n",
     "- Pinecone\n",
+    "- Postgres(utilizing the pgvector extension)\n",
     "\n",
     "\n",
     "**Load vector database with authorization and semantic information in metadata:**\n",

docs/docs/integrations/text_embedding/azureopenai.ipynb

@@ -27,7 +27,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet langchain_openai"
+    "%pip install --upgrade --quiet langchain-openai"
    ]
   },
   {

docs/docs/integrations/toolkits/jira.ipynb

@@ -14,7 +14,8 @@
     "To use this tool, you must first set as environment variables:\n",
     "    JIRA_API_TOKEN\n",
     "    JIRA_USERNAME\n",
-    "    JIRA_INSTANCE_URL"
+    "    JIRA_INSTANCE_URL\n",
+    "    JIRA_CLOUD"
    ]
   },
   {
@@ -88,7 +89,8 @@
     "os.environ[\"JIRA_API_TOKEN\"] = \"abc\"\n",
     "os.environ[\"JIRA_USERNAME\"] = \"123\"\n",
     "os.environ[\"JIRA_INSTANCE_URL\"] = \"https://jira.atlassian.com\"\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"xyz\""
+    "os.environ[\"OPENAI_API_KEY\"] = \"xyz\"\n",
+    "os.environ[\"JIRA_CLOUD\"] = \"True\""
    ]
   },
   {

docs/docs/integrations/tools/google_drive.ipynb

@@ -99,7 +99,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_googldrive.tools.google_drive.tool import GoogleDriveSearchTool\n",
+    "from langchain_googledrive.tools.google_drive.tool import GoogleDriveSearchTool\n",
     "from langchain_googledrive.utilities.google_drive import GoogleDriveAPIWrapper\n",
     "\n",
     "# By default, search only in the filename.\n",

docs/docs/integrations/vectorstores/annoy.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Annoy\n",
     "\n",
-    "> [Annoy](https://github.com/spotify/annoy) (`Approximate Nearest Neighbors Oh Yeah`) is a C++ library with Python bindings to search for points in space that are close to a given query point. It also creates large read-only file-based data structures that are mmapped into memory so that many processes may share the same data.\n",
+    "> [Annoy](https://github.com/spotify/annoy) (`Approximate Nearest Neighbors Oh Yeah`) is a C++ library with Python bindings to search for points in space that are close to a given query point. It also creates large read-only file-based data structures that are mapped into memory so that many processes may share the same data.\n",
     "\n",
     "You'll need to install `langchain-community` with `pip install -qU langchain-community` to use this integration\n",
     "\n",

docs/docs/tutorials/chatbot.ipynb

@@ -270,8 +270,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.chat_message_histories import ChatMessageHistory\n",
-    "from langchain_core.chat_history import BaseChatMessageHistory\n",
+    "from langchain_core.chat_history import (\n",
+    "    BaseChatMessageHistory,\n",
+    "    InMemoryChatMessageHistory,\n",
+    ")\n",
     "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
     "\n",
     "store = {}\n",
@@ -279,7 +281,7 @@
     "\n",
     "def get_session_history(session_id: str) -> BaseChatMessageHistory:\n",
     "    if session_id not in store:\n",
-    "        store[session_id] = ChatMessageHistory()\n",
+    "        store[session_id] = InMemoryChatMessageHistory()\n",
     "    return store[session_id]\n",
     "\n",
     "\n",

docs/docs/tutorials/llm_chain.ipynb

@@ -325,7 +325,7 @@
    "id": "fedf6f13",
    "metadata": {},
    "source": [
-    "Next, we can create the PromptTemplate. This will be a combination of the `system_template` as well as a simpler template for where the put the text"
+    "Next, we can create the PromptTemplate. This will be a combination of the `system_template` as well as a simpler template for where to put the text to be translated"
    ]
   },
   {
@@ -538,7 +538,7 @@
     "\n",
     "### Client\n",
     "\n",
-    "Now let's set up a client for programmatically interacting with our service. We can easily do this with the `[langserve.RemoteRunnable](/docs/langserve/#client)`.\n",
+    "Now let's set up a client for programmatically interacting with our service. We can easily do this with the [langserve.RemoteRunnable](/docs/langserve/#client).\n",
     "Using this, we can interact with the served chain as if it were running client-side."
    ]
   },

docs/docs/tutorials/summarization.ipynb

@@ -640,7 +640,7 @@
    "metadata": {},
    "source": [
     "## Splitting and summarizing in a single chain\n",
-    "For convenience, we can wrap both the text splitting of our long document and summarizing in a single `AnalyzeDocumentsChain`."
+    "For convenience, we can wrap both the text splitting of our long document and summarizing in a single [chain](/docs/how_to/sequence):"
    ]
   },
   {
@@ -650,12 +650,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains import AnalyzeDocumentChain\n",
+    "def split_text(text: str):\n",
+    "    return text_splitter.create_documents([text])\n",
     "\n",
-    "summarize_document_chain = AnalyzeDocumentChain(\n",
-    "    combine_docs_chain=chain, text_splitter=text_splitter\n",
-    ")\n",
-    "summarize_document_chain.invoke(docs[0].page_content)"
+    "\n",
+    "summarize_document_chain = split_text | chain"
    ]
   },
   {

docs/docs/versions/v0_2/deprecations.mdx

@@ -568,6 +568,8 @@ Removal: 0.3.0
 
 Alternative: [RunnableSequence](/docs/how_to/sequence/), e.g., `prompt | llm`
 
+This [migration guide](/docs/how_to/migrate_chains/#llmchain) has a side-by-side comparison.
+
 
 #### LLMSingleActionAgent
 
@@ -754,6 +756,7 @@ Removal: 0.3.0
 
 
 Alternative: [create_retrieval_chain](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html#langchain-chains-retrieval-create-retrieval-chain)
+This [migration guide](/docs/how_to/migrate_chains/#retrievalqa) has a side-by-side comparison.
 
 
 #### load_agent_from_config
@@ -820,6 +823,7 @@ Removal: 0.3.0
 
 
 Alternative: [create_history_aware_retriever](https://api.python.langchain.com/en/latest/chains/langchain.chains.history_aware_retriever.create_history_aware_retriever.html) together with [create_retrieval_chain](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html#langchain-chains-retrieval-create-retrieval-chain) (see example in docstring)
+This [migration guide](/docs/how_to/migrate_chains/#conversationalretrievalchain) has a side-by-side comparison.
 
 
 #### create_extraction_chain_pydantic

docs/docs/versions/v0_2/index.mdx

@@ -11,6 +11,7 @@ LangChain v0.2 was released in May 2024. This release includes a number of [brea
 :::note Reference
 
 - [Breaking Changes & Deprecations](/docs/versions/v0_2/deprecations)
+- [Migrating legacy chains to LCEL](/docs/how_to/migrate_chains/)
 - [Migrating to Astream Events v2](/docs/versions/v0_2/migrating_astream_events)
 
 :::

docs/docusaurus.config.js

@@ -275,10 +275,6 @@ const config = {
           {
             title: "Community",
             items: [
-              {
-                label: "Discord",
-                href: "https://discord.gg/cU2adEyC7w",
-              },
               {
                 label: "Twitter",
                 href: "https://twitter.com/LangChainAI",

docs/ignore-step.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+echo "VERCEL_ENV: $VERCEL_ENV"
+echo "VERCEL_GIT_COMMIT_REF: $VERCEL_GIT_COMMIT_REF"
+
+
+if [ "$VERCEL_ENV" == "production" ] || [ "$VERCEL_GIT_COMMIT_REF" == "master" ] || [ "$VERCEL_GIT_COMMIT_REF" == "v0.1" ]; then 
+    echo "✅ Production build - proceeding with build"
+    exit 1; 
+else 
+    echo "Checking for changes in docs/ and templates/:"
+    echo "---"
+    git log -n 50 --pretty=format:"%s" -- . ../templates | grep -v '(#'
+    if [ $? -eq 0 ]; then
+        echo "---"
+        echo "✅ Changes detected in docs/ or templates/ - proceeding with build"
+        exit 1
+    else
+        echo "---"
+        echo "🛑 No changes detected in docs/ or templates/ - ignoring build"
+        exit 0
+    fi
+fi

docs/scripts/document_loader_feat_table.py

@@ -23,6 +23,18 @@ The following table shows the feature support for all document loaders.
 
 """
 
+DEPRECATED = [
+    "AirbyteCDKLoader",
+    "AirbyteGongLoader",
+    "AirbyteHubspotLoader",
+    "AirbyteJSONLoader",
+    "AirbyteSalesforceLoader",
+    "AirbyteShopifyLoader",
+    "AirbyteStripeLoader",
+    "AirbyteTypeformLoader",
+    "AirbyteZendeskSupportLoader",
+]
+
 
 def get_document_loader_table() -> str:
     """Get the table of document loaders."""
@@ -55,7 +67,7 @@ def get_document_loader_table() -> str:
     title = ["Document Loader", "Description", "Lazy loading", "Native async support"]
     rows = [title, [":-"] * 2 + [":-:"] * (len(title) - 2)]
     for loader, feats in sorted(doc_loaders_feat_table.items()):
-        if not feats:
+        if not feats or loader in DEPRECATED:
             continue
         rows += [
             [loader, feats["description"]]

docs/src/theme/Columns.js

@@ -10,7 +10,7 @@ export function ColumnContainer({children}) {
 
 export function Column({children}) {
     return (
-        <div style={{ flex: "1 0 300px", padding: "10px", overflowX: "clip", zoom: '80%' }}>
+        <div style={{ flex: "1 0 300px", padding: "10px", overflowX: "scroll", zoom: '80%' }}>
             {children}
         </div>
     )

docs/vercel.json

@@ -1,6 +1,7 @@
 {
   "buildCommand": "yarn build",
   "outputDirectory": "build",
+  "ignoreCommand": "bash ignore-step.sh",
   "trailingSlash": true,
   "rewrites": [
     {

libs/cli/langchain_cli/integration_template/integration_template/document_loaders.py

@@ -61,7 +61,7 @@ class __ModuleName__Loader(BaseLoader):
         .. code-block:: python
 
             TODO: Example output
-    """
+    """  # noqa: E501
 
     # TODO: This method must be implemented to load documents.
     # Do not implement load(), a default implementation is already available.

libs/cli/langchain_cli/integration_template/integration_template/vectorstores.py

@@ -1,4 +1,5 @@
 """__ModuleName__ vector stores."""
+
 from __future__ import annotations
 
 import asyncio

libs/cli/langchain_cli/integration_template/pyproject.toml

@@ -38,10 +38,10 @@ optional = true
 optional = true
 
 [tool.poetry.group.lint.dependencies]
-ruff = "^0.1.8"
+ruff = "^0.5"
 
 [tool.poetry.group.typing.dependencies]
-mypy = "^1.7.1"
+mypy = "^1.10"
 langchain-core = { path = "../../core", develop = true }
 
 [tool.poetry.group.dev]

libs/cli/langchain_cli/integration_template/tests/integration_tests/test_chat_models.py

@@ -1,4 +1,5 @@
 """Test Chat__ModuleName__ chat model."""
+
 from __module_name__.chat_models import Chat__ModuleName__
 
 

libs/cli/langchain_cli/integration_template/tests/integration_tests/test_embeddings.py

@@ -1,4 +1,5 @@
 """Test __ModuleName__ embeddings."""
+
 from __module_name__.embeddings import __ModuleName__Embeddings
 
 

libs/cli/langchain_cli/integration_template/tests/integration_tests/test_llms.py

@@ -1,4 +1,5 @@
 """Test __ModuleName__LLM llm."""
+
 from __module_name__.llms import __ModuleName__LLM
 
 

libs/cli/langchain_cli/integration_template/tests/unit_tests/test_chat_models.py

@@ -1,6 +1,5 @@
 """Test chat model integration."""
 
-
 from __module_name__.chat_models import Chat__ModuleName__
 
 

libs/cli/langchain_cli/integration_template/tests/unit_tests/test_embeddings.py

@@ -1,6 +1,5 @@
 """Test embedding model integration."""
 
-
 from __module_name__.embeddings import __ModuleName__Embeddings
 
 

libs/cli/langchain_cli/integration_template/tests/unit_tests/test_llms.py

@@ -1,4 +1,5 @@
 """Test __ModuleName__ Chat API wrapper."""
+
 from __module_name__ import __ModuleName__LLM
 
 

libs/cli/langchain_cli/namespaces/integration.py

@@ -1,6 +1,7 @@
 """
 Develop integration packages for LangChain.
 """
+
 import re
 import shutil
 import subprocess
@@ -154,7 +155,8 @@ def create_doc(
         str,
         typer.Option(
             help=(
-                "The type of component. Currently only 'ChatModel', 'DocumentLoader' supported."
+                "The type of component. Currently only 'ChatModel', 'DocumentLoader' "
+                "supported."
             ),
         ),
     ] = "ChatModel",

libs/cli/langchain_cli/namespaces/migrate/codemods/replace_imports.py

@@ -10,6 +10,7 @@ This codemod deals with the following cases:
 4. `from pydantic.settings import BaseSettings as <name>`  # TODO: This is not working.
 5. `import pydantic` -> `pydantic.BaseSettings`
 """
+
 from __future__ import annotations
 
 import json

libs/cli/langchain_cli/namespaces/migrate/generate/generic.py

@@ -1,4 +1,5 @@
 """Generate migrations from langchain to langchain-community or core packages."""
+
 import importlib
 import inspect
 import pkgutil

libs/cli/langchain_cli/namespaces/migrate/generate/partner.py

@@ -1,4 +1,5 @@
 """Generate migrations for partner packages."""
+
 import importlib
 from typing import List, Tuple
 

libs/cli/langchain_cli/namespaces/migrate/main.py

@@ -1,4 +1,5 @@
 """Migrate LangChain to the most recent version."""
+
 # Adapted from bump-pydantic
 # https://github.com/pydantic/bump-pydantic
 import difflib

libs/cli/poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
 
 [[package]]
 name = "aiohttp"
@@ -1384,28 +1384,29 @@ jupyter = ["ipywidgets (>=7.5.1,<9)"]
 
 [[package]]
 name = "ruff"
-version = "0.1.15"
+version = "0.5.0"
 description = "An extremely fast Python linter and code formatter, written in Rust."
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "ruff-0.1.15-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:5fe8d54df166ecc24106db7dd6a68d44852d14eb0729ea4672bb4d96c320b7df"},
-    {file = "ruff-0.1.15-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:6f0bfbb53c4b4de117ac4d6ddfd33aa5fc31beeaa21d23c45c6dd249faf9126f"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e0d432aec35bfc0d800d4f70eba26e23a352386be3a6cf157083d18f6f5881c8"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:9405fa9ac0e97f35aaddf185a1be194a589424b8713e3b97b762336ec79ff807"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c66ec24fe36841636e814b8f90f572a8c0cb0e54d8b5c2d0e300d28a0d7bffec"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:6f8ad828f01e8dd32cc58bc28375150171d198491fc901f6f98d2a39ba8e3ff5"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:86811954eec63e9ea162af0ffa9f8d09088bab51b7438e8b6488b9401863c25e"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fd4025ac5e87d9b80e1f300207eb2fd099ff8200fa2320d7dc066a3f4622dc6b"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b17b93c02cdb6aeb696effecea1095ac93f3884a49a554a9afa76bb125c114c1"},
-    {file = "ruff-0.1.15-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:ddb87643be40f034e97e97f5bc2ef7ce39de20e34608f3f829db727a93fb82c5"},
-    {file = "ruff-0.1.15-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:abf4822129ed3a5ce54383d5f0e964e7fef74a41e48eb1dfad404151efc130a2"},
-    {file = "ruff-0.1.15-py3-none-musllinux_1_2_i686.whl", hash = "sha256:6c629cf64bacfd136c07c78ac10a54578ec9d1bd2a9d395efbee0935868bf852"},
-    {file = "ruff-0.1.15-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:1bab866aafb53da39c2cadfb8e1c4550ac5340bb40300083eb8967ba25481447"},
-    {file = "ruff-0.1.15-py3-none-win32.whl", hash = "sha256:2417e1cb6e2068389b07e6fa74c306b2810fe3ee3476d5b8a96616633f40d14f"},
-    {file = "ruff-0.1.15-py3-none-win_amd64.whl", hash = "sha256:3837ac73d869efc4182d9036b1405ef4c73d9b1f88da2413875e34e0d6919587"},
-    {file = "ruff-0.1.15-py3-none-win_arm64.whl", hash = "sha256:9a933dfb1c14ec7a33cceb1e49ec4a16b51ce3c20fd42663198746efc0427360"},
-    {file = "ruff-0.1.15.tar.gz", hash = "sha256:f6dfa8c1b21c913c326919056c390966648b680966febcb796cc9d1aaab8564e"},
+    {file = "ruff-0.5.0-py3-none-linux_armv6l.whl", hash = "sha256:ee770ea8ab38918f34e7560a597cc0a8c9a193aaa01bfbd879ef43cb06bd9c4c"},
+    {file = "ruff-0.5.0-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:38f3b8327b3cb43474559d435f5fa65dacf723351c159ed0dc567f7ab735d1b6"},
+    {file = "ruff-0.5.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:7594f8df5404a5c5c8f64b8311169879f6cf42142da644c7e0ba3c3f14130370"},
+    {file = "ruff-0.5.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:adc7012d6ec85032bc4e9065110df205752d64010bed5f958d25dbee9ce35de3"},
+    {file = "ruff-0.5.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d505fb93b0fabef974b168d9b27c3960714d2ecda24b6ffa6a87ac432905ea38"},
+    {file = "ruff-0.5.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9dc5cfd3558f14513ed0d5b70ce531e28ea81a8a3b1b07f0f48421a3d9e7d80a"},
+    {file = "ruff-0.5.0-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:db3ca35265de239a1176d56a464b51557fce41095c37d6c406e658cf80bbb362"},
+    {file = "ruff-0.5.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b1a321c4f68809fddd9b282fab6a8d8db796b270fff44722589a8b946925a2a8"},
+    {file = "ruff-0.5.0-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2c4dfcd8d34b143916994b3876b63d53f56724c03f8c1a33a253b7b1e6bf2a7d"},
+    {file = "ruff-0.5.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:81e5facfc9f4a674c6a78c64d38becfbd5e4f739c31fcd9ce44c849f1fad9e4c"},
+    {file = "ruff-0.5.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:e589e27971c2a3efff3fadafb16e5aef7ff93250f0134ec4b52052b673cf988d"},
+    {file = "ruff-0.5.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:d2ffbc3715a52b037bcb0f6ff524a9367f642cdc5817944f6af5479bbb2eb50e"},
+    {file = "ruff-0.5.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:cd096e23c6a4f9c819525a437fa0a99d1c67a1b6bb30948d46f33afbc53596cf"},
+    {file = "ruff-0.5.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:46e193b36f2255729ad34a49c9a997d506e58f08555366b2108783b3064a0e1e"},
+    {file = "ruff-0.5.0-py3-none-win32.whl", hash = "sha256:49141d267100f5ceff541b4e06552e98527870eafa1acc9dec9139c9ec5af64c"},
+    {file = "ruff-0.5.0-py3-none-win_amd64.whl", hash = "sha256:e9118f60091047444c1b90952736ee7b1792910cab56e9b9a9ac20af94cd0440"},
+    {file = "ruff-0.5.0-py3-none-win_arm64.whl", hash = "sha256:ed5c4df5c1fb4518abcb57725b576659542bdbe93366f4f329e8f398c4b71178"},
+    {file = "ruff-0.5.0.tar.gz", hash = "sha256:eb641b5873492cf9bd45bc9c5ae5320648218e04386a5f0c264ad6ccce8226a1"},
 ]
 
 [[package]]
@@ -1836,4 +1837,4 @@ serve = []
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.1,<4.0"
-content-hash = "4576fb13ecd9e13bc6c85e4cd6f56520708c7c1468f4b81bc6a346b128c9f695"
+content-hash = "f549b3468a0b27c75b171c3a4efd8df9c3b3ae737c7e097ffc3fb6fb0fe5f2ef"

libs/cli/pyproject.toml

@@ -29,7 +29,7 @@ pytest = "^7.4.2"
 pytest-watch = "^4.2.0"
 
 [tool.poetry.group.lint.dependencies]
-ruff = "^0.1.5"
+ruff = "^0.5"
 
 [tool.poetry.group.test.dependencies]
 
@@ -62,9 +62,9 @@ _bump_2.uses = { version = "version" }
 
 _bump_1 = "poetry version patch"
 _check_formatting = "poetry run ruff format . --diff"
-_lint = "poetry run ruff ."
+_lint = "poetry run ruff check ."
 _format = "poetry run ruff format ."
-_lint_fix = "poetry run ruff . --fix"
+_lint_fix = "poetry run ruff check . --fix"
 
 [build-system]
 requires = ["poetry-core"]

libs/cli/scripts/generate_migrations.py

@@ -1,4 +1,5 @@
 """Script to generate migrations for the migration script."""
+
 import json
 import pkgutil
 

libs/cli/tests/unit_tests/migrate/cli_runner/cases/imports_with_alias_changes.py

@@ -1,4 +1,5 @@
 """Handle a test case where the import is updated and may involve an alias change."""
+
 from tests.unit_tests.migrate.cli_runner.case import Case
 from tests.unit_tests.migrate.cli_runner.file import File
 

libs/cli/tests/unit_tests/migrate/test_code_migrations.py

@@ -3,6 +3,7 @@
 Migration script only updates imports not the rest of the code that uses the
 import.
 """
+
 from langchain_cli.namespaces.migrate.codemods.replace_imports import (
     RULE_TO_PATHS,
     _load_migrations_from_fixtures,

libs/community/Makefile

@@ -46,16 +46,16 @@ lint_tests: MYPY_CACHE=.mypy_cache_test
 
 lint lint_diff lint_package lint_tests:
 	./scripts/check_pydantic.sh .
-	./scripts/lint_imports.sh
+	./scripts/lint_imports.sh .
 	./scripts/check_pickle.sh .
-	poetry run ruff .
+	poetry run ruff check .
 	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) --diff
-	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff --select I $(PYTHON_FILES)
+	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff check --select I $(PYTHON_FILES)
 	[ "$(PYTHON_FILES)" = "" ] || mkdir -p $(MYPY_CACHE) && poetry run mypy $(PYTHON_FILES) --cache-dir $(MYPY_CACHE)
 
 format format_diff:
 	poetry run ruff format $(PYTHON_FILES)
-	poetry run ruff --select I --fix $(PYTHON_FILES)
+	poetry run ruff check --select I --fix $(PYTHON_FILES)
 
 spell_check:
 	poetry run codespell --toml pyproject.toml

libs/community/extended_testing_deps.txt

@@ -52,7 +52,7 @@ openapi-pydantic>=0.3.2,<0.4
 oracle-ads>=2.9.1,<3
 oracledb>=2.2.0,<3
 pandas>=2.0.1,<3
-pdfminer-six>=20221105
+pdfminer-six>=20221105,<20240706
 pgvector>=0.1.6,<0.2
 praw>=7.7.1,<8
 premai>=0.3.25,<0.4

libs/community/langchain_community/__init__.py

@@ -1,4 +1,5 @@
 """Main entrypoint into package."""
+
 from importlib import metadata
 
 try:

libs/community/langchain_community/adapters/openai.py

@@ -206,8 +206,7 @@ class ChatCompletion:
         provider: str = "ChatOpenAI",
         stream: Literal[False] = False,
         **kwargs: Any,
-    ) -> dict:
-        ...
+    ) -> dict: ...
 
     @overload
     @staticmethod
@@ -217,8 +216,7 @@ class ChatCompletion:
         provider: str = "ChatOpenAI",
         stream: Literal[True],
         **kwargs: Any,
-    ) -> Iterable:
-        ...
+    ) -> Iterable: ...
 
     @staticmethod
     def create(
@@ -249,8 +247,7 @@ class ChatCompletion:
         provider: str = "ChatOpenAI",
         stream: Literal[False] = False,
         **kwargs: Any,
-    ) -> dict:
-        ...
+    ) -> dict: ...
 
     @overload
     @staticmethod
@@ -260,8 +257,7 @@ class ChatCompletion:
         provider: str = "ChatOpenAI",
         stream: Literal[True],
         **kwargs: Any,
-    ) -> AsyncIterator:
-        ...
+    ) -> AsyncIterator: ...
 
     @staticmethod
     async def acreate(
@@ -319,8 +315,7 @@ class Completions:
         provider: str = "ChatOpenAI",
         stream: Literal[False] = False,
         **kwargs: Any,
-    ) -> ChatCompletions:
-        ...
+    ) -> ChatCompletions: ...
 
     @overload
     @staticmethod
@@ -330,8 +325,7 @@ class Completions:
         provider: str = "ChatOpenAI",
         stream: Literal[True],
         **kwargs: Any,
-    ) -> Iterable:
-        ...
+    ) -> Iterable: ...
 
     @staticmethod
     def create(
@@ -366,8 +360,7 @@ class Completions:
         provider: str = "ChatOpenAI",
         stream: Literal[False] = False,
         **kwargs: Any,
-    ) -> ChatCompletions:
-        ...
+    ) -> ChatCompletions: ...
 
     @overload
     @staticmethod
@@ -377,8 +370,7 @@ class Completions:
         provider: str = "ChatOpenAI",
         stream: Literal[True],
         **kwargs: Any,
-    ) -> AsyncIterator:
-        ...
+    ) -> AsyncIterator: ...
 
     @staticmethod
     async def acreate(

libs/community/langchain_community/agent_toolkits/file_management/toolkit.py

@@ -63,7 +63,7 @@ class FileManagementToolkit(BaseToolkit):
     selected_tools: Optional[List[str]] = None
     """If provided, only provide the selected tools. Defaults to all."""
 
-    @root_validator
+    @root_validator(pre=True)
     def validate_tools(cls, values: dict) -> dict:
         selected_tools = values.get("selected_tools") or []
         for tool_name in selected_tools:

libs/community/langchain_community/agent_toolkits/playwright/toolkit.py

@@ -74,7 +74,7 @@ class PlayWrightBrowserToolkit(BaseToolkit):
         extra = Extra.forbid
         arbitrary_types_allowed = True
 
-    @root_validator
+    @root_validator(pre=True)
     def validate_imports_and_browser_provided(cls, values: dict) -> dict:
         """Check that the arguments are valid."""
         lazy_import_playwright_browsers()

libs/community/langchain_community/cache.py

@@ -58,6 +58,7 @@ from langchain_community.vectorstores.azure_cosmos_db import (
     CosmosDBSimilarityType,
     CosmosDBVectorSearchType,
 )
+from langchain_community.vectorstores.utils import DistanceStrategy
 
 try:
     from sqlalchemy.orm import declarative_base
@@ -84,6 +85,7 @@ from langchain_community.vectorstores import (
     OpenSearchVectorSearch as OpenSearchVectorStore,
 )
 from langchain_community.vectorstores.redis import Redis as RedisVectorstore
+from langchain_community.vectorstores.singlestoredb import SingleStoreDB
 
 logger = logging.getLogger(__file__)
 
@@ -2189,14 +2191,14 @@ class AzureCosmosDBSemanticCache(BaseCache):
                 index_name=index_name,
             )
         else:
-            self._cache_dict[
-                index_name
-            ] = AzureCosmosDBVectorSearch.from_connection_string(
-                connection_string=self.cosmosdb_connection_string,
-                namespace=namespace,
-                embedding=self.embedding,
-                index_name=index_name,
-                application_name=self.application_name,
+            self._cache_dict[index_name] = (
+                AzureCosmosDBVectorSearch.from_connection_string(
+                    connection_string=self.cosmosdb_connection_string,
+                    namespace=namespace,
+                    embedding=self.embedding,
+                    index_name=index_name,
+                    application_name=self.application_name,
+                )
             )
 
         # create index for the vectorstore
@@ -2373,3 +2375,221 @@ class OpenSearchSemanticCache(BaseCache):
         if index_name in self._cache_dict:
             self._cache_dict[index_name].delete_index(index_name=index_name)
             del self._cache_dict[index_name]
+
+
+class SingleStoreDBSemanticCache(BaseCache):
+    """Cache that uses SingleStore DB as a backend"""
+
+    def __init__(
+        self,
+        embedding: Embeddings,
+        *,
+        cache_table_prefix: str = "cache_",
+        search_threshold: float = 0.2,
+        **kwargs: Any,
+    ):
+        """Initialize with necessary components.
+
+        Args:
+            embedding (Embeddings): A text embedding model.
+            cache_table_prefix (str, optional): Prefix for the cache table name.
+                Defaults to "cache_".
+            search_threshold (float, optional): The minimum similarity score for
+                a search result to be considered a match. Defaults to 0.2.
+
+            Following arguments pertrain to the SingleStoreDB vector store:
+
+            distance_strategy (DistanceStrategy, optional):
+                Determines the strategy employed for calculating
+                the distance between vectors in the embedding space.
+                Defaults to DOT_PRODUCT.
+                Available options are:
+                - DOT_PRODUCT: Computes the scalar product of two vectors.
+                    This is the default behavior
+                - EUCLIDEAN_DISTANCE: Computes the Euclidean distance between
+                    two vectors. This metric considers the geometric distance in
+                    the vector space, and might be more suitable for embeddings
+                    that rely on spatial relationships. This metric is not
+                    compatible with the WEIGHTED_SUM search strategy.
+
+            content_field (str, optional): Specifies the field to store the content.
+                Defaults to "content".
+            metadata_field (str, optional): Specifies the field to store metadata.
+                Defaults to "metadata".
+            vector_field (str, optional): Specifies the field to store the vector.
+                Defaults to "vector".
+            id_field (str, optional): Specifies the field to store the id.
+                Defaults to "id".
+
+            use_vector_index (bool, optional): Toggles the use of a vector index.
+                Works only with SingleStoreDB 8.5 or later. Defaults to False.
+                If set to True, vector_size parameter is required to be set to
+                a proper value.
+
+            vector_index_name (str, optional): Specifies the name of the vector index.
+                Defaults to empty. Will be ignored if use_vector_index is set to False.
+
+            vector_index_options (dict, optional): Specifies the options for
+                the vector index. Defaults to {}.
+                Will be ignored if use_vector_index is set to False. The options are:
+                index_type (str, optional): Specifies the type of the index.
+                    Defaults to IVF_PQFS.
+                For more options, please refer to the SingleStoreDB documentation:
+                https://docs.singlestore.com/cloud/reference/sql-reference/vector-functions/vector-indexing/
+
+            vector_size (int, optional): Specifies the size of the vector.
+                Defaults to 1536. Required if use_vector_index is set to True.
+                Should be set to the same value as the size of the vectors
+                stored in the vector_field.
+
+            Following arguments pertain to the connection pool:
+
+            pool_size (int, optional): Determines the number of active connections in
+                the pool. Defaults to 5.
+            max_overflow (int, optional): Determines the maximum number of connections
+                allowed beyond the pool_size. Defaults to 10.
+            timeout (float, optional): Specifies the maximum wait time in seconds for
+                establishing a connection. Defaults to 30.
+
+            Following arguments pertain to the database connection:
+
+            host (str, optional): Specifies the hostname, IP address, or URL for the
+                database connection. The default scheme is "mysql".
+            user (str, optional): Database username.
+            password (str, optional): Database password.
+            port (int, optional): Database port. Defaults to 3306 for non-HTTP
+                connections, 80 for HTTP connections, and 443 for HTTPS connections.
+            database (str, optional): Database name.
+
+            Additional optional arguments provide further customization over the
+            database connection:
+
+            pure_python (bool, optional): Toggles the connector mode. If True,
+                operates in pure Python mode.
+            local_infile (bool, optional): Allows local file uploads.
+            charset (str, optional): Specifies the character set for string values.
+            ssl_key (str, optional): Specifies the path of the file containing the SSL
+                key.
+            ssl_cert (str, optional): Specifies the path of the file containing the SSL
+                certificate.
+            ssl_ca (str, optional): Specifies the path of the file containing the SSL
+                certificate authority.
+            ssl_cipher (str, optional): Sets the SSL cipher list.
+            ssl_disabled (bool, optional): Disables SSL usage.
+            ssl_verify_cert (bool, optional): Verifies the server's certificate.
+                Automatically enabled if ``ssl_ca`` is specified.
+            ssl_verify_identity (bool, optional): Verifies the server's identity.
+            conv (dict[int, Callable], optional): A dictionary of data conversion
+                functions.
+            credential_type (str, optional): Specifies the type of authentication to
+                use: auth.PASSWORD, auth.JWT, or auth.BROWSER_SSO.
+            autocommit (bool, optional): Enables autocommits.
+            results_type (str, optional): Determines the structure of the query results:
+                tuples, namedtuples, dicts.
+            results_format (str, optional): Deprecated. This option has been renamed to
+                results_type.
+
+        Examples:
+            Basic Usage:
+
+            .. code-block:: python
+
+                import langchain
+                from langchain.cache import SingleStoreDBSemanticCache
+                from langchain.embeddings import OpenAIEmbeddings
+
+                langchain.llm_cache = SingleStoreDBSemanticCache(
+                    embedding=OpenAIEmbeddings(),
+                    host="https://user:password@127.0.0.1:3306/database"
+                )
+
+            Advanced Usage:
+
+            .. code-block:: python
+
+                import langchain
+                from langchain.cache import SingleStoreDBSemanticCache
+                from langchain.embeddings import OpenAIEmbeddings
+
+                langchain.llm_cache = = SingleStoreDBSemanticCache(
+                    embeddings=OpenAIEmbeddings(),
+                    use_vector_index=True,
+                    host="127.0.0.1",
+                    port=3306,
+                    user="user",
+                    password="password",
+                    database="db",
+                    table_name="my_custom_table",
+                    pool_size=10,
+                    timeout=60,
+                )
+        """
+
+        self._cache_dict: Dict[str, SingleStoreDB] = {}
+        self.embedding = embedding
+        self.cache_table_prefix = cache_table_prefix
+        self.search_threshold = search_threshold
+
+        # Pass the rest of the kwargs to the connection.
+        self.connection_kwargs = kwargs
+
+    def _index_name(self, llm_string: str) -> str:
+        hashed_index = _hash(llm_string)
+        return f"{self.cache_table_prefix}{hashed_index}"
+
+    def _get_llm_cache(self, llm_string: str) -> SingleStoreDB:
+        index_name = self._index_name(llm_string)
+
+        # return vectorstore client for the specific llm string
+        if index_name not in self._cache_dict:
+            self._cache_dict[index_name] = SingleStoreDB(
+                embedding=self.embedding,
+                table_name=index_name,
+                **self.connection_kwargs,
+            )
+        return self._cache_dict[index_name]
+
+    def lookup(self, prompt: str, llm_string: str) -> Optional[RETURN_VAL_TYPE]:
+        """Look up based on prompt and llm_string."""
+        llm_cache = self._get_llm_cache(llm_string)
+        generations: List = []
+        # Read from a Hash
+        results = llm_cache.similarity_search_with_score(
+            query=prompt,
+            k=1,
+        )
+        if results:
+            for document_score in results:
+                if (
+                    document_score[1] > self.search_threshold
+                    and llm_cache.distance_strategy == DistanceStrategy.DOT_PRODUCT
+                ) or (
+                    document_score[1] < self.search_threshold
+                    and llm_cache.distance_strategy
+                    == DistanceStrategy.EUCLIDEAN_DISTANCE
+                ):
+                    generations.extend(loads(document_score[0].metadata["return_val"]))
+        return generations if generations else None
+
+    def update(self, prompt: str, llm_string: str, return_val: RETURN_VAL_TYPE) -> None:
+        """Update cache based on prompt and llm_string."""
+        for gen in return_val:
+            if not isinstance(gen, Generation):
+                raise ValueError(
+                    "SingleStoreDBSemanticCache only supports caching of "
+                    f"normal LLM generations, got {type(gen)}"
+                )
+        llm_cache = self._get_llm_cache(llm_string)
+        metadata = {
+            "llm_string": llm_string,
+            "prompt": prompt,
+            "return_val": dumps([g for g in return_val]),
+        }
+        llm_cache.add_texts(texts=[prompt], metadatas=[metadata])
+
+    def clear(self, **kwargs: Any) -> None:
+        """Clear semantic cache for a given llm_string."""
+        index_name = self._index_name(kwargs["llm_string"])
+        if index_name in self._cache_dict:
+            self._cache_dict[index_name].drop()
+            del self._cache_dict[index_name]

libs/community/langchain_community/callbacks/__init__.py

@@ -6,6 +6,7 @@
 
     BaseCallbackHandler --> <name>CallbackHandler  # Example: AimCallbackHandler
 """
+
 import importlib
 from typing import TYPE_CHECKING, Any
 

libs/community/langchain_community/callbacks/arize_callback.py

@@ -82,9 +82,9 @@ class ArizeCallbackHandler(BaseCallbackHandler):
                 "completion_tokens", 0
             )
         else:
-            self.prompt_tokens = (
-                self.total_tokens
-            ) = self.completion_tokens = 0  # assign default value
+            self.prompt_tokens = self.total_tokens = self.completion_tokens = (
+                0  # assign default value
+            )
 
         for generations in response.generations:
             for generation in generations:

libs/community/langchain_community/callbacks/arthur_callback.py

@@ -1,4 +1,5 @@
 """ArthurAI's Callback Handler."""
+
 from __future__ import annotations
 
 import os

libs/community/langchain_community/callbacks/openai_info.py

@@ -223,19 +223,23 @@ class OpenAICallbackHandler(BaseCallbackHandler):
                 message = generation.message
                 if isinstance(message, AIMessage):
                     usage_metadata = message.usage_metadata
+                    response_metadata = message.response_metadata
                 else:
                     usage_metadata = None
+                    response_metadata = None
             except AttributeError:
                 usage_metadata = None
+                response_metadata = None
         else:
             usage_metadata = None
+            response_metadata = None
         if usage_metadata:
             token_usage = {"total_tokens": usage_metadata["total_tokens"]}
             completion_tokens = usage_metadata["output_tokens"]
             prompt_tokens = usage_metadata["input_tokens"]
-            if response.llm_output is None:
-                # model name (and therefore cost) is unavailable in
-                # streaming responses
+            if response_model_name := (response_metadata or {}).get("model_name"):
+                model_name = standardize_model_name(response_model_name)
+            elif response.llm_output is None:
                 model_name = ""
             else:
                 model_name = standardize_model_name(

libs/community/langchain_community/callbacks/promptlayer_callback.py

@@ -1,4 +1,5 @@
 """Callback handler for promptlayer."""
+
 from __future__ import annotations
 
 import datetime

libs/community/langchain_community/callbacks/tracers/wandb.py

@@ -1,4 +1,5 @@
 """A Tracer Implementation that records activity to Weights & Biases."""
+
 from __future__ import annotations
 
 import json
@@ -234,9 +235,9 @@ def build_tree(runs: List[Dict[str, Any]]) -> Dict[str, Any]:
 
     for child_id, parent_id in child_to_parent.items():
         parent_dict = id_to_data[parent_id]
-        parent_dict[next(iter(parent_dict))][
-            next(iter(id_to_data[child_id]))
-        ] = id_to_data[child_id][next(iter(id_to_data[child_id]))]
+        parent_dict[next(iter(parent_dict))][next(iter(id_to_data[child_id]))] = (
+            id_to_data[child_id][next(iter(id_to_data[child_id]))]
+        )
 
     root_dict = next(
         data for id_val, data in id_to_data.items() if id_val not in child_to_parent

libs/community/langchain_community/chains/ernie_functions/base.py

@@ -1,4 +1,5 @@
 """Methods for creating chains that use Ernie function-calling APIs."""
+
 import inspect
 from typing import (
     Any,
@@ -191,9 +192,9 @@ def get_ernie_output_parser(
             }
         else:
             pydantic_schema = functions[0]
-        output_parser: Union[
-            BaseOutputParser, BaseGenerationOutputParser
-        ] = PydanticOutputFunctionsParser(pydantic_schema=pydantic_schema)
+        output_parser: Union[BaseOutputParser, BaseGenerationOutputParser] = (
+            PydanticOutputFunctionsParser(pydantic_schema=pydantic_schema)
+        )
     else:
         output_parser = JsonOutputFunctionsParser(args_only=len(functions) <= 1)
     return output_parser

libs/community/langchain_community/chains/graph_qa/arangodb.py

@@ -1,4 +1,5 @@
 """Question answering over a graph."""
+
 from __future__ import annotations
 
 import re

libs/community/langchain_community/chains/graph_qa/base.py

@@ -1,4 +1,5 @@
 """Question answering over a graph."""
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Optional