Merge branch 'master' into eugene/update_add_texts

This PR moves the in memory implementation to langchain-core.

* The implementation remains importable from langchain-community.
* Supporting utilities are marked as private for now.

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

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

.github/scripts/check_diff.py

@@ -1,11 +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
@@ -122,9 +128,12 @@ if __name__ == "__main__":
 
     outputs = {
         "dirs-to-lint": add_dependents(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"], 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-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 "",
     }

.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/_release.yml

@@ -135,6 +135,7 @@ jobs:
       - release-notes
     uses:
       ./.github/workflows/_test_release.yml
+    permissions: write-all
     with:
       working-directory: ${{ inputs.working-directory }}
       dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
@@ -202,7 +203,7 @@ jobs:
           poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: poetry install --with test,test_integration
+        run: poetry install --with test
         working-directory: ${{ inputs.working-directory }}
 
       # Overwrite the local version of the package with the test PyPI version.
@@ -245,6 +246,10 @@ jobs:
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
+      - name: Import integration test dependencies
+        run: poetry install --with test,test_integration
+        working-directory: ${{ inputs.working-directory }}
+
       - name: Run integration tests
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         env:

.github/workflows/check_new_docs.yml

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

.github/workflows/people.yml

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

.github/workflows/scheduled_test.yml

@@ -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

@@ -38,24 +38,25 @@ conda install langchain -c conda-forge
 
 For these applications, LangChain simplifies the entire application lifecycle:
 
-- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel) and [components](https://python.langchain.com/v0.2/docs/concepts/#components). Integrate with hundreds of [third-party providers](https://python.langchain.com/v0.2/docs/integrations/platforms/).
+- **Open-source libraries**:  Build your applications using LangChain's open-source [building blocks](https://python.langchain.com/v0.2/docs/concepts#langchain-expression-language-lcel), [components](https://python.langchain.com/v0.2/docs/concepts), and [third-party integrations](https://python.langchain.com/v0.2/docs/integrations/platforms/).
+Use [LangGraph](/docs/concepts/#langgraph) to build stateful agents with first-class streaming and human-in-the-loop support.
 - **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://docs.smith.langchain.com/) so that you can constantly optimize and deploy with confidence.
-- **Deployment**: Turn any chain into a REST API with [LangServe](https://python.langchain.com/v0.2/docs/langserve/).
+- **Deployment**: Turn your LangGraph applications into production-ready APIs and Assistants with [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/).
 
 ### Open-source libraries
 - **`langchain-core`**: Base abstractions and LangChain Expression Language.
 - **`langchain-community`**: Third party integrations.
   - Some integrations have been further split into **partner packages** that only rely on **`langchain-core`**. Examples include **`langchain_openai`** and **`langchain_anthropic`**.
 - **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
-- **[`LangGraph`](https://langchain-ai.github.io/langgraph/)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
+- **[`LangGraph`](https://langchain-ai.github.io/langgraph/)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph. Integrates smoothly with LangChain, but can be used without it.
 
 ### Productionization:
 - **[LangSmith](https://docs.smith.langchain.com/)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
 
 ### Deployment:
-- **[LangServe](https://python.langchain.com/v0.2/docs/langserve/)**: A library for deploying LangChain chains as REST APIs.
+- **[LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/)**: Turn your LangGraph applications into production-ready APIs and Assistants.
 
-![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack.svg "LangChain Architecture Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_062024.svg "LangChain Architecture Overview")
 
 ## 🧱 What can you build with LangChain?
 
@@ -106,7 +107,7 @@ Retrieval Augmented Generation involves [loading data](https://python.langchain.
 
 **🤖 Agents**
 
-Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents) along with the [LangGraph](https://github.com/langchain-ai/langgraph) extension for building custom agents.
+Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents), along with [LangGraph](https://github.com/langchain-ai/langgraph) for building custom agents.
 
 ## 📖 Documentation
 
@@ -120,10 +121,9 @@ Please see [here](https://python.langchain.com) for full documentation, which in
 
 ## 🌐 Ecosystem
 
-- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
-- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
-- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploying LangChain runnables and chains as REST APIs.
-  - [LangChain Templates](https://python.langchain.com/v0.2/docs/templates/): Example applications hosted with LangServe.
+- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Trace and evaluate your language model applications and intelligent agents to help you move from prototype to production.
+- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Create stateful, multi-actor applications with LLMs. Integrates smoothly with LangChain, but can be used without it.
+- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploy LangChain runnables and chains as REST APIs.
 
 
 ## 💁 Contributing

docs/Makefile

@@ -61,7 +61,7 @@ render:
 	$(PYTHON) scripts/notebook_convert.py $(INTERMEDIATE_DIR) $(OUTPUT_NEW_DOCS_DIR)
 
 md-sync:
-	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
+	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --include="*/_category_.yml" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
 
 generate-references:
 	$(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(OUTPUT_NEW_DOCS_DIR)

docs/api_reference/templates/runnable_non_pydantic.rst

@@ -3,6 +3,7 @@
 
 .. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
 
+    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
 
 .. currentmodule:: {{ module }}
 

docs/api_reference/templates/runnable_pydantic.rst

@@ -3,6 +3,8 @@
 
 .. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
 
+    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
+
 .. currentmodule:: {{ module }}
 
 .. autopydantic_model:: {{ objname }}
@@ -17,6 +19,6 @@
     :member-order: groupwise
     :show-inheritance: True
     :special-members: __call__
-    :exclude-members: construct, copy, dict, from_orm, parse_file, parse_obj, parse_raw, schema, schema_json, update_forward_refs, validate, json, is_lc_serializable, to_json, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace, invoke, ainvoke, batch, abatch, batch_as_completed, abatch_as_completed, astream_log, stream, astream, astream_events, transform, atransform, get_output_schema, get_prompts, configurable_fields, configurable_alternatives, config_schema, map, pick, pipe, with_listeners, with_alisteners, with_config, with_fallbacks, with_types, with_retry, InputType, OutputType, config_specs, output_schema, get_input_schema, get_graph, get_name, input_schema, name, bind, assign
+    :exclude-members: construct, copy, dict, from_orm, parse_file, parse_obj, parse_raw, schema, schema_json, update_forward_refs, validate, json, is_lc_serializable, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace, astream_log, transform, atransform, get_output_schema, get_prompts, config_schema, map, pick, pipe, with_listeners, with_alisteners, with_config, with_fallbacks, with_types, with_retry, InputType, OutputType, config_specs, output_schema, get_input_schema, get_graph, get_name, input_schema, name, bind, assign
 
 .. example_links:: {{ objname }}

docs/docs/concepts.mdx

@@ -51,8 +51,8 @@ A developer platform that lets you debug, test, evaluate, and monitor LLM applic
 <ThemedImage
   alt="Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers."
   sources={{
-    light: useBaseUrl('/svg/langchain_stack.svg'),
-    dark: useBaseUrl('/svg/langchain_stack_dark.svg'),
+    light: useBaseUrl('/svg/langchain_stack_062024.svg'),
+    dark: useBaseUrl('/svg/langchain_stack_062024_dark.svg'),
   }}
   title="LangChain Framework Overview"
 />
@@ -85,11 +85,16 @@ 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"></span>
+<span data-heading-keywords="invoke,runnable"></span>
 
 To make it as easy as possible to create custom chains, we've implemented a ["Runnable"](https://api.python.langchain.com/en/stable/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable) protocol. Many LangChain components implement the `Runnable` protocol, including chat models, LLMs, output parsers, retrievers, prompt templates, and more. There are also several useful primitives for working with runnables, which you can read about below.
 
@@ -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.
@@ -550,6 +557,28 @@ If you are still using AgentExecutor, do not fear: we still have a guide on [how
 It is recommended, however, that you start to transition to LangGraph.
 In order to assist in this we have put together a [transition guide on how to do so](/docs/how_to/migrate_agent).
 
+#### ReAct agents
+<span data-heading-keywords="react,react agent"></span>
+
+One popular architecture for building agents is [**ReAct**](https://arxiv.org/abs/2210.03629).
+ReAct combines reasoning and acting in an iterative process - in fact the name "ReAct" stands for "Reason" and "Act".
+
+The general flow looks like this:
+
+- The model will "think" about what step to take in response to an input and any previous observations.
+- The model will then choose an action from available tools (or choose to respond to the user).
+- The model will generate arguments to that tool.
+- The agent runtime (executor) will parse out the chosen tool and call it with the generated arguments.
+- The executor will return the results of the tool call back to the model as an observation.
+- This process repeats until the agent chooses to respond.
+
+There are general prompting based implementations that do not require any model-specific features, but the most
+reliable implementations use features like [tool calling](/docs/how_to/tool_calling/) to reliably format outputs
+and reduce variance.
+
+Please see the [LangGraph documentation](https://langchain-ai.github.io/langgraph/) for more information,
+or [this how-to guide](/docs/how_to/migrate_agent/) for specific information on migrating to LangGraph.
+
 ### Callbacks
 
 LangChain provides a callbacks system that allows you to hook into the various stages of your LLM application. This is useful for logging, monitoring, streaming, and other tasks.
@@ -754,14 +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.
@@ -784,9 +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>
@@ -796,10 +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:
 
@@ -875,7 +944,7 @@ The standard interface consists of:
 The following how-to guides are good practical resources for using function/tool calling:
 
 - [How to return structured data from an LLM](/docs/how_to/structured_output/)
-- [How to use a model to call tools](/docs/how_to/tool_calling/)
+- [How to use a model to call tools](/docs/how_to/tool_calling)
 
 For a full list of model providers that support tool calling, [see this table](/docs/integrations/chat/#advanced-features).
 
@@ -1033,7 +1102,7 @@ See several videos and cookbooks showcasing RAG with LangGraph:
 - [Cookbooks for RAG using LangGraph](https://github.com/langchain-ai/langgraph/tree/main/examples/rag)
 
 See our LangGraph RAG recipes with partners:
-- [Meta](https://github.com/meta-llama/llama-recipes/tree/main/recipes/use_cases/agents/langchain) 
+- [Meta](https://github.com/meta-llama/llama-recipes/tree/main/recipes/3p_integrations/langchain)
 - [Mistral](https://github.com/mistralai/cookbook/tree/main/third_party/langchain)
 
 :::
@@ -1079,3 +1148,13 @@ This process is vital for building reliable applications.
 - It allows you to track results over time and automatically run your evaluators on a schedule or as part of CI/Code
 
 To learn more, check out [this LangSmith guide](https://docs.smith.langchain.com/concepts/evaluation).
+
+### Tracing
+<span data-heading-keywords="trace,tracing"></span>
+
+A trace is essentially a series of steps that your application takes to go from input to output.
+Traces contain individual steps called `runs`. These can be individual calls from a model, retriever,
+tool, or sub-chains.
+Tracing gives you observability inside your chains and agents, and is vital in diagnosing issues.
+
+For a deeper dive, check out [this LangSmith conceptual guide](https://docs.smith.langchain.com/concepts/tracing).

docs/docs/contributing/code/guidelines.mdx

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

docs/docs/contributing/code/index.mdx

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

docs/docs/contributing/code/setup.mdx

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

docs/docs/contributing/documentation/_category_.yml

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

docs/docs/contributing/documentation/index.mdx

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

docs/docs/contributing/documentation/setup.mdx

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

docs/docs/contributing/documentation/style_guide.mdx

@@ -1,10 +1,8 @@
 ---
-sidebar_label: "Style guide"
+sidebar_class_name: "hidden"
 ---
 
-# LangChain Documentation Style Guide
-
-## Introduction
+# Documentation Style Guide
 
 As LangChain continues to grow, the surface area of documentation required to cover it continues to grow too.
 This page provides guidelines for anyone writing documentation for LangChain, as well as some of our philosophies around
@@ -12,116 +10,137 @@ organization and structure.
 
 ## Philosophy
 
-LangChain's documentation aspires to follow the [Diataxis framework](https://diataxis.fr).
-Under this framework, all documentation falls under one of four categories:
+LangChain's documentation follows the [Diataxis framework](https://diataxis.fr).
+Under this framework, all documentation falls under one of four categories: [Tutorials](/docs/contributing/documentation/style_guide/#tutorials),
+[How-to guides](/docs/contributing/documentation/style_guide/#how-to-guides),
+[References](/docs/contributing/documentation/style_guide/#references), and [Explanations](/docs/contributing/documentation/style_guide/#conceptual-guide).
 
-- **Tutorials**: Lessons that take the reader by the hand through a series of conceptual steps to complete a project.
-  - An example of this is our [LCEL streaming guide](/docs/how_to/streaming).
-  - Our guides on [custom components](/docs/how_to/custom_chat_model) is another one.
-- **How-to guides**: Guides that take the reader through the steps required to solve a real-world problem.
-  - The clearest examples of this are our [Use case](/docs/how_to#use-cases) quickstart pages.
-- **Reference**: Technical descriptions of the machinery and how to operate it.
-  - Our [Runnable interface](/docs/concepts#interface) page is an example of this.
-  - The [API reference pages](https://api.python.langchain.com/) are another.
-- **Explanation**: Explanations that clarify and illuminate a particular topic.
-  - The [LCEL primitives pages](/docs/how_to/sequence) are an example of this.
+### Tutorials
+
+Tutorials are lessons that take the reader through a practical activity. Their purpose is to help the user
+gain understanding of concepts and how they interact by showing one way to achieve some goal in a hands-on way. They should **avoid** giving
+multiple permutations of ways to achieve that goal in-depth. Instead, it should guide a new user through a recommended path to accomplishing the tutorial's goal. While the end result of a tutorial does not necessarily need to
+be completely production-ready, it should be useful and practically satisfy the the goal that you clearly stated in the tutorial's introduction. Information on how to address additional scenarios
+belongs in how-to guides.
+
+To quote the Diataxis website:
+
+> A tutorial serves the user’s *acquisition* of skills and knowledge - their study. Its purpose is not to help the user get something done, but to help them learn.
+
+In LangChain, these are often higher level guides that show off end-to-end use cases.
+
+Some examples include:
+
+- [Build a Simple LLM Application with LCEL](/docs/tutorials/llm_chain/)
+- [Build a Retrieval Augmented Generation (RAG) App](/docs/tutorials/rag/)
+  
+Here are some high-level tips on writing a good tutorial:
+
+- Focus on guiding the user to get something done, but keep in mind the end-goal is more to impart principles than to create a perfect production system.
+- Be specific, not abstract and follow one path.
+  - No need to go deeply into alternative approaches, but it’s ok to reference them, ideally with a link to an appropriate how-to guide.
+- Get "a point on the board" as soon as possible - something the user can run that outputs something.
+  - You can iterate and expand afterwards.
+  - Try to frequently checkpoint at given steps where the user can run code and see progress.
+- Focus on results, not technical explanation.
+  - Crosslink heavily to appropriate conceptual/reference pages.
+- The first time you mention a LangChain concept, use its full name (e.g. "LangChain Expression Language (LCEL)"), and link to its conceptual/other documentation page.
+  - It's also helpful to add a prerequisite callout that links to any pages with necessary background information.
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as related how-to guides.
+  
+### How-to guides
+
+A how-to guide, as the name implies, demonstrates how to do something discrete and specific.
+It should assume that the user is already familiar with underlying concepts, and is trying to solve an immediate problem, but
+should still give some background or list the scenarios where the information contained within can be relevant.
+They can and should discuss alternatives if one approach may be better than another in certain cases.
+
+To quote the Diataxis website:
+
+> A how-to guide serves the work of the already-competent user, whom you can assume to know what they want to do, and to be able to follow your instructions correctly.
+
+Some examples include:
+
+- [How to: return structured data from a model](/docs/how_to/structured_output/)
+- [How to: write a custom chat model](/docs/how_to/custom_chat_model/)
+
+Here are some high-level tips on writing a good how-to guide:
+
+- Clearly explain what you are guiding the user through at the start.
+- Assume higher intent than a tutorial and show what the user needs to do to get that task done.
+- Assume familiarity of concepts, but explain why suggested actions are helpful.
+  - Crosslink heavily to conceptual/reference pages.
+- Discuss alternatives and responses to real-world tradeoffs that may arise when solving a problem.
+- Use lots of example code.
+  - Prefer full code blocks that the reader can copy and run.
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as other related how-to guides.
+
+### Conceptual guide
+
+LangChain's conceptual guide falls under the **Explanation** quadrant of Diataxis. They should cover LangChain terms and concepts
+in a more abstract way than how-to guides or tutorials, and should be geared towards curious users interested in
+gaining a deeper understanding of the framework. Try to avoid excessively large code examples - the goal here is to
+impart perspective to the user rather than to finish a practical project. These guides should cover **why** things work they way they do.
+
+This guide on documentation style is meant to fall under this category.
+
+To quote the Diataxis website:
+
+> The perspective of explanation is higher and wider than that of the other types. It does not take the user’s eye-level view, as in a how-to guide, or a close-up view of the machinery, like reference material. Its scope in each case is a topic - “an area of knowledge”, that somehow has to be bounded in a reasonable, meaningful way.
+
+Some examples include:
+
+- [Retrieval conceptual docs](/docs/concepts/#retrieval)
+- [Chat model conceptual docs](/docs/concepts/#chat-models)
+
+Here are some high-level tips on writing a good conceptual guide:
+
+- Explain design decisions. Why does concept X exist and why was it designed this way?
+- Use analogies and reference other concepts and alternatives
+- Avoid blending in too much reference content
+- You can and should reference content covered in other guides, but make sure to link to them
+
+### References
+
+References contain detailed, low-level information that describes exactly what functionality exists and how to use it.
+In LangChain, this is mainly our API reference pages, which are populated from docstrings within code.
+References pages are generally not read end-to-end, but are consulted as necessary when a user needs to know
+how to use something specific.
+
+To quote the Diataxis website:
+
+> The only purpose of a reference guide is to describe, as succinctly as possible, and in an orderly way. Whereas the content of tutorials and how-to guides are led by needs of the user, reference material is led by the product it describes.
+
+Many of the reference pages in LangChain are automatically generated from code,
+but here are some high-level tips on writing a good docstring:
+
+- Be concise
+- Discuss special cases and deviations from a user's expectations
+- Go into detail on required inputs and outputs
+- Light details on when one might use the feature are fine, but in-depth details belong in other sections.
 
 Each category serves a distinct purpose and requires a specific approach to writing and structuring the content.
 
-## Taxonomy
-
-Keeping the above in mind, we have sorted LangChain's docs into categories. It is helpful to think in these terms
-when contributing new documentation:
-
-### Getting started
-
-The [getting started section](/docs/introduction) includes a high-level introduction to LangChain, a quickstart that
-tours LangChain's various features, and logistical instructions around installation and project setup.
-
-It contains elements of **How-to guides** and **Explanations**.
-
-### Use cases
-
-[Use cases](/docs/how_to#use-cases) are guides that are meant to show how to use LangChain to accomplish a specific task (RAG, information extraction, etc.).
-The quickstarts should be good entrypoints for first-time LangChain developers who prefer to learn by getting something practical prototyped,
-then taking the pieces apart retrospectively. These should mirror what LangChain is good at.
-
-The quickstart pages here should fit the **How-to guide** category, with the other pages intended to be **Explanations** of more
-in-depth concepts and strategies that accompany the main happy paths.
-
-:::note
-The below sections are listed roughly in order of increasing level of abstraction.
-:::
-
-### Expression Language
-
-[LangChain Expression Language (LCEL)](/docs/concepts#langchain-expression-language-lcel) is the fundamental way that most LangChain components fit together, and this section is designed to teach
-developers how to use it to build with LangChain's primitives effectively.
-
-This section should contains **Tutorials** that teach how to stream and use LCEL primitives for more abstract tasks, **Explanations** of specific behaviors,
-and some **References** for how to use different methods in the Runnable interface.
-
-### Components
-
-The [components section](/docs/concepts) covers concepts one level of abstraction higher than LCEL.
-Abstract base classes like `BaseChatModel` and `BaseRetriever` should be covered here, as well as core implementations of these base classes,
-such as `ChatPromptTemplate` and `RecursiveCharacterTextSplitter`. Customization guides belong here too.
-
-This section should contain mostly conceptual **Tutorials**, **References**, and **Explanations** of the components they cover.
-
-:::note
-As a general rule of thumb, everything covered in the `Expression Language` and `Components` sections (with the exception of the `Composition` section of components) should
-cover only components that exist in `langchain_core`.
-:::
-
-### Integrations
-
-The [integrations](/docs/integrations/platforms/) are specific implementations of components. These often involve third-party APIs and services.
-If this is the case, as a general rule, these are maintained by the third-party partner.
-
-This section should contain mostly **Explanations** and **References**, though the actual content here is more flexible than other sections and more at the
-discretion of the third-party provider.
-
-:::note
-Concepts covered in `Integrations` should generally exist in `langchain_community` or specific partner packages.
-:::
-
-### Guides and Ecosystem
-
-The [Guides](/docs/tutorials) and [Ecosystem](https://docs.smith.langchain.com/) sections should contain guides that address higher-level problems than the sections above.
-This includes, but is not limited to, considerations around productionization and development workflows.
-
-These should contain mostly **How-to guides**, **Explanations**, and **Tutorials**.
-
-### API references
-
-LangChain's API references. Should act as **References** (as the name implies) with some **Explanation**-focused content as well. 
-
-## Sample developer journey
-
-We have set up our docs to assist a new developer to LangChain. Let's walk through the intended path:
-
-- The developer lands on https://python.langchain.com, and reads through the introduction and the diagram.
-- If they are just curious, they may be drawn to the [Quickstart](/docs/tutorials/llm_chain) to get a high-level tour of what LangChain contains.
-- If they have a specific task in mind that they want to accomplish, they will be drawn to the Use-Case section. The use-case should provide a good, concrete hook that shows the value LangChain can provide them and be a good entrypoint to the framework.
-- They can then move to learn more about the fundamentals of LangChain through the Expression Language sections.
-- Next, they can learn about LangChain's various components and integrations.
-- Finally, they can get additional knowledge through the Guides.
-
-This is only an ideal of course - sections will inevitably reference lower or higher-level concepts that are documented in other sections.
-
-## Guidelines
+## General guidelines
 
 Here are some other guidelines you should think about when writing and organizing documentation.
 
-### Linking to other sections
+We generally do not merge new tutorials from outside contributors without an actue need.
+We welcome updates as well as new integration docs, how-tos, and references.
+
+### Avoid duplication
+
+Multiple pages that cover the same material in depth are difficult to maintain and cause confusion. There should
+be only one (very rarely two), canonical pages for a given concept or feature. Instead, you should link to other guides.
+
+### Link to other sections
 
 Because sections of the docs do not exist in a vacuum, it is important to link to other sections as often as possible
 to allow a developer to learn more about an unfamiliar topic inline.
 
 This includes linking to the API references as well as conceptual sections!
 
-### Conciseness
+### Be concise
 
 In general, take a less-is-more approach. If a section with a good explanation of a concept already exists, you should link to it rather than
 re-explain it, unless the concept you are documenting presents some new wrinkle.
@@ -130,9 +149,10 @@ Be concise, including in code samples.
 
 ### General style
 
-- Use active voice and present tense whenever possible.
-- Use examples and code snippets to illustrate concepts and usage.
-- Use appropriate header levels (`#`, `##`, `###`, etc.) to organize the content hierarchically.
-- Use bullet points and numbered lists to break down information into easily digestible chunks.
-- Use tables (especially for **Reference** sections) and diagrams often to present information visually.
-- Include the table of contents for longer documentation pages to help readers navigate the content, but hide it for shorter pages.
+- Use active voice and present tense whenever possible
+- Use examples and code snippets to illustrate concepts and usage
+- Use appropriate header levels (`#`, `##`, `###`, etc.) to organize the content hierarchically
+- Use fewer cells with more code to make copy/paste easier
+- Use bullet points and numbered lists to break down information into easily digestible chunks
+- Use tables (especially for **Reference** sections) and diagrams often to present information visually
+- Include the table of contents for longer documentation pages to help readers navigate the content, but hide it for shorter pages

docs/docs/contributing/index.mdx

@@ -12,8 +12,8 @@ As an open-source project in a rapidly developing field, we are extremely open t
 
 There are many ways to contribute to LangChain. Here are some common ways people contribute:
 
-- [**Documentation**](/docs/contributing/documentation/style_guide): Help improve our docs, including this one!
-- [**Code**](./code.mdx): Help us write code, fix bugs, or improve our infrastructure.
+- [**Documentation**](/docs/contributing/documentation/): Help improve our docs, including this one!
+- [**Code**](/docs/contributing/code/): Help us write code, fix bugs, or improve our infrastructure.
 - [**Integrations**](integrations.mdx): Help us integrate with your favorite vendors and tools.
 - [**Discussions**](https://github.com/langchain-ai/langchain/discussions): Help answer usage questions and discuss issues with users.
 

docs/docs/contributing/integrations.mdx

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

docs/docs/contributing/repo_structure.mdx

@@ -7,6 +7,7 @@ If you plan on contributing to LangChain code or documentation, it can be useful
 to understand the high level structure of the repository.
 
 LangChain is organized as a [monorepo](https://en.wikipedia.org/wiki/Monorepo) that contains multiple packages.
+You can check out our [installation guide](/docs/how_to/installation/) for more on how they fit together.
 
 Here's the structure visualized as a tree:
 
@@ -51,7 +52,7 @@ There are other files in the root directory level, but their presence should be
 The `/docs` directory contains the content for the documentation that is shown
 at https://python.langchain.com/ and the associated API Reference https://api.python.langchain.com/en/latest/langchain_api_reference.html.
 
-See the [documentation](/docs/contributing/documentation/style_guide) guidelines to learn how to contribute to the documentation.
+See the [documentation](/docs/contributing/documentation/) guidelines to learn how to contribute to the documentation.
 
 ## Code
 
@@ -59,6 +60,6 @@ The `/libs` directory contains the code for the LangChain packages.
 
 To learn more about how to contribute code see the following guidelines:
 
-- [Code](./code.mdx) Learn how to develop in the LangChain codebase.
-- [Integrations](./integrations.mdx) to learn how to contribute to third-party integrations to langchain-community or to start a new partner package.
-- [Testing](./testing.mdx) guidelines to learn how to write tests for the packages.
+- [Code](/docs/contributing/code/): Learn how to develop in the LangChain codebase.
+- [Integrations](./integrations.mdx): Learn how to contribute to third-party integrations to `langchain-community` or to start a new partner package.
+- [Testing](./testing.mdx): Guidelines to learn how to write tests for the packages.

docs/docs/contributing/testing.mdx

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

docs/docs/how_to/binding.ipynb

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

docs/docs/how_to/document_loader_html.ipynb

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

docs/docs/how_to/document_loader_markdown.ipynb

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

docs/docs/how_to/extraction_examples.ipynb

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

docs/docs/how_to/few_shot_examples.ipynb

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

docs/docs/how_to/few_shot_examples_chat.ipynb

@@ -23,7 +23,7 @@
     "- [Prompt templates](/docs/concepts/#prompt-templates)\n",
     "- [Example selectors](/docs/concepts/#example-selectors)\n",
     "- [Chat models](/docs/concepts/#chat-model)\n",
-    "- [Vectorstores](/docs/concepts/#vectorstores)\n",
+    "- [Vectorstores](/docs/concepts/#vector-stores)\n",
     "\n",
     ":::\n",
     "\n",
@@ -51,7 +51,7 @@
     "- `examples`: A list of dictionary examples to include in the final prompt.\n",
     "- `example_prompt`: converts each example into 1 or more messages through its [`format_messages`](https://api.python.langchain.com/en/latest/prompts/langchain_core.prompts.chat.ChatPromptTemplate.html?highlight=format_messages#langchain_core.prompts.chat.ChatPromptTemplate.format_messages) method. A common example would be to convert each example into one human message and one AI message response, or a human message followed by a function call message.\n",
     "\n",
-    "Below is a simple demonstration. First, define the examples you'd like to include:"
+    "Below is a simple demonstration. First, define the examples you'd like to include. Let's give the LLM an unfamiliar mathematical operator, denoted by the \"🦜\" emoji:"
    ]
   },
   {
@@ -59,17 +59,7 @@
    "execution_count": 1,
    "id": "5b79e400",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 24.0 is available.\n",
-      "You should consider upgrading via the '/Users/jacoblee/.pyenv/versions/3.10.5/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n",
-      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "%pip install -qU langchain langchain-openai langchain-chroma\n",
     "\n",
@@ -79,9 +69,50 @@
     "os.environ[\"OPENAI_API_KEY\"] = getpass()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "30856d92",
+   "metadata": {},
+   "source": [
+    "If we try to ask the model what the result of this expression is, it will fail:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
+   "id": "174dec5b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The expression \"2 🦜 9\" is not a standard mathematical operation or equation. It appears to be a combination of the number 2 and the parrot emoji 🦜 followed by the number 9. It does not have a specific mathematical meaning.', response_metadata={'token_usage': {'completion_tokens': 54, 'prompt_tokens': 17, 'total_tokens': 71}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-aad12dda-5c47-4a1e-9949-6fe94e03242a-0', usage_metadata={'input_tokens': 17, 'output_tokens': 54, 'total_tokens': 71})"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0.0)\n",
+    "\n",
+    "model.invoke(\"What is 2 🦜 9?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e6d58385",
+   "metadata": {},
+   "source": [
+    "Now let's see what happens if we give the LLM some examples to work with. We'll define some below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
    "id": "0fc5a02a-6249-4e92-95c3-30fff9671e8b",
    "metadata": {
     "tags": []
@@ -91,8 +122,8 @@
     "from langchain_core.prompts import ChatPromptTemplate, FewShotChatMessagePromptTemplate\n",
     "\n",
     "examples = [\n",
-    "    {\"input\": \"2+2\", \"output\": \"4\"},\n",
-    "    {\"input\": \"2+3\", \"output\": \"5\"},\n",
+    "    {\"input\": \"2 🦜 2\", \"output\": \"4\"},\n",
+    "    {\"input\": \"2 🦜 3\", \"output\": \"5\"},\n",
     "]"
    ]
   },
@@ -106,7 +137,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "id": "65e72ad1-9060-47d0-91a1-bc130c8b98ac",
    "metadata": {
     "tags": []
@@ -116,7 +147,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[HumanMessage(content='2+2'), AIMessage(content='4'), HumanMessage(content='2+3'), AIMessage(content='5')]\n"
+      "[HumanMessage(content='2 🦜 2'), AIMessage(content='4'), HumanMessage(content='2 🦜 3'), AIMessage(content='5')]\n"
      ]
     }
    ],
@@ -146,7 +177,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "id": "9f86d6d9-50de-41b6-b6c7-0f9980cc0187",
    "metadata": {
     "tags": []
@@ -162,9 +193,17 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "dd8029c5",
+   "metadata": {},
+   "source": [
+    "And now let's ask the model the initial question and see how it does:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
    "id": "97d443b1-6fae-4b36-bede-3ff7306288a3",
    "metadata": {
     "tags": []
@@ -173,10 +212,10 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='A triangle does not have a square. The square of a number is the result of multiplying the number by itself.', response_metadata={'token_usage': {'completion_tokens': 23, 'prompt_tokens': 52, 'total_tokens': 75}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-3456c4ef-7b4d-4adb-9e02-8079de82a47a-0')"
+       "AIMessage(content='11', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 60, 'total_tokens': 61}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5ec4e051-262f-408e-ad00-3f2ebeb561c3-0', usage_metadata={'input_tokens': 60, 'output_tokens': 1, 'total_tokens': 61})"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -184,9 +223,9 @@
    "source": [
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "chain = final_prompt | ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0.0)\n",
+    "chain = final_prompt | model\n",
     "\n",
-    "chain.invoke({\"input\": \"What's the square of a triangle?\"})"
+    "chain.invoke({\"input\": \"What is 2 🦜 9?\"})"
    ]
   },
   {
@@ -194,6 +233,8 @@
    "id": "70ab7114-f07f-46be-8874-3705a25aba5f",
    "metadata": {},
    "source": [
+    "And we can see that the model has now inferred that the parrot emoji means addition from the given few-shot examples!\n",
+    "\n",
     "## Dynamic few-shot prompting\n",
     "\n",
     "Sometimes you may want to select only a few examples from your overall set to show based on the input. For this, you can replace the `examples` passed into `FewShotChatMessagePromptTemplate` with an `example_selector`. The other components remain the same as above! Our dynamic few-shot prompt template would look like:\n",
@@ -208,7 +249,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 9,
    "id": "ad66f06a-66fd-4fcc-8166-5d0e3c801e57",
    "metadata": {
     "tags": []
@@ -220,9 +261,9 @@
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "examples = [\n",
-    "    {\"input\": \"2+2\", \"output\": \"4\"},\n",
-    "    {\"input\": \"2+3\", \"output\": \"5\"},\n",
-    "    {\"input\": \"2+4\", \"output\": \"6\"},\n",
+    "    {\"input\": \"2 🦜 2\", \"output\": \"4\"},\n",
+    "    {\"input\": \"2 🦜 3\", \"output\": \"5\"},\n",
+    "    {\"input\": \"2 🦜 4\", \"output\": \"6\"},\n",
     "    {\"input\": \"What did the cow say to the moon?\", \"output\": \"nothing at all\"},\n",
     "    {\n",
     "        \"input\": \"Write me a poem about the moon\",\n",
@@ -247,7 +288,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 10,
    "id": "7790303a-f722-452e-8921-b14bdf20bdff",
    "metadata": {
     "tags": []
@@ -257,10 +298,10 @@
      "data": {
       "text/plain": [
        "[{'input': 'What did the cow say to the moon?', 'output': 'nothing at all'},\n",
-       " {'input': '2+4', 'output': '6'}]"
+       " {'input': '2 🦜 4', 'output': '6'}]"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -287,7 +328,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 11,
    "id": "253c255e-41d7-45f6-9d88-c7a0ced4b1bd",
    "metadata": {
     "tags": []
@@ -297,7 +338,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[HumanMessage(content='2+3'), AIMessage(content='5'), HumanMessage(content='2+2'), AIMessage(content='4')]\n"
+      "[HumanMessage(content='2 🦜 3'), AIMessage(content='5'), HumanMessage(content='2 🦜 4'), AIMessage(content='6')]\n"
      ]
     }
    ],
@@ -317,7 +358,7 @@
     "    ),\n",
     ")\n",
     "\n",
-    "print(few_shot_prompt.invoke(input=\"What's 3+3?\").to_messages())"
+    "print(few_shot_prompt.invoke(input=\"What's 3 🦜 3?\").to_messages())"
    ]
   },
   {
@@ -330,7 +371,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 12,
    "id": "e731cb45-f0ea-422c-be37-42af2a6cb2c4",
    "metadata": {
     "tags": []
@@ -340,7 +381,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "messages=[HumanMessage(content='2+3'), AIMessage(content='5'), HumanMessage(content='2+2'), AIMessage(content='4')]\n"
+      "messages=[HumanMessage(content='2 🦜 3'), AIMessage(content='5'), HumanMessage(content='2 🦜 4'), AIMessage(content='6')]\n"
      ]
     }
    ],
@@ -353,7 +394,7 @@
     "    ]\n",
     ")\n",
     "\n",
-    "print(few_shot_prompt.invoke(input=\"What's 3+3?\"))"
+    "print(few_shot_prompt.invoke(input=\"What's 3 🦜 3?\"))"
    ]
   },
   {
@@ -368,7 +409,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 13,
    "id": "0568cbc6-5354-47f1-ab4d-dfcc616cf583",
    "metadata": {
     "tags": []
@@ -377,10 +418,10 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='6', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 51, 'total_tokens': 52}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-6bcbe158-a8e3-4a85-a754-1ba274a9f147-0')"
+       "AIMessage(content='6', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 60, 'total_tokens': 61}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-d1863e5e-17cd-4e9d-bf7a-b9f118747a65-0', usage_metadata={'input_tokens': 60, 'output_tokens': 1, 'total_tokens': 61})"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -388,7 +429,7 @@
    "source": [
     "chain = final_prompt | ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0.0)\n",
     "\n",
-    "chain.invoke({\"input\": \"What's 3+3?\"})"
+    "chain.invoke({\"input\": \"What's 3 🦜 3?\"})"
    ]
   },
   {
@@ -428,7 +469,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/index.mdx

@@ -21,7 +21,7 @@ For comprehensive descriptions of every class and function see the [API Referenc
 This highlights functionality that is core to using LangChain.
 
 - [How to: return structured data from a model](/docs/how_to/structured_output/)
-- [How to: use a model to call tools](/docs/how_to/tool_calling/)
+- [How to: use a model to call tools](/docs/how_to/tool_calling)
 - [How to: stream runnables](/docs/how_to/streaming)
 - [How to: debug your LLM apps](/docs/how_to/debugging/)
 
@@ -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
 
@@ -79,6 +80,12 @@ These are the core building blocks you can use when building applications.
 - [How to: stream a response back](/docs/how_to/chat_streaming)
 - [How to: track token usage](/docs/how_to/chat_token_usage_tracking)
 - [How to: track response metadata across providers](/docs/how_to/response_metadata)
+- [How to: let your end users choose their model](/docs/how_to/chat_models_universal_init/)
+- [How to: use chat model to call tools](/docs/how_to/tool_calling)
+- [How to: stream tool calls](/docs/how_to/tool_streaming)
+- [How to: 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: init any model in one line](/docs/how_to/chat_models_universal_init/)
 
 ### Messages
@@ -176,15 +183,17 @@ Indexing is the process of keeping your vectorstore in-sync with the underlying
 
 ### Tools
 
-LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to pass to the language model) as well as the implementation of the function to call).
+LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to pass to the language model) as well as the implementation of the function to call. Refer [here](/docs/integrations/tools/) for a list of pre-buit tools. 
 
 - [How to: create custom tools](/docs/how_to/custom_tools)
 - [How to: use built-in tools and built-in toolkits](/docs/how_to/tools_builtin)
-- [How to: use a chat model to call tools](/docs/how_to/tool_calling/)
+- [How to: use chat model to call tools](/docs/how_to/tool_calling)
+- [How to: pass tool results back to model](/docs/how_to/tool_results_pass_to_model)
 - [How to: add ad-hoc tool calling capability to LLMs and chat models](/docs/how_to/tools_prompting)
 - [How to: pass run time values to tools](/docs/how_to/tool_runtime)
 - [How to: add a human in the loop to tool usage](/docs/how_to/tools_human)
 - [How to: handle errors when calling tools](/docs/how_to/tools_error)
+- [How to: disable parallel tool calling](/docs/how_to/tool_choice)
 
 ### Multimodal
 
@@ -196,7 +205,7 @@ 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.
 
 :::
 
@@ -309,7 +318,8 @@ LangSmith allows you to closely trace, monitor and evaluate your LLM application
 It seamlessly integrates with LangChain and LangGraph, and you can use it to inspect and debug individual steps of your chains and agents as you build.
 
 LangSmith documentation is hosted on a separate site.
-You can peruse [LangSmith how-to guides here](https://docs.smith.langchain.com/how_to_guides/).
+You can peruse [LangSmith how-to guides here](https://docs.smith.langchain.com/how_to_guides/), but we'll highlight a few sections that are particularly
+relevant to LangChain below:
 
 ### Evaluation
 <span data-heading-keywords="evaluation,evaluate"></span>
@@ -318,3 +328,13 @@ Evaluating performance is a vital part of building LLM-powered applications.
 LangSmith helps with every step of the process from creating a dataset to defining metrics to running evaluators.
 
 To learn more, check out the [LangSmith evaluation how-to guides](https://docs.smith.langchain.com/how_to_guides#evaluation).
+
+### Tracing
+<span data-heading-keywords="trace,tracing"></span>
+
+Tracing gives you observability inside your chains and agents, and is vital in diagnosing issues.
+
+- [How to: trace with LangChain](https://docs.smith.langchain.com/how_to_guides/tracing/trace_with_langchain)
+- [How to: add metadata and tags to traces](https://docs.smith.langchain.com/how_to_guides/tracing/trace_with_langchain#add-metadata-and-tags-to-traces)
+
+You can see general tracing-related how-tos [in this section of the LangSmith docs](https://docs.smith.langchain.com/how_to_guides/tracing).

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/installation.mdx

@@ -2,11 +2,14 @@
 sidebar_position: 2
 ---
 
-# Installation
+# How to install LangChain packages
+
+The LangChain ecosystem is split into different packages, which allow you to choose exactly which pieces of
+functionality to install.
 
 ## Official release
 
-To install LangChain run:
+To install the main LangChain package, run:
 
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
@@ -21,11 +24,24 @@ import CodeBlock from "@theme/CodeBlock";
   </TabItem>
 </Tabs>
 
-This will install the bare minimum requirements of LangChain.
-A lot of the value of LangChain comes when integrating it with various model providers, datastores, etc.
+While this package acts as a sane starting point to using LangChain,
+much of the value of LangChain comes when integrating it with various model providers, datastores, etc.
 By default, the dependencies needed to do that are NOT installed. You will need to install the dependencies for specific integrations separately.
+We'll show how to do that in the next sections of this guide.
 
-## From source
+## Ecosystem packages
+
+With the exception of the `langsmith` SDK, all packages in the LangChain ecosystem depend on `langchain-core`, which contains base
+classes and abstractions that other packages use. The dependency graph below shows how the difference packages are related.
+A directed arrow indicates that the source package depends on the target package:
+
+![](/img/ecosystem_packages.png)
+
+When installing a package, you do not need to explicitly install that package's explicit dependencies (such as `langchain-core`).
+However, you may choose to if you are using a feature only available in a certain version of that dependency.
+If you do, you should make sure that the installed or pinned version is compatible with any other integration packages you use.
+
+### From source
 
 If you want to install from source, you can do so by cloning the repo and be sure that the directory is `PATH/TO/REPO/langchain/libs/langchain` running:
 
@@ -33,21 +49,21 @@ If you want to install from source, you can do so by cloning the repo and be sur
 pip install -e .
 ```
 
-## LangChain core
+### LangChain core
 The `langchain-core` package contains base abstractions that the rest of the LangChain ecosystem uses, along with the LangChain Expression Language. It is automatically installed by `langchain`, but can also be used separately. Install with:
 
 ```bash
 pip install langchain-core
 ```
 
-## LangChain community
+### LangChain community
 The `langchain-community` package contains third-party integrations. Install with:
 
 ```bash
 pip install langchain-community
 ```
 
-## LangChain experimental
+### LangChain experimental
 The `langchain-experimental` package holds experimental LangChain code, intended for research and experimental uses.
 Install with:
 
@@ -55,14 +71,15 @@ Install with:
 pip install langchain-experimental
 ```
 
-## LangGraph
-`langgraph` is a library for building stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain.
+### LangGraph
+`langgraph` is a library for building stateful, multi-actor applications with LLMs. It integrates smoothly with LangChain, but can be used without it.
 Install with:
 
 ```bash
 pip install langgraph
 ```
-## LangServe
+
+### LangServe
 LangServe helps developers deploy LangChain runnables and chains as a REST API.
 LangServe is automatically installed by LangChain CLI.
 If not using LangChain CLI, install with:
@@ -80,9 +97,10 @@ Install with:
 pip install langchain-cli
 ```
 
-## LangSmith SDK
-The LangSmith SDK is automatically installed by LangChain.
-If not using LangChain, install with:
+### LangSmith SDK
+The LangSmith SDK is automatically installed by LangChain. However, it does not depend on
+`langchain-core`, and can be installed and used independently if desired.
+If you are not using LangChain, you can install it with:
 
 ```bash
 pip install langsmith

docs/docs/how_to/migrate_agent.ipynb

@@ -1,5 +1,19 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "adc7ee09",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "keywords: [create_react_agent, create_react_agent()]\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "457cdc67-1893-4653-8b0c-b185a5947e74",
@@ -7,9 +21,18 @@
    "source": [
     "# How to migrate from legacy LangChain agents to LangGraph\n",
     "\n",
-    "Here we focus on how to move from legacy LangChain agents to LangGraph agents.\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "- [Agents](/docs/concepts/#agents)\n",
+    "- [LangGraph](https://langchain-ai.github.io/langgraph/)\n",
+    "- [Tool calling](/docs/how_to/tool_calling/)\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "Here we focus on how to move from legacy LangChain agents to more flexible [LangGraph](https://langchain-ai.github.io/langgraph/) agents.\n",
     "LangChain agents (the [AgentExecutor](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor) in particular) have multiple configuration parameters.\n",
-    "In this notebook we will show how those parameters map to the LangGraph [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent).\n",
+    "In this notebook we will show how those parameters map to the LangGraph react agent executor using the [create_react_agent](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) prebuilt helper method.\n",
     "\n",
     "#### Prerequisites\n",
     "\n",
@@ -195,7 +218,7 @@
     "\n",
     "Let's take a look at all of these below. We will pass in custom instructions to get the agent to respond in Spanish.\n",
     "\n",
-    "First up, using AgentExecutor:"
+    "First up, using `AgentExecutor`:"
    ]
   },
   {
@@ -238,7 +261,16 @@
    "id": "bd5f5500-5ae4-4000-a9fd-8c5a2cc6404d",
    "metadata": {},
    "source": [
-    "Now, let's pass a custom system message to [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent). This can either be a string or a LangChain SystemMessage."
+    "Now, let's pass a custom system message to [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent).\n",
+    "\n",
+    "LangGraph's prebuilt `create_react_agent` does not take a prompt template directly as a parameter, but instead takes a [`messages_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) parameter. This modifies messages before they are passed into the model, and can be one of four values:\n",
+    "\n",
+    "- A `SystemMessage`, which is added to the beginning of the list of messages.\n",
+    "- A `string`, which is converted to a `SystemMessage` and added to the beginning of the list of messages.\n",
+    "- A `Callable`, which should take in a list of messages. The output is then passed to the language model.\n",
+    "- Or a [`Runnable`](/docs/concepts/#langchain-expression-language-lcel), which should should take in a list of messages. The output is then passed to the language model.\n",
+    "\n",
+    "Here's how it looks in action:"
    ]
   },
   {
@@ -319,7 +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."
    ]
@@ -407,7 +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",
@@ -478,6 +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) "
    ]
   },
@@ -536,7 +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."
    ]
@@ -587,6 +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"
    ]
   },
@@ -615,6 +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."
    ]
   },
@@ -655,11 +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."
    ]
   },
   {
@@ -737,6 +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,
@@ -782,6 +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."
    ]
   },
@@ -848,6 +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**:"
@@ -936,6 +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\"`)."
    ]
   },
@@ -996,7 +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."
    ]
@@ -1045,6 +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."
@@ -1148,7 +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)."
    ]
@@ -1212,6 +1278,18 @@
     "except GraphRecursionError as e:\n",
     "    print(\"Stopping agent prematurely due to triggering stop condition\")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "41377eb8",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "You've now learned how to migrate your LangChain agent executors to LangGraph.\n",
+    "\n",
+    "Next, check out other [LangGraph how-to guides](https://langchain-ai.github.io/langgraph/how-tos/)."
+   ]
   }
  ],
  "metadata": {

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/sql_csv.ipynb

@@ -351,7 +351,7 @@
    "id": "ab1b2e7c-6ea8-4674-98eb-a43c69f5c19d",
    "metadata": {},
    "source": [
-    "To help enforce proper use of our Python tool, we'll using [tool calling](/docs/how_to/tool_calling/):"
+    "To help enforce proper use of our Python tool, we'll using [tool calling](/docs/how_to/tool_calling):"
    ]
   },
   {

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"
     }
@@ -250,7 +250,7 @@
    "id": "e28c14d3",
    "metadata": {},
    "source": [
-    "Alternatively, you can use tool calling directly to allow the model to choose between options, if your [chosen model supports it](/docs/integrations/chat/). This involves a bit more parsing and setup but in some instances leads to better performance because you don't have to use nested schemas. See [this how-to guide](/docs/how_to/tool_calling/) for more details."
+    "Alternatively, you can use tool calling directly to allow the model to choose between options, if your [chosen model supports it](/docs/integrations/chat/). This involves a bit more parsing and setup but in some instances leads to better performance because you don't have to use nested schemas. See [this how-to guide](/docs/how_to/tool_calling) for more details."
    ]
   },
   {
@@ -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_calling.ipynb

@@ -1,5 +1,18 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "keywords: [tool calling, tool call]\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -11,6 +24,7 @@
     "This guide assumes familiarity with the following concepts:\n",
     "- [Chat models](/docs/concepts/#chat-models)\n",
     "- [LangChain Tools](/docs/concepts/#tools)\n",
+    "- [Output parsers](/docs/concepts/#output-parsers)\n",
     "\n",
     ":::\n",
     "\n",
@@ -38,6 +52,12 @@
     "parameters matching the desired schema, then treat the generated output as your final \n",
     "result.\n",
     "\n",
+    ":::note\n",
+    "\n",
+    "If you only need formatted values, try the [.with_structured_output()](/docs/how_to/structured_output/#the-with_structured_output-method) chat model method as a simpler entrypoint.\n",
+    "\n",
+    ":::\n",
+    "\n",
     "However, tool calling goes beyond [structured output](/docs/how_to/structured_output/)\n",
     "since you can pass responses from called tools back to the model to create longer interactions.\n",
     "For instance, given a search engine tool, an LLM might handle a \n",
@@ -52,8 +72,13 @@
     "support variants of a tool calling feature.\n",
     "\n",
     "LangChain implements standard interfaces for defining tools, passing them to LLMs, \n",
-    "and representing tool calls. This guide will show you how to use them.\n",
-    "\n",
+    "and representing tool calls. This guide and the other How-to pages in the Tool section will show you how to use tools with LangChain."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
     "## Passing tools to chat models\n",
     "\n",
     "Chat models that support tool calling features implement a `.bind_tools` method, which \n",
@@ -153,7 +178,7 @@
     "# | output: false\n",
     "# | echo: false\n",
     "\n",
-    "%pip install -qU langchain langchain_openai\n",
+    "%pip install -qU langchain_openai\n",
     "\n",
     "import os\n",
     "from getpass import getpass\n",
@@ -167,81 +192,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm_with_tools = llm.bind_tools(tools)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We can also use the `tool_choice` parameter to ensure certain behavior. For example, we can force our tool to call the multiply tool by using the following code:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_9cViskmLvPnHjXk9tbVla5HA', 'function': {'arguments': '{\"a\":2,\"b\":4}', 'name': 'Multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 9, 'prompt_tokens': 103, 'total_tokens': 112}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-095b827e-2bdd-43bb-8897-c843f4504883-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 2, 'b': 4}, 'id': 'call_9cViskmLvPnHjXk9tbVla5HA'}], usage_metadata={'input_tokens': 103, 'output_tokens': 9, 'total_tokens': 112})"
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_g4RuAijtDcSeM96jXyCuiLSN', 'function': {'arguments': '{\"a\":3,\"b\":12}', 'name': 'Multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 95, 'total_tokens': 113}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-5157d15a-7e0e-4ab1-af48-3d98010cd152-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_g4RuAijtDcSeM96jXyCuiLSN'}], usage_metadata={'input_tokens': 95, 'output_tokens': 18, 'total_tokens': 113})"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "llm_forced_to_multiply = llm.bind_tools(tools, tool_choice=\"Multiply\")\n",
-    "llm_forced_to_multiply.invoke(\"what is 2 + 4\")"
+    "llm_with_tools = llm.bind_tools(tools)\n",
+    "\n",
+    "query = \"What is 3 * 12?\"\n",
+    "\n",
+    "llm_with_tools.invoke(query)"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Even if we pass it something that doesn't require multiplcation - it will still call the tool!"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We can also just force our tool to select at least one of our tools by passing in the \"any\" (or \"required\" which is OpenAI specific) keyword to the `tool_choice` parameter."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_mCSiJntCwHJUBfaHZVUB2D8W', 'function': {'arguments': '{\"a\":1,\"b\":2}', 'name': 'Add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 15, 'prompt_tokens': 94, 'total_tokens': 109}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-28f75260-9900-4bed-8cd3-f1579abb65e5-0', tool_calls=[{'name': 'Add', 'args': {'a': 1, 'b': 2}, 'id': 'call_mCSiJntCwHJUBfaHZVUB2D8W'}], usage_metadata={'input_tokens': 94, 'output_tokens': 15, 'total_tokens': 109})"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_forced_to_use_tool = llm.bind_tools(tools, tool_choice=\"any\")\n",
-    "llm_forced_to_use_tool.invoke(\"What day is today?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "As we can see, even though the prompt didn't really suggest a tool call, our LLM made one since it was forced to do so. You can look at the docs for [`bind_tool`](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.BaseChatOpenAI.html#langchain_openai.chat_models.base.BaseChatOpenAI.bind_tools) to learn about all the ways to customize how your LLM selects tools."
+    "As we can see, even though the prompt didn't really suggest a tool call, our LLM made one since it was forced to do so. You can look at the docs for [bind_tools()](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.BaseChatOpenAI.html#langchain_openai.chat_models.base.BaseChatOpenAI.bind_tools) to learn about all the ways to customize how your LLM selects tools."
    ]
   },
   {
@@ -273,10 +250,10 @@
       "text/plain": [
        "[{'name': 'Multiply',\n",
        "  'args': {'a': 3, 'b': 12},\n",
-       "  'id': 'call_KquHA7mSbgtAkpkmRPaFnJKa'},\n",
+       "  'id': 'call_TnadLbWJu9HwDULRb51RNSMw'},\n",
        " {'name': 'Add',\n",
        "  'args': {'a': 11, 'b': 49},\n",
-       "  'id': 'call_Fl0hQi4IBTzlpaJYlM5kPQhE'}]"
+       "  'id': 'call_Q9vt1up05sOQScXvUYWzSpCg'}]"
       ]
      },
      "execution_count": 5,
@@ -302,7 +279,8 @@
     "a name, string arguments, identifier, and error message.\n",
     "\n",
     "If desired, [output parsers](/docs/how_to#output-parsers) can further \n",
-    "process the output. For example, we can convert back to the original Pydantic class:"
+    "process the output. For example, we can convert existing values populated on the `.tool_calls` attribute back to the original Pydantic class using the\n",
+    "[PydanticToolsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.openai_tools.PydanticToolsParser.html):"
    ]
   },
   {
@@ -322,443 +300,27 @@
     }
    ],
    "source": [
-    "from langchain_core.output_parsers.openai_tools import PydanticToolsParser\n",
+    "from langchain_core.output_parsers import PydanticToolsParser\n",
     "\n",
     "chain = llm_with_tools | PydanticToolsParser(tools=[Multiply, Add])\n",
     "chain.invoke(query)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Streaming\n",
-    "\n",
-    "When tools are called in a streaming context, \n",
-    "[message chunks](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk) \n",
-    "will be populated with [tool call chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolCallChunk.html#langchain_core.messages.tool.ToolCallChunk) \n",
-    "objects in a list via the `.tool_call_chunks` attribute. A `ToolCallChunk` includes \n",
-    "optional string fields for the tool `name`, `args`, and `id`, and includes an optional \n",
-    "integer field `index` that can be used to join chunks together. Fields are optional \n",
-    "because portions of a tool call may be streamed across different chunks (e.g., a chunk \n",
-    "that includes a substring of the arguments may have null values for the tool name and id).\n",
-    "\n",
-    "Because message chunks inherit from their parent message class, an \n",
-    "[AIMessageChunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk) \n",
-    "with tool call chunks will also include `.tool_calls` and `.invalid_tool_calls` fields. \n",
-    "These fields are parsed best-effort from the message's tool call chunks.\n",
-    "\n",
-    "Note that not all providers currently support streaming for tool calls:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[]\n",
-      "[{'name': 'Multiply', 'args': '', 'id': 'call_3aQwTP9CYlFxwOvQZPHDu6wL', 'index': 0}]\n",
-      "[{'name': None, 'args': '{\"a\"', 'id': None, 'index': 0}]\n",
-      "[{'name': None, 'args': ': 3, ', 'id': None, 'index': 0}]\n",
-      "[{'name': None, 'args': '\"b\": 1', 'id': None, 'index': 0}]\n",
-      "[{'name': None, 'args': '2}', 'id': None, 'index': 0}]\n",
-      "[{'name': 'Add', 'args': '', 'id': 'call_SQUoSsJz2p9Kx2x73GOgN1ja', 'index': 1}]\n",
-      "[{'name': None, 'args': '{\"a\"', 'id': None, 'index': 1}]\n",
-      "[{'name': None, 'args': ': 11,', 'id': None, 'index': 1}]\n",
-      "[{'name': None, 'args': ' \"b\": ', 'id': None, 'index': 1}]\n",
-      "[{'name': None, 'args': '49}', 'id': None, 'index': 1}]\n",
-      "[]\n"
-     ]
-    }
-   ],
-   "source": [
-    "async for chunk in llm_with_tools.astream(query):\n",
-    "    print(chunk.tool_call_chunks)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Note that adding message chunks will merge their corresponding tool call chunks. This is the principle by which LangChain's various [tool output parsers](/docs/how_to/output_parser_structured) support streaming.\n",
-    "\n",
-    "For example, below we accumulate tool call chunks:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[]\n",
-      "[{'name': 'Multiply', 'args': '', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\"', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, ', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 1', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\"', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11,', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": ', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": 49}', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": 49}', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n"
-     ]
-    }
-   ],
-   "source": [
-    "first = True\n",
-    "async for chunk in llm_with_tools.astream(query):\n",
-    "    if first:\n",
-    "        gathered = chunk\n",
-    "        first = False\n",
-    "    else:\n",
-    "        gathered = gathered + chunk\n",
-    "\n",
-    "    print(gathered.tool_call_chunks)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<class 'str'>\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(type(gathered.tool_call_chunks[0][\"args\"]))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And below we accumulate tool calls to demonstrate partial parsing:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[]\n",
-      "[]\n",
-      "[{'name': 'Multiply', 'args': {}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 1}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n"
-     ]
-    }
-   ],
-   "source": [
-    "first = True\n",
-    "async for chunk in llm_with_tools.astream(query):\n",
-    "    if first:\n",
-    "        gathered = chunk\n",
-    "        first = False\n",
-    "    else:\n",
-    "        gathered = gathered + chunk\n",
-    "\n",
-    "    print(gathered.tool_calls)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<class 'dict'>\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(type(gathered.tool_calls[0][\"args\"]))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Passing tool outputs to the model\n",
-    "\n",
-    "If we're using the model-generated tool invocations to actually call tools and want to pass the tool results back to the model, we can do so using `ToolMessage`s."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[HumanMessage(content='What is 3 * 12? Also, what is 11 + 49?'),\n",
-       " AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_svc2GLSxNFALbaCAbSjMI9J8', 'function': {'arguments': '{\"a\": 3, \"b\": 12}', 'name': 'Multiply'}, 'type': 'function'}, {'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh', 'function': {'arguments': '{\"a\": 11, \"b\": 49}', 'name': 'Add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 50, 'prompt_tokens': 105, 'total_tokens': 155}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a79ad1dd-95f1-4a46-b688-4c83f327a7b3-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_svc2GLSxNFALbaCAbSjMI9J8'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh'}]),\n",
-       " ToolMessage(content='36', tool_call_id='call_svc2GLSxNFALbaCAbSjMI9J8'),\n",
-       " ToolMessage(content='60', tool_call_id='call_r8jxte3zW6h3MEGV3zH2qzFh')]"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import HumanMessage, ToolMessage\n",
-    "\n",
-    "messages = [HumanMessage(query)]\n",
-    "ai_msg = llm_with_tools.invoke(messages)\n",
-    "messages.append(ai_msg)\n",
-    "for tool_call in ai_msg.tool_calls:\n",
-    "    selected_tool = {\"add\": add, \"multiply\": multiply}[tool_call[\"name\"].lower()]\n",
-    "    tool_output = selected_tool.invoke(tool_call[\"args\"])\n",
-    "    messages.append(ToolMessage(tool_output, tool_call_id=tool_call[\"id\"]))\n",
-    "messages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='3 * 12 is 36 and 11 + 49 is 60.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 171, 'total_tokens': 189}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'stop', 'logprobs': None}, id='run-20b52149-e00d-48ea-97cf-f8de7a255f8c-0')"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_with_tools.invoke(messages)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Note that we pass back the same `id` in the `ToolMessage` as the what we receive from the model in order to help the model match tool responses with tool calls.\n",
-    "\n",
-    "## Few-shot prompting\n",
-    "\n",
-    "For more complex tool use it's very useful to add few-shot examples to the prompt. We can do this by adding `AIMessage`s with `ToolCall`s and corresponding `ToolMessage`s to our prompt.\n",
-    "\n",
-    "For example, even with some special instructions our model can get tripped up by order of operations:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[{'name': 'Multiply',\n",
-       "  'args': {'a': 119, 'b': 8},\n",
-       "  'id': 'call_T88XN6ECucTgbXXkyDeC2CQj'},\n",
-       " {'name': 'Add',\n",
-       "  'args': {'a': 952, 'b': -20},\n",
-       "  'id': 'call_licdlmGsRqzup8rhqJSb1yZ4'}]"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_with_tools.invoke(\n",
-    "    \"Whats 119 times 8 minus 20. Don't do any math yourself, only use tools for math. Respect order of operations\"\n",
-    ").tool_calls"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The model shouldn't be trying to add anything yet, since it technically can't know the results of 119 * 8 yet.\n",
-    "\n",
-    "By adding a prompt with some examples we can correct this behavior:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[{'name': 'Multiply',\n",
-       "  'args': {'a': 119, 'b': 8},\n",
-       "  'id': 'call_9MvuwQqg7dlJupJcoTWiEsDo'}]"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import AIMessage\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "\n",
-    "examples = [\n",
-    "    HumanMessage(\n",
-    "        \"What's the product of 317253 and 128472 plus four\", name=\"example_user\"\n",
-    "    ),\n",
-    "    AIMessage(\n",
-    "        \"\",\n",
-    "        name=\"example_assistant\",\n",
-    "        tool_calls=[\n",
-    "            {\"name\": \"Multiply\", \"args\": {\"x\": 317253, \"y\": 128472}, \"id\": \"1\"}\n",
-    "        ],\n",
-    "    ),\n",
-    "    ToolMessage(\"16505054784\", tool_call_id=\"1\"),\n",
-    "    AIMessage(\n",
-    "        \"\",\n",
-    "        name=\"example_assistant\",\n",
-    "        tool_calls=[{\"name\": \"Add\", \"args\": {\"x\": 16505054784, \"y\": 4}, \"id\": \"2\"}],\n",
-    "    ),\n",
-    "    ToolMessage(\"16505054788\", tool_call_id=\"2\"),\n",
-    "    AIMessage(\n",
-    "        \"The product of 317253 and 128472 plus four is 16505054788\",\n",
-    "        name=\"example_assistant\",\n",
-    "    ),\n",
-    "]\n",
-    "\n",
-    "system = \"\"\"You are bad at math but are an expert at using a calculator. \n",
-    "\n",
-    "Use past tool usage as an example of how to correctly use the tools.\"\"\"\n",
-    "few_shot_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", system),\n",
-    "        *examples,\n",
-    "        (\"human\", \"{query}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "chain = {\"query\": RunnablePassthrough()} | few_shot_prompt | llm_with_tools\n",
-    "chain.invoke(\"Whats 119 times 8 minus 20\").tool_calls"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And we get the correct output this time.\n",
-    "\n",
-    "Here's what the [LangSmith trace](https://smith.langchain.com/public/f70550a1-585f-4c9d-a643-13148ab1616f/r) looks like."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Binding model-specific formats (advanced)\n",
-    "\n",
-    "Providers adopt different conventions for formatting tool schemas. \n",
-    "For instance, OpenAI uses a format like this:\n",
-    "\n",
-    "- `type`: The type of the tool. At the time of writing, this is always `\"function\"`.\n",
-    "- `function`: An object containing tool parameters.\n",
-    "- `function.name`: The name of the schema to output.\n",
-    "- `function.description`: A high level description of the schema to output.\n",
-    "- `function.parameters`: The nested details of the schema you want to extract, formatted as a [JSON schema](https://json-schema.org/) dict.\n",
-    "\n",
-    "We can bind this model-specific format directly to the model as well if preferred. Here's an example:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_mn4ELw1NbuE0DFYhIeK0GrPe', 'function': {'arguments': '{\"a\":119,\"b\":8}', 'name': 'multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 17, 'prompt_tokens': 62, 'total_tokens': 79}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-353e8a9a-7125-4f94-8c68-4f3da4c21120-0', tool_calls=[{'name': 'multiply', 'args': {'a': 119, 'b': 8}, 'id': 'call_mn4ELw1NbuE0DFYhIeK0GrPe'}])"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
-    "model_with_tools = model.bind(\n",
-    "    tools=[\n",
-    "        {\n",
-    "            \"type\": \"function\",\n",
-    "            \"function\": {\n",
-    "                \"name\": \"multiply\",\n",
-    "                \"description\": \"Multiply two integers together.\",\n",
-    "                \"parameters\": {\n",
-    "                    \"type\": \"object\",\n",
-    "                    \"properties\": {\n",
-    "                        \"a\": {\"type\": \"number\", \"description\": \"First integer\"},\n",
-    "                        \"b\": {\"type\": \"number\", \"description\": \"Second integer\"},\n",
-    "                    },\n",
-    "                    \"required\": [\"a\", \"b\"],\n",
-    "                },\n",
-    "            },\n",
-    "        }\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "model_with_tools.invoke(\"Whats 119 times 8?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This is functionally equivalent to the `bind_tools()` calls above."
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "## Next steps\n",
     "\n",
-    "Now you've learned how to bind tool schemas to a chat model and to call those tools. Next, check out some more specific uses of tool calling:\n",
+    "Now you've learned how to bind tool schemas to a chat model and to call those tools. Next, you can learn more about how to use tools:\n",
+    "\n",
+    "- Few shot promting [with tools](/docs/how_to/tools_few_shot/)\n",
+    "- Stream [tool calls](/docs/how_to/tool_streaming/)\n",
+    "- Bind [model-specific tools](/docs/how_to/tools_model_specific/)\n",
+    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)\n",
+    "- Pass [tool results back to model](/docs/how_to/tool_results_pass_to_model)\n",
+    "\n",
+    "You can also check out some more specific uses of tool calling:\n",
     "\n",
     "- Building [tool-using chains and agents](/docs/how_to#tools)\n",
     "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
@@ -781,7 +343,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/tool_calling_parallel.ipynb

@@ -0,0 +1,108 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Disabling parallel tool calling (OpenAI only)\n",
+    "\n",
+    "OpenAI tool calling performs tool calling in parallel by default. That means that if we ask a question like \"What is the weather in Tokyo, New York, and Chicago?\" and we have a tool for getting the weather, it will call the tool 3 times in parallel. We can force it to call only a single tool once by using the ``parallel_tool_call`` parameter."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "First let's set up our tools and model:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(a: int, b: int) -> int:\n",
+    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    return a + b\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(a: int, b: int) -> int:\n",
+    "    \"\"\"Multiplies a and b.\"\"\"\n",
+    "    return a * b\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now let's show a quick example of how disabling parallel tool calls work:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'add',\n",
+       "  'args': {'a': 2, 'b': 2},\n",
+       "  'id': 'call_Hh4JOTCDM85Sm9Pr84VKrWu5'}]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm_with_tools = llm.bind_tools(tools, parallel_tool_calls=False)\n",
+    "llm_with_tools.invoke(\"Please call the first tool two times\").tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "As we can see, even though we explicitly told the model to call a tool twice, by disabling parallel tool calls the model was constrained to only calling one."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tool_choice.ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to force tool calling behavior\n",
+    "\n",
+    "In order to force our LLM to spelect a specific tool, we can use the `tool_choice` parameter to ensure certain behavior. First, let's define our model and tools:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(a: int, b: int) -> int:\n",
+    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    return a + b\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(a: int, b: int) -> int:\n",
+    "    \"\"\"Multiplies a and b.\"\"\"\n",
+    "    return a * b\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "%pip install -qU langchain langchain_openai\n",
+    "\n",
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "For example, we can force our tool to call the multiply tool by using the following code:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_9cViskmLvPnHjXk9tbVla5HA', 'function': {'arguments': '{\"a\":2,\"b\":4}', 'name': 'Multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 9, 'prompt_tokens': 103, 'total_tokens': 112}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-095b827e-2bdd-43bb-8897-c843f4504883-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 2, 'b': 4}, 'id': 'call_9cViskmLvPnHjXk9tbVla5HA'}], usage_metadata={'input_tokens': 103, 'output_tokens': 9, 'total_tokens': 112})"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm_forced_to_multiply = llm.bind_tools(tools, tool_choice=\"Multiply\")\n",
+    "llm_forced_to_multiply.invoke(\"what is 2 + 4\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Even if we pass it something that doesn't require multiplcation - it will still call the tool!"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We can also just force our tool to select at least one of our tools by passing in the \"any\" (or \"required\" which is OpenAI specific) keyword to the `tool_choice` parameter."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_mCSiJntCwHJUBfaHZVUB2D8W', 'function': {'arguments': '{\"a\":1,\"b\":2}', 'name': 'Add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 15, 'prompt_tokens': 94, 'total_tokens': 109}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-28f75260-9900-4bed-8cd3-f1579abb65e5-0', tool_calls=[{'name': 'Add', 'args': {'a': 1, 'b': 2}, 'id': 'call_mCSiJntCwHJUBfaHZVUB2D8W'}], usage_metadata={'input_tokens': 94, 'output_tokens': 15, 'total_tokens': 109})"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm_forced_to_use_tool = llm.bind_tools(tools, tool_choice=\"any\")\n",
+    "llm_forced_to_use_tool.invoke(\"What day is today?\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tool_results_pass_to_model.ipynb

@@ -0,0 +1,127 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to pass tool outputs to the model\n",
+    "\n",
+    "If we're using the model-generated tool invocations to actually call tools and want to pass the tool results back to the model, we can do so using `ToolMessage`s. First, let's define our tools and our model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(a: int, b: int) -> int:\n",
+    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    return a + b\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(a: int, b: int) -> int:\n",
+    "    \"\"\"Multiplies a and b.\"\"\"\n",
+    "    return a * b\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm_with_tools = llm.bind_tools(tools)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now we can use ``ToolMessage`` to pass back the output of the tool calls to the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='What is 3 * 12? Also, what is 11 + 49?'),\n",
+       " AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_svc2GLSxNFALbaCAbSjMI9J8', 'function': {'arguments': '{\"a\": 3, \"b\": 12}', 'name': 'Multiply'}, 'type': 'function'}, {'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh', 'function': {'arguments': '{\"a\": 11, \"b\": 49}', 'name': 'Add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 50, 'prompt_tokens': 105, 'total_tokens': 155}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a79ad1dd-95f1-4a46-b688-4c83f327a7b3-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_svc2GLSxNFALbaCAbSjMI9J8'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh'}]),\n",
+       " ToolMessage(content='36', tool_call_id='call_svc2GLSxNFALbaCAbSjMI9J8'),\n",
+       " ToolMessage(content='60', tool_call_id='call_r8jxte3zW6h3MEGV3zH2qzFh')]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import HumanMessage, ToolMessage\n",
+    "\n",
+    "query = \"What is 3 * 12? Also, what is 11 + 49?\"\n",
+    "\n",
+    "messages = [HumanMessage(query)]\n",
+    "ai_msg = llm_with_tools.invoke(messages)\n",
+    "messages.append(ai_msg)\n",
+    "for tool_call in ai_msg.tool_calls:\n",
+    "    selected_tool = {\"add\": add, \"multiply\": multiply}[tool_call[\"name\"].lower()]\n",
+    "    tool_output = selected_tool.invoke(tool_call[\"args\"])\n",
+    "    messages.append(ToolMessage(tool_output, tool_call_id=tool_call[\"id\"]))\n",
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='3 * 12 is 36 and 11 + 49 is 60.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 171, 'total_tokens': 189}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'stop', 'logprobs': None}, id='run-20b52149-e00d-48ea-97cf-f8de7a255f8c-0')"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm_with_tools.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note that we pass back the same `id` in the `ToolMessage` as the what we receive from the model in order to help the model match tool responses with tool calls."
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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](https://python.langchain.com/v0.2/docs/how_to/tool_calling)\n",
     ":::\n",
     "\n",
     ":::{.callout-info} Supported models\n",
@@ -227,7 +227,7 @@
     "\n",
     "Chat models only output requests to invoke tools, they don't actually invoke the underlying tools.\n",
     "\n",
-    "To see how to invoke the tools, please refer to [how to use a model to call tools](https://python.langchain.com/v0.2/docs/how_to/tool_calling/).\n",
+    "To see how to invoke the tools, please refer to [how to use a model to call tools](https://python.langchain.com/v0.2/docs/how_to/tool_calling).\n",
     ":::"
    ]
   }

docs/docs/how_to/tool_streaming.ipynb

@@ -0,0 +1,235 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to stream tool calls\n",
+    "\n",
+    "When tools are called in a streaming context, \n",
+    "[message chunks](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk) \n",
+    "will be populated with [tool call chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolCallChunk.html#langchain_core.messages.tool.ToolCallChunk) \n",
+    "objects in a list via the `.tool_call_chunks` attribute. A `ToolCallChunk` includes \n",
+    "optional string fields for the tool `name`, `args`, and `id`, and includes an optional \n",
+    "integer field `index` that can be used to join chunks together. Fields are optional \n",
+    "because portions of a tool call may be streamed across different chunks (e.g., a chunk \n",
+    "that includes a substring of the arguments may have null values for the tool name and id).\n",
+    "\n",
+    "Because message chunks inherit from their parent message class, an \n",
+    "[AIMessageChunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk) \n",
+    "with tool call chunks will also include `.tool_calls` and `.invalid_tool_calls` fields. \n",
+    "These fields are parsed best-effort from the message's tool call chunks.\n",
+    "\n",
+    "Note that not all providers currently support streaming for tool calls. Before we start let's define our tools and our model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(a: int, b: int) -> int:\n",
+    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    return a + b\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(a: int, b: int) -> int:\n",
+    "    \"\"\"Multiplies a and b.\"\"\"\n",
+    "    return a * b\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm_with_tools = llm.bind_tools(tools)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now let's define our query and stream our output:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[]\n",
+      "[{'name': 'Multiply', 'args': '', 'id': 'call_3aQwTP9CYlFxwOvQZPHDu6wL', 'index': 0}]\n",
+      "[{'name': None, 'args': '{\"a\"', 'id': None, 'index': 0}]\n",
+      "[{'name': None, 'args': ': 3, ', 'id': None, 'index': 0}]\n",
+      "[{'name': None, 'args': '\"b\": 1', 'id': None, 'index': 0}]\n",
+      "[{'name': None, 'args': '2}', 'id': None, 'index': 0}]\n",
+      "[{'name': 'Add', 'args': '', 'id': 'call_SQUoSsJz2p9Kx2x73GOgN1ja', 'index': 1}]\n",
+      "[{'name': None, 'args': '{\"a\"', 'id': None, 'index': 1}]\n",
+      "[{'name': None, 'args': ': 11,', 'id': None, 'index': 1}]\n",
+      "[{'name': None, 'args': ' \"b\": ', 'id': None, 'index': 1}]\n",
+      "[{'name': None, 'args': '49}', 'id': None, 'index': 1}]\n",
+      "[]\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"What is 3 * 12? Also, what is 11 + 49?\"\n",
+    "\n",
+    "async for chunk in llm_with_tools.astream(query):\n",
+    "    print(chunk.tool_call_chunks)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note that adding message chunks will merge their corresponding tool call chunks. This is the principle by which LangChain's various [tool output parsers](/docs/how_to/output_parser_structured) support streaming.\n",
+    "\n",
+    "For example, below we accumulate tool call chunks:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[]\n",
+      "[{'name': 'Multiply', 'args': '', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\"', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, ', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 1', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\"', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11,', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": ', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": 49}', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": 49}', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "first = True\n",
+    "async for chunk in llm_with_tools.astream(query):\n",
+    "    if first:\n",
+    "        gathered = chunk\n",
+    "        first = False\n",
+    "    else:\n",
+    "        gathered = gathered + chunk\n",
+    "\n",
+    "    print(gathered.tool_call_chunks)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'str'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(type(gathered.tool_call_chunks[0][\"args\"]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And below we accumulate tool calls to demonstrate partial parsing:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[]\n",
+      "[]\n",
+      "[{'name': 'Multiply', 'args': {}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 1}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "first = True\n",
+    "async for chunk in llm_with_tools.astream(query):\n",
+    "    if first:\n",
+    "        gathered = chunk\n",
+    "        first = False\n",
+    "    else:\n",
+    "        gathered = gathered + chunk\n",
+    "\n",
+    "    print(gathered.tool_calls)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'dict'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(type(gathered.tool_calls[0][\"args\"]))"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tools_few_shot.ipynb

@@ -0,0 +1,175 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to use few-shot prompting with tool calling\n",
+    "\n",
+    "For more complex tool use it's very useful to add few-shot examples to the prompt. We can do this by adding `AIMessage`s with `ToolCall`s and corresponding `ToolMessage`s to our prompt.\n",
+    "\n",
+    "First let's define our tools and model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(a: int, b: int) -> int:\n",
+    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    return a + b\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(a: int, b: int) -> int:\n",
+    "    \"\"\"Multiplies a and b.\"\"\"\n",
+    "    return a * b\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm_with_tools = llm.bind_tools(tools)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's run our model where we can notice that even with some special instructions our model can get tripped up by order of operations. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'Multiply',\n",
+       "  'args': {'a': 119, 'b': 8},\n",
+       "  'id': 'call_T88XN6ECucTgbXXkyDeC2CQj'},\n",
+       " {'name': 'Add',\n",
+       "  'args': {'a': 952, 'b': -20},\n",
+       "  'id': 'call_licdlmGsRqzup8rhqJSb1yZ4'}]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm_with_tools.invoke(\n",
+    "    \"Whats 119 times 8 minus 20. Don't do any math yourself, only use tools for math. Respect order of operations\"\n",
+    ").tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The model shouldn't be trying to add anything yet, since it technically can't know the results of 119 * 8 yet.\n",
+    "\n",
+    "By adding a prompt with some examples we can correct this behavior:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'Multiply',\n",
+       "  'args': {'a': 119, 'b': 8},\n",
+       "  'id': 'call_9MvuwQqg7dlJupJcoTWiEsDo'}]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import AIMessage, HumanMessage, ToolMessage\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "examples = [\n",
+    "    HumanMessage(\n",
+    "        \"What's the product of 317253 and 128472 plus four\", name=\"example_user\"\n",
+    "    ),\n",
+    "    AIMessage(\n",
+    "        \"\",\n",
+    "        name=\"example_assistant\",\n",
+    "        tool_calls=[\n",
+    "            {\"name\": \"Multiply\", \"args\": {\"x\": 317253, \"y\": 128472}, \"id\": \"1\"}\n",
+    "        ],\n",
+    "    ),\n",
+    "    ToolMessage(\"16505054784\", tool_call_id=\"1\"),\n",
+    "    AIMessage(\n",
+    "        \"\",\n",
+    "        name=\"example_assistant\",\n",
+    "        tool_calls=[{\"name\": \"Add\", \"args\": {\"x\": 16505054784, \"y\": 4}, \"id\": \"2\"}],\n",
+    "    ),\n",
+    "    ToolMessage(\"16505054788\", tool_call_id=\"2\"),\n",
+    "    AIMessage(\n",
+    "        \"The product of 317253 and 128472 plus four is 16505054788\",\n",
+    "        name=\"example_assistant\",\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "system = \"\"\"You are bad at math but are an expert at using a calculator. \n",
+    "\n",
+    "Use past tool usage as an example of how to correctly use the tools.\"\"\"\n",
+    "few_shot_prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", system),\n",
+    "        *examples,\n",
+    "        (\"human\", \"{query}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = {\"query\": RunnablePassthrough()} | few_shot_prompt | llm_with_tools\n",
+    "chain.invoke(\"Whats 119 times 8 minus 20\").tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And we get the correct output this time.\n",
+    "\n",
+    "Here's what the [LangSmith trace](https://smith.langchain.com/public/f70550a1-585f-4c9d-a643-13148ab1616f/r) looks like."
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tools_model_specific.ipynb

@@ -0,0 +1,79 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to bind model-specific tools\n",
+    "\n",
+    "Providers adopt different conventions for formatting tool schemas. \n",
+    "For instance, OpenAI uses a format like this:\n",
+    "\n",
+    "- `type`: The type of the tool. At the time of writing, this is always `\"function\"`.\n",
+    "- `function`: An object containing tool parameters.\n",
+    "- `function.name`: The name of the schema to output.\n",
+    "- `function.description`: A high level description of the schema to output.\n",
+    "- `function.parameters`: The nested details of the schema you want to extract, formatted as a [JSON schema](https://json-schema.org/) dict.\n",
+    "\n",
+    "We can bind this model-specific format directly to the model as well if preferred. Here's an example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_mn4ELw1NbuE0DFYhIeK0GrPe', 'function': {'arguments': '{\"a\":119,\"b\":8}', 'name': 'multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 17, 'prompt_tokens': 62, 'total_tokens': 79}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-353e8a9a-7125-4f94-8c68-4f3da4c21120-0', tool_calls=[{'name': 'multiply', 'args': {'a': 119, 'b': 8}, 'id': 'call_mn4ELw1NbuE0DFYhIeK0GrPe'}])"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI()\n",
+    "\n",
+    "model_with_tools = model.bind(\n",
+    "    tools=[\n",
+    "        {\n",
+    "            \"type\": \"function\",\n",
+    "            \"function\": {\n",
+    "                \"name\": \"multiply\",\n",
+    "                \"description\": \"Multiply two integers together.\",\n",
+    "                \"parameters\": {\n",
+    "                    \"type\": \"object\",\n",
+    "                    \"properties\": {\n",
+    "                        \"a\": {\"type\": \"number\", \"description\": \"First integer\"},\n",
+    "                        \"b\": {\"type\": \"number\", \"description\": \"Second integer\"},\n",
+    "                    },\n",
+    "                    \"required\": [\"a\", \"b\"],\n",
+    "                },\n",
+    "            },\n",
+    "        }\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "model_with_tools.invoke(\"Whats 119 times 8?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This is functionally equivalent to the `bind_tools()` method."
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tools_prompting.ipynb

@@ -19,7 +19,7 @@
     "\n",
     ":::{.callout-caution}\n",
     "\n",
-    "Some models have been fine-tuned for tool calling and provide a dedicated API for tool calling. Generally, such models are better at tool calling than non-fine-tuned models, and are recommended for use cases that require tool calling. Please see the [how to use a chat model to call tools](/docs/how_to/tool_calling/) guide for more information.\n",
+    "Some models have been fine-tuned for tool calling and provide a dedicated API for tool calling. Generally, such models are better at tool calling than non-fine-tuned models, and are recommended for use cases that require tool calling. Please see the [how to use a chat model to call tools](/docs/how_to/tool_calling) guide for more information.\n",
     "\n",
     ":::\n",
     "\n",
@@ -34,7 +34,7 @@
     "\n",
     ":::\n",
     "\n",
-    "In this guide, we'll see how to add **ad-hoc** tool calling support to a chat model. This is an alternative method to invoke tools if you're using a model that does not natively support [tool calling](/docs/how_to/tool_calling/).\n",
+    "In this guide, we'll see how to add **ad-hoc** tool calling support to a chat model. This is an alternative method to invoke tools if you're using a model that does not natively support [tool calling](/docs/how_to/tool_calling).\n",
     "\n",
     "We'll do this by simply writing a prompt that will get the model to invoke the appropriate tools. Here's a diagram of the logic:\n",
     "\n",
@@ -87,7 +87,7 @@
    "id": "7ec6409b-21e5-4d0a-8a46-c4ef0b055dd3",
    "metadata": {},
    "source": [
-    "You can select any of the given models for this how-to guide. Keep in mind that most of these models already [support native tool calling](/docs/integrations/chat/), so using the prompting strategy shown here doesn't make sense for these models, and instead you should follow the [how to use a chat model to call tools](/docs/how_to/tool_calling/) guide.\n",
+    "You can select any of the given models for this how-to guide. Keep in mind that most of these models already [support native tool calling](/docs/integrations/chat/), so using the prompting strategy shown here doesn't make sense for these models, and instead you should follow the [how to use a chat model to call tools](/docs/how_to/tool_calling) guide.\n",
     "\n",
     "```{=mdx}\n",
     "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",

docs/docs/how_to/trim_messages.ipynb

@@ -323,7 +323,7 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='A \"polygon\"! Because it\\'s a \"poly-gone\" silent!', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 32, 'total_tokens': 46}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_319be4768e', 'finish_reason': 'stop', 'logprobs': None}, id='run-64cc4575-14d1-4f3f-b4af-97f24758f703-0', usage_metadata={'input_tokens': 32, 'output_tokens': 14, 'total_tokens': 46})"
+       "AIMessage(content='A: A \"Polly-gone\"!', response_metadata={'token_usage': {'completion_tokens': 9, 'prompt_tokens': 32, 'total_tokens': 41}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_66b29dffce', 'finish_reason': 'stop', 'logprobs': None}, id='run-83e96ddf-bcaa-4f63-824c-98b0f8a0d474-0', usage_metadata={'input_tokens': 32, 'output_tokens': 9, 'total_tokens': 41})"
       ]
      },
      "execution_count": 7,
@@ -391,24 +391,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 9,
    "id": "a9517858-fc2f-4dc3-898d-bf98a0e905a0",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Parent run c87e2f1b-81ad-4fa7-bfd9-ce6edb29a482 not found for run 7892ee8f-0669-4d6b-a2ca-ef8aae81042a. Treating as a root run.\n"
-     ]
-    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"A polygon! Because it's a parrot gone quiet!\", response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 32, 'total_tokens': 43}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_319be4768e', 'finish_reason': 'stop', 'logprobs': None}, id='run-72dad96e-8b58-45f4-8c08-21f9f1a6b68f-0', usage_metadata={'input_tokens': 32, 'output_tokens': 11, 'total_tokens': 43})"
+       "AIMessage(content='A \"polly-no-wanna-cracker\"!', response_metadata={'token_usage': {'completion_tokens': 10, 'prompt_tokens': 32, 'total_tokens': 42}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_5bf7397cd3', 'finish_reason': 'stop', 'logprobs': None}, id='run-054dd309-3497-4e7b-b22a-c1859f11d32e-0', usage_metadata={'input_tokens': 32, 'output_tokens': 10, 'total_tokens': 42})"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -422,7 +415,7 @@
     "\n",
     "def dummy_get_session_history(session_id):\n",
     "    if session_id != \"1\":\n",
-    "        raise InMemoryChatMessageHistory()\n",
+    "        return InMemoryChatMessageHistory()\n",
     "    return chat_history\n",
     "\n",
     "\n",
@@ -464,9 +457,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv-2",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "poetry-venv-2"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -478,7 +471,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/ai21.ipynb

@@ -18,7 +18,9 @@
     "# ChatAI21\n",
     "\n",
     "This notebook covers how to get started with AI21 chat models.\n",
-    "\n",
+    "Note that different chat models support different parameters. See the ",
+    "[AI21 documentation](https://docs.ai21.com/reference) to learn more about the parameters in your chosen model.\n",
+    "[See all AI21's LangChain components.](https://pypi.org/project/langchain-ai21/) \n",
     "## Installation"
    ]
   },
@@ -44,7 +46,8 @@
    "source": [
     "## Environment Setup\n",
     "\n",
-    "We'll need to get a [AI21 API key](https://docs.ai21.com/) and set the `AI21_API_KEY` environment variable:\n"
+    "We'll need to get an [AI21 API key](https://docs.ai21.com/) and set the ",
+    "`AI21_API_KEY` environment variable:\n"
    ]
   },
   {

docs/docs/integrations/chat/anthropic.ipynb

@@ -36,7 +36,7 @@
     "| [ChatAnthropic](https://api.python.langchain.com/en/latest/chat_models/langchain_anthropic.chat_models.ChatAnthropic.html) | [langchain-anthropic](https://api.python.langchain.com/en/latest/anthropic_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-anthropic?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-anthropic?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",
+    "| [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",

docs/docs/integrations/chat/azure_chat_openai.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "641f8cb0",
+   "id": "afaf8039",
    "metadata": {},
    "source": [
     "---\n",
@@ -12,20 +12,89 @@
   },
   {
    "cell_type": "markdown",
-   "id": "38f26d7a",
+   "id": "e49f1e0d",
    "metadata": {},
    "source": [
     "# AzureChatOpenAI\n",
     "\n",
-    ">[Azure OpenAI Service](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview) provides REST API access to OpenAI's powerful language models including the GPT-4, GPT-3.5-Turbo, and Embeddings model series. These models can be easily adapted to your specific task including but not limited to content generation, summarization, semantic search, and natural language to code translation. Users can access the service through REST APIs, Python SDK, or a web-based interface in the Azure OpenAI Studio.\n",
+    "This guide will help you get started with AzureOpenAI [chat models](/docs/concepts/#chat-models). For detailed documentation of all AzureChatOpenAI features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.html).\n",
     "\n",
-    "This notebook goes over how to connect to an Azure-hosted OpenAI endpoint. First, we need to install the `langchain-openai` package."
+    "Azure OpenAI has several chat models. You can find information about their latest models and their costs, context windows, and supported input types in the [Azure docs](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models).\n",
+    "\n",
+    ":::info Azure OpenAI vs OpenAI\n",
+    "\n",
+    "Azure OpenAI refers to OpenAI models hosted on the [Microsoft Azure platform](https://azure.microsoft.com/en-us/products/ai-services/openai-service). OpenAI also provides its own model APIs. To access OpenAI services directly, use the [ChatOpenAI integration](/docs/integrations/chat/openai/).\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/azure) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [AzureChatOpenAI](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.html) | [langchain-openai](https://api.python.langchain.com/en/latest/openai_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-openai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-openai?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 AzureOpenAI models you'll need to create an Azure account, create a deployment of an Azure OpenAI model, get the name and endpoint for your deployment, get an Azure OpenAI API key, and install the `langchain-openai` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Head to the [Azure docs](https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart?tabs=command-line%2Cpython-new&pivots=programming-language-python) to create your deployment and generate an API key. Once you've done this set the AZURE_OPENAI_API_KEY and AZURE_OPENAI_ENDPOINT environment variables:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d83ba7de",
+   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"AZURE_OPENAI_API_KEY\"] = getpass.getpass(\"Enter your AzureOpenAI API key: \")\n",
+    "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"https://YOUR-ENDPOINT.openai.azure.com/\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain AzureOpenAI integration lives in the `langchain-openai` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -34,65 +103,56 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e39133c8",
-   "metadata": {
-    "vscode": {
-     "languageId": "raw"
-    }
-   },
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
+   "metadata": {},
    "source": [
-    "Next, let's set some environment variables to help us connect to the Azure OpenAI service. You can find these values in the Azure portal."
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions.\n",
+    "- Replace `azure_deployment` with the name of your deployment,\n",
+    "- You can find the latest supported `api_version` here: https://learn.microsoft.com/en-us/azure/ai-services/openai/reference."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "1d8d73bd",
+   "execution_count": 1,
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
+    "from langchain_openai import AzureChatOpenAI\n",
     "\n",
-    "os.environ[\"AZURE_OPENAI_API_KEY\"] = \"...\"\n",
-    "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"https://<your-endpoint>.openai.azure.com/\"\n",
-    "os.environ[\"AZURE_OPENAI_API_VERSION\"] = \"2023-06-01-preview\"\n",
-    "os.environ[\"AZURE_OPENAI_CHAT_DEPLOYMENT_NAME\"] = \"chat\""
+    "llm = AzureChatOpenAI(\n",
+    "    azure_deployment=\"YOUR-DEPLOYMENT\",\n",
+    "    api_version=\"2024-05-01-preview\",\n",
+    "    temperature=0,\n",
+    "    max_tokens=None,\n",
+    "    timeout=None,\n",
+    "    max_retries=2,\n",
+    "    # other params...\n",
+    ")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "e7b160f8",
+   "id": "2b4f3e15",
    "metadata": {},
    "source": [
-    "Next, let's construct our model and chat with it:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "cbe4bb58-ba13-4355-8af9-cd990dc47a64",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "from langchain_openai import AzureChatOpenAI\n",
-    "\n",
-    "model = AzureChatOpenAI(\n",
-    "    openai_api_version=os.environ[\"AZURE_OPENAI_API_VERSION\"],\n",
-    "    azure_deployment=os.environ[\"AZURE_OPENAI_CHAT_DEPLOYMENT_NAME\"],\n",
-    ")"
+    "## Invocation"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "99509140",
-   "metadata": {},
+   "id": "62e0dbc3",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"J'adore programmer.\", response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 19, 'total_tokens': 25}, 'model_name': 'gpt-35-turbo', 'system_fingerprint': None, 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}, id='run-25ed88db-38f2-4b0c-a943-a03f217711a9-0')"
+       "AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'completion_tokens': 8, 'prompt_tokens': 31, 'total_tokens': 39}, 'model_name': 'gpt-35-turbo', 'system_fingerprint': None, 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}, id='run-a6a732c2-cb02-4e50-9a9c-ab30eab034fc-0', usage_metadata={'input_tokens': 31, 'output_tokens': 8, 'total_tokens': 39})"
       ]
      },
      "execution_count": 4,
@@ -101,95 +161,165 @@
     }
    ],
    "source": [
-    "message = HumanMessage(\n",
-    "    content=\"Translate this sentence from English to French. I love programming.\"\n",
-    ")\n",
-    "model.invoke([message])"
+    "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": 11,
+   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "J'adore la programmation.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(ai_msg.content)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "f27fa24d",
+   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
    "metadata": {},
    "source": [
-    "## Model Version\n",
-    "Azure OpenAI responses contain `model` property, which is name of the model used to generate the response. However unlike native OpenAI responses, it does not contain the version of the model, which is set on the deployment in Azure. This makes it tricky to know which version of the model was used to generate the response, which as result can lead to e.g. wrong total cost calculation with `OpenAICallbackHandler`.\n",
+    "## Chaining\n",
+    "\n",
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Ich liebe das Programmieren.', response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 26, 'total_tokens': 32}, 'model_name': 'gpt-35-turbo', 'system_fingerprint': None, 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}, id='run-084967d7-06f2-441f-b5c1-477e2a9e9d03-0', usage_metadata={'input_tokens': 26, 'output_tokens': 6, 'total_tokens': 32})"
+      ]
+     },
+     "execution_count": 12,
+     "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": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
+   "metadata": {},
+   "source": [
+    "## Specifying model version\n",
+    "\n",
+    "Azure OpenAI responses contain `model_name` response metadata property, which is name of the model used to generate the response. However unlike native OpenAI responses, it does not contain the specific version of the model, which is set on the deployment in Azure. E.g. it does not distinguish between `gpt-35-turbo-0125` and `gpt-35-turbo-0301`. This makes it tricky to know which version of the model was used to generate the response, which as result can lead to e.g. wrong total cost calculation with `OpenAICallbackHandler`.\n",
     "\n",
     "To solve this problem, you can pass `model_version` parameter to `AzureChatOpenAI` class, which will be added to the model name in the llm output. This way you can easily distinguish between different versions of the model."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "0531798a",
+   "execution_count": null,
+   "id": "04b36e75-e8b7-4721-899e-76301ac2ecd9",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.callbacks import get_openai_callback"
+    "%pip install -qU langchain-community"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "aceddb72",
-   "metadata": {
-    "scrolled": true
-   },
+   "execution_count": 5,
+   "id": "84c411b0-1790-4798-8bb7-47d8ece4c2dc",
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Total Cost (USD): $0.000041\n"
+      "Total Cost (USD): $0.000063\n"
      ]
     }
    ],
    "source": [
-    "model = AzureChatOpenAI(\n",
-    "    openai_api_version=os.environ[\"AZURE_OPENAI_API_VERSION\"],\n",
-    "    azure_deployment=os.environ[\n",
-    "        \"AZURE_OPENAI_CHAT_DEPLOYMENT_NAME\"\n",
-    "    ],  # in Azure, this deployment has version 0613 - input and output tokens are counted separately\n",
-    ")\n",
+    "from langchain_community.callbacks import get_openai_callback\n",
+    "\n",
     "with get_openai_callback() as cb:\n",
-    "    model.invoke([message])\n",
+    "    llm.invoke(messages)\n",
     "    print(\n",
     "        f\"Total Cost (USD): ${format(cb.total_cost, '.6f')}\"\n",
     "    )  # without specifying the model version, flat-rate 0.002 USD per 1k input and output tokens is used"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "2e61eefd",
-   "metadata": {},
-   "source": [
-    "We can provide the model version to `AzureChatOpenAI` constructor. It will get appended to the model name returned by Azure OpenAI and cost will be counted correctly."
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "8d5e54e9",
+   "execution_count": 6,
+   "id": "21234693-d92b-4d69-8a7f-55aa062084bf",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Total Cost (USD): $0.000044\n"
+      "Total Cost (USD): $0.000078\n"
      ]
     }
    ],
    "source": [
-    "model0301 = AzureChatOpenAI(\n",
-    "    openai_api_version=os.environ[\"AZURE_OPENAI_API_VERSION\"],\n",
-    "    azure_deployment=os.environ[\"AZURE_OPENAI_CHAT_DEPLOYMENT_NAME\"],\n",
+    "llm_0301 = AzureChatOpenAI(\n",
+    "    azure_deployment=\"YOUR-DEPLOYMENT\",\n",
+    "    api_version=\"2024-05-01-preview\",\n",
     "    model_version=\"0301\",\n",
     ")\n",
     "with get_openai_callback() as cb:\n",
-    "    model0301.invoke([message])\n",
+    "    llm_0301.invoke(messages)\n",
     "    print(f\"Total Cost (USD): ${format(cb.total_cost, '.6f')}\")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all AzureChatOpenAI features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.html"
+   ]
   }
  ],
  "metadata": {
@@ -208,7 +338,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/bedrock.ipynb

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

docs/docs/integrations/chat/cohere.ipynb

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

@@ -35,7 +35,7 @@
     "| [ChatVertexAI](https://api.python.langchain.com/en/latest/chat_models/langchain_google_vertexai.chat_models.ChatVertexAI.html) | [langchain-google-vertexai](https://api.python.langchain.com/en/latest/google_vertexai_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-google-vertexai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-google-vertexai?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",
+    "| [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",

docs/docs/integrations/chat/groq.ipynb

@@ -91,7 +91,7 @@
     "\n",
     "## Tool calling\n",
     "\n",
-    "Groq chat models support [tool calling](/docs/how_to/tool_calling/) to generate output matching a specific schema. The model may choose to call multiple tools or the same tool multiple times if appropriate.\n",
+    "Groq chat models support [tool calling](/docs/how_to/tool_calling) to generate output matching a specific schema. The model may choose to call multiple tools or the same tool multiple times if appropriate.\n",
     "\n",
     "Here's an example:"
    ]

docs/docs/integrations/chat/ibm_watsonx.ipynb

@@ -0,0 +1,585 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "1c95cd76",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "sidebar_label: IBM watsonx.ai\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "70996d8a",
+   "metadata": {},
+   "source": [
+    "# ChatWatsonx\n",
+    "\n",
+    ">ChatWatsonx is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) foundation models.\n",
+    "\n",
+    "The aim of these examples is to show how to communicate with `watsonx.ai` models using `LangChain` LLMs API."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef7b088a",
+   "metadata": {},
+   "source": [
+    "## Overview\n",
+    "\n",
+    "### Integration details\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/openai) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatWatsonx](https://api.python.langchain.com/en/latest/ibm_api_reference.html) | [langchain-ibm](https://api.python.langchain.com/en/latest/ibm_api_reference.html) | ❌ | ❌ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ibm?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ibm?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 | 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",
+    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f406e092",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "To access IBM watsonx.ai models you'll need to create an IBM watsonx.ai account, get an API key, and install the `langchain-ibm` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "The cell below defines the credentials required to work with watsonx Foundation Model inferencing.\n",
+    "\n",
+    "**Action:** Provide the IBM Cloud user API key. For details, see\n",
+    "[Managing user API keys](https://cloud.ibm.com/docs/account?topic=account-userapikey&interface=ui)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "11d572a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "watsonx_api_key = getpass()\n",
+    "os.environ[\"WATSONX_APIKEY\"] = watsonx_api_key"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c59782a7",
+   "metadata": {},
+   "source": [
+    "Additionally you are able to pass additional secrets as an environment variable. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f98c573c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"WATSONX_URL\"] = \"your service instance url\"\n",
+    "os.environ[\"WATSONX_TOKEN\"] = \"your token for accessing the CPD cluster\"\n",
+    "os.environ[\"WATSONX_PASSWORD\"] = \"your password for accessing the CPD cluster\"\n",
+    "os.environ[\"WATSONX_USERNAME\"] = \"your username for accessing the CPD cluster\"\n",
+    "os.environ[\"WATSONX_INSTANCE_ID\"] = \"your instance_id for accessing the CPD cluster\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b3dc9176",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain IBM integration lives in the `langchain-ibm` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "387eda86",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -qU langchain-ibm"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e36acbef",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "You might need to adjust model `parameters` for different models or tasks. For details, refer to [Available MetaNames](https://ibm.github.io/watsonx-ai-python-sdk/fm_model.html#metanames.GenTextParamsMetaNames)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "407cd500",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "parameters = {\n",
+    "    \"decoding_method\": \"sample\",\n",
+    "    \"max_new_tokens\": 100,\n",
+    "    \"min_new_tokens\": 1,\n",
+    "    \"stop_sequences\": [\".\"],\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b586538",
+   "metadata": {},
+   "source": [
+    "Initialize the `WatsonxLLM` class with the previously set parameters.\n",
+    "\n",
+    "\n",
+    "**Note**: \n",
+    "\n",
+    "- To provide context for the API call, you must pass the `project_id` or `space_id`. To get your project or space ID, open your project or space, go to the **Manage** tab, and click **General**. For more information see: [Project documentation](https://www.ibm.com/docs/en/watsonx-as-a-service?topic=projects) or [Deployment space documentation](https://www.ibm.com/docs/en/watsonx/saas?topic=spaces-creating-deployment).\n",
+    "- Depending on the region of your provisioned service instance, use one of the urls listed in [watsonx.ai API Authentication](https://ibm.github.io/watsonx-ai-python-sdk/setup_cloud.html#authentication).\n",
+    "\n",
+    "In this example, we’ll use the `project_id` and Dallas URL.\n",
+    "\n",
+    "\n",
+    "You need to specify the `model_id` that will be used for inferencing. You can find the list of all the available models in [Supported foundation models](https://ibm.github.io/watsonx-ai-python-sdk/fm_model.html#ibm_watsonx_ai.foundation_models.utils.enums.ModelTypes)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "98371396",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_ibm import ChatWatsonx\n",
+    "\n",
+    "chat = ChatWatsonx(\n",
+    "    model_id=\"ibm/granite-13b-chat-v2\",\n",
+    "    url=\"https://us-south.ml.cloud.ibm.com\",\n",
+    "    project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
+    "    params=parameters,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2202f4e0",
+   "metadata": {},
+   "source": [
+    "Alternatively, you can use Cloud Pak for Data credentials. For details, see [watsonx.ai software setup](https://ibm.github.io/watsonx-ai-python-sdk/setup_cpd.html).  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "243ecccb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatWatsonx(\n",
+    "    model_id=\"ibm/granite-13b-chat-v2\",\n",
+    "    url=\"PASTE YOUR URL HERE\",\n",
+    "    username=\"PASTE YOUR USERNAME HERE\",\n",
+    "    password=\"PASTE YOUR PASSWORD HERE\",\n",
+    "    instance_id=\"openshift\",\n",
+    "    version=\"4.8\",\n",
+    "    project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
+    "    params=parameters,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "96ed13d4",
+   "metadata": {},
+   "source": [
+    "Instead of `model_id`, you can also pass the `deployment_id` of the previously tuned model. The entire model tuning workflow is described in [Working with TuneExperiment and PromptTuner](https://ibm.github.io/watsonx-ai-python-sdk/pt_working_with_class_and_prompt_tuner.html)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "08e66c88",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatWatsonx(\n",
+    "    deployment_id=\"PASTE YOUR DEPLOYMENT_ID HERE\",\n",
+    "    url=\"https://us-south.ml.cloud.ibm.com\",\n",
+    "    project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
+    "    params=parameters,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f571001d",
+   "metadata": {},
+   "source": [
+    "## Invocation\n",
+    "\n",
+    "To obtain completions, you can call the model directly using a string prompt."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "beea2b5b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Je t'aime pour écouter la Rock.\", response_metadata={'token_usage': {'generated_token_count': 12, 'input_token_count': 28}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-05b305ce-5401-4a10-b557-41a4b15c7f6f-0')"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Invocation\n",
+    "\n",
+    "messages = [\n",
+    "    (\"system\", \"You are a helpful assistant that translates English to French.\"),\n",
+    "    (\n",
+    "        \"human\",\n",
+    "        \"I love you for listening to Rock.\",\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "chat.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "8ab1a25a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Sure, I can help you with that! Horses are large, powerful mammals that belong to the family Equidae.', response_metadata={'token_usage': {'generated_token_count': 24, 'input_token_count': 24}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-391776ff-3b38-4768-91e8-ff64177149e5-0')"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Invocation multiple chat\n",
+    "from langchain_core.messages import (\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    ")\n",
+    "\n",
+    "system_message = SystemMessage(\n",
+    "    content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
+    ")\n",
+    "human_message = HumanMessage(content=\"horse\")\n",
+    "\n",
+    "chat.invoke([system_message, human_message])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "20e4b568",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "Create `ChatPromptTemplate` objects which will be responsible for creating a random question."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "dd919925",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "system = (\n",
+    "    \"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
+    ")\n",
+    "human = \"{input}\"\n",
+    "prompt = ChatPromptTemplate.from_messages([(\"system\", system), (\"human\", human)])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1a013a53",
+   "metadata": {},
+   "source": [
+    "Provide a inputs and run the chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "68160377",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Ich liebe Python.', response_metadata={'token_usage': {'generated_token_count': 5, 'input_token_count': 23}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-1b1ccf5d-0e33-46f2-a087-e2a136ba1fb7-0')"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain = prompt | chat\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love Python\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d2c9da33",
+   "metadata": {},
+   "source": [
+    "## Streaming the Model output \n",
+    "\n",
+    "You can stream the model output."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3f63166a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The moon is a natural satellite of the Earth, and it has been a source of fascination for humans for centuries."
+     ]
+    }
+   ],
+   "source": [
+    "system_message = SystemMessage(\n",
+    "    content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
+    ")\n",
+    "human_message = HumanMessage(content=\"moon\")\n",
+    "\n",
+    "for chunk in chat.stream([system_message, human_message]):\n",
+    "    print(chunk.content, end=\"\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5a7a2aa1",
+   "metadata": {},
+   "source": [
+    "## Batch the Model output \n",
+    "\n",
+    "You can batch the model output."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "9e948729",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[AIMessage(content='Cats are domestic animals that belong to the Felidae family.', response_metadata={'token_usage': {'generated_token_count': 13, 'input_token_count': 24}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-71a8bd7a-a1aa-497b-9bdd-a4d6fe1d471a-0'),\n",
+       " AIMessage(content='Dogs are domesticated mammals of the family Canidae, characterized by their adaptability to various environments and social structures.', response_metadata={'token_usage': {'generated_token_count': 24, 'input_token_count': 24}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-22b7a0cb-e44a-4b68-9921-872f82dcd82b-0')]"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "message_1 = [\n",
+    "    SystemMessage(\n",
+    "        content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
+    "    ),\n",
+    "    HumanMessage(content=\"cat\"),\n",
+    "]\n",
+    "message_2 = [\n",
+    "    SystemMessage(\n",
+    "        content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
+    "    ),\n",
+    "    HumanMessage(content=\"dog\"),\n",
+    "]\n",
+    "\n",
+    "chat.batch([message_1, message_2])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c739e1fe",
+   "metadata": {},
+   "source": [
+    "## Tool calling\n",
+    "\n",
+    "### ChatWatsonx.bind_tools()\n",
+    "\n",
+    "Please note that `ChatWatsonx.bind_tools` is on beta state, so right now we only support `mistralai/mixtral-8x7b-instruct-v01` model.\n",
+    "\n",
+    "You should also redefine `max_new_tokens` parameter to get the entire model response. By default `max_new_tokens` is set to 20."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "328fce76",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_ibm import ChatWatsonx\n",
+    "\n",
+    "parameters = {\"max_new_tokens\": 200}\n",
+    "\n",
+    "chat = ChatWatsonx(\n",
+    "    model_id=\"mistralai/mixtral-8x7b-instruct-v01\",\n",
+    "    url=\"https://us-south.ml.cloud.ibm.com\",\n",
+    "    project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
+    "    params=parameters,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "e1633a73",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class GetWeather(BaseModel):\n",
+    "    \"\"\"Get the current weather in a given location\"\"\"\n",
+    "\n",
+    "    location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
+    "\n",
+    "\n",
+    "llm_with_tools = chat.bind_tools([GetWeather])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3bf9b8ab",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'function_call': {'type': 'function'}, 'tool_calls': [{'type': 'function', 'function': {'name': 'GetWeather', 'arguments': '{\"location\": \"Los Angeles\"}'}, 'id': None}, {'type': 'function', 'function': {'name': 'GetWeather', 'arguments': '{\"location\": \"New York\"}'}, 'id': None}]}, response_metadata={'token_usage': {'generated_token_count': 99, 'input_token_count': 320}, 'model_name': 'mistralai/mixtral-8x7b-instruct-v01', 'system_fingerprint': '', 'finish_reason': 'eos_token'}, id='run-38627104-f2ac-4edb-8390-d5425fb65979-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'Los Angeles'}, 'id': None}, {'name': 'GetWeather', 'args': {'location': 'New York'}, 'id': None}])"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg = llm_with_tools.invoke(\n",
+    "    \"Which city is hotter today: LA or NY?\",\n",
+    ")\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ba03dbf4",
+   "metadata": {},
+   "source": [
+    "### AIMessage.tool_calls\n",
+    "Notice that the AIMessage has a `tool_calls` attribute. This contains in a standardized ToolCall format that is model-provider agnostic."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "38f10ba7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'GetWeather', 'args': {'location': 'Los Angeles'}, 'id': None},\n",
+       " {'name': 'GetWeather', 'args': {'location': 'New York'}, 'id': None}]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9ee72a59",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all IBM watsonx.ai features and configurations head to the API reference: https://api.python.langchain.com/en/latest/ibm_api_reference.html"
+   ]
+  }
+ ],
+ "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": "3.1.undefined"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/chat/llamacpp.ipynb

@@ -21,7 +21,7 @@
     "| [ChatLlamaCpp](https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.llamacpp.ChatLlamaCpp.html) | [langchain-community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ✅ | ❌ | ❌ |\n",
     "\n",
     "### Model features\n",
-    "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | Image input | 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",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | Image input | 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",
@@ -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/chat/ollama_functions.ipynb

@@ -15,85 +15,85 @@
    "source": [
     "# OllamaFunctions\n",
     "\n",
-    "This notebook shows how to use an experimental wrapper around Ollama that gives it the same API as OpenAI Functions.\n",
+    "This notebook shows how to use an experimental wrapper around Ollama that gives it [tool calling capabilities](https://python.langchain.com/v0.2/docs/concepts/#functiontool-calling).\n",
     "\n",
     "Note that more powerful and capable models will perform better with complex schema and/or multiple functions. The examples below use llama3 and phi3 models.\n",
     "For a complete list of supported models and model variants, see the [Ollama model library](https://ollama.ai/library).\n",
     "\n",
+    ":::warning\n",
+    "\n",
+    "This is an experimental wrapper that attempts to bolt-on tool calling support to models that do not natively support it. Use with caution.\n",
+    "\n",
+    ":::\n",
+    "## Overview\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "|                                                                Class                                                                | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
+    "|:-----------------------------------------------------------------------------------------------------------------------------------:|:-------:|:-----:|:------------:|:----------:|:-----------------:|:--------------:|\n",
+    "| [OllamaFunctions](https://api.python.langchain.com/en/latest/llms/langchain_experimental.llms.ollama_function.OllamaFunctions.html) | [langchain-experimental](https://api.python.langchain.com/en/latest/openai_api_reference.html) | ✅ | ❌ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-experimental?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-experimental?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "\n",
+    "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | Image input | 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",
-    "Follow [these instructions](https://github.com/jmorganca/ollama) to set up and run a local Ollama instance.\n",
+    "To access `OllamaFunctions` you will need to install `langchain-experimental` integration package.\n",
+    "Follow [these instructions](https://github.com/jmorganca/ollama) to set up and run a local Ollama instance as well as download and serve [supported models](https://ollama.com/library).\n",
     "\n",
-    "## Usage\n",
+    "### Credentials\n",
     "\n",
-    "You can initialize OllamaFunctions in a similar way to how you'd initialize a standard ChatOllama instance:"
+    "Credentials support is not present at this time.\n",
+    "\n",
+    "### Installation\n",
+    "\n",
+    "The `OllamaFunctions` class lives in the `langchain-experimental` package:\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-experimental"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "`OllamaFunctions` takes the same init parameters as `ChatOllama`. \n",
+    "\n",
+    "In order to use tool calling, you must also specify `format=\"json\"`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-04-28T00:53:25.276543Z",
-     "start_time": "2024-04-28T00:53:24.881202Z"
-    },
-    "scrolled": true
+     "end_time": "2024-06-23T15:20:21.818089Z",
+     "start_time": "2024-06-23T15:20:21.815759Z"
+    }
    },
    "outputs": [],
    "source": [
     "from langchain_experimental.llms.ollama_functions import OllamaFunctions\n",
     "\n",
-    "model = OllamaFunctions(model=\"llama3\", format=\"json\")"
+    "llm = OllamaFunctions(model=\"phi3\")"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You can then bind functions defined with JSON Schema parameters and a `function_call` parameter to force the model to call the given function:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-04-26T04:59:17.270931Z",
-     "start_time": "2024-04-26T04:59:17.263347Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "model = model.bind_tools(\n",
-    "    tools=[\n",
-    "        {\n",
-    "            \"name\": \"get_current_weather\",\n",
-    "            \"description\": \"Get the current weather in a given location\",\n",
-    "            \"parameters\": {\n",
-    "                \"type\": \"object\",\n",
-    "                \"properties\": {\n",
-    "                    \"location\": {\n",
-    "                        \"type\": \"string\",\n",
-    "                        \"description\": \"The city and state, \" \"e.g. San Francisco, CA\",\n",
-    "                    },\n",
-    "                    \"unit\": {\n",
-    "                        \"type\": \"string\",\n",
-    "                        \"enum\": [\"celsius\", \"fahrenheit\"],\n",
-    "                    },\n",
-    "                },\n",
-    "                \"required\": [\"location\"],\n",
-    "            },\n",
-    "        }\n",
-    "    ],\n",
-    "    function_call={\"name\": \"get_current_weather\"},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Calling a function with this model then results in JSON output matching the provided schema:"
+    "## Invocation"
    ]
   },
   {
@@ -101,15 +101,15 @@
    "execution_count": 3,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-04-26T04:59:26.092428Z",
-     "start_time": "2024-04-26T04:59:17.272627Z"
+     "end_time": "2024-06-23T15:20:46.794689Z",
+     "start_time": "2024-06-23T15:20:44.982632Z"
     }
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='', additional_kwargs={'function_call': {'name': 'get_current_weather', 'arguments': '{\"location\": \"Boston, MA\"}'}}, id='run-1791f9fe-95ad-4ca4-bdf7-9f73eab31e6f-0')"
+       "AIMessage(content=\"J'adore programmer.\", id='run-94815fcf-ae11-438a-ba3f-00819328b5cd-0')"
       ]
      },
      "execution_count": 3,
@@ -118,79 +118,55 @@
     }
    ],
    "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "model.invoke(\"what is the weather in Boston?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Structured Output\n",
-    "\n",
-    "One useful thing you can do with function calling using `with_structured_output()` function is extracting properties from a given input in a structured format:"
+    "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": 4,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-04-26T04:59:26.098828Z",
-     "start_time": "2024-04-26T04:59:26.094021Z"
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"J'adore programmer.\""
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
     }
-   },
-   "outputs": [],
+   ],
    "source": [
-    "from langchain_core.prompts import PromptTemplate\n",
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "\n",
-    "# Schema for structured response\n",
-    "class Person(BaseModel):\n",
-    "    name: str = Field(description=\"The person's name\", required=True)\n",
-    "    height: float = Field(description=\"The person's height\", required=True)\n",
-    "    hair_color: str = Field(description=\"The person's hair color\")\n",
-    "\n",
-    "\n",
-    "# Prompt template\n",
-    "prompt = PromptTemplate.from_template(\n",
-    "    \"\"\"Alex is 5 feet tall. \n",
-    "Claudia is 1 feet taller than Alex and jumps higher than him. \n",
-    "Claudia is a brunette and Alex is blonde.\n",
-    "\n",
-    "Human: {question}\n",
-    "AI: \"\"\"\n",
-    ")\n",
-    "\n",
-    "# Chain\n",
-    "llm = OllamaFunctions(model=\"phi3\", format=\"json\", temperature=0)\n",
-    "structured_llm = llm.with_structured_output(Person)\n",
-    "chain = prompt | structured_llm"
+    "ai_msg.content"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Extracting data about Alex"
+    "## Chaining\n",
+    "\n",
+    "We can [chain](https://python.langchain.com/v0.2/docs/how_to/sequence/) our model with a prompt template like so:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-04-26T04:59:30.164955Z",
-     "start_time": "2024-04-26T04:59:26.099790Z"
-    }
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Person(name='Alex', height=5.0, hair_color='blonde')"
+       "AIMessage(content='Programmieren ist sehr verrückt! Es freut mich, dass Sie auf Programmierung so positiv eingestellt sind.', id='run-ee99be5e-4d48-4ab6-b602-35415f0bdbde-0')"
       ]
      },
      "execution_count": 5,
@@ -199,41 +175,123 @@
     }
    ],
    "source": [
-    "alex = chain.invoke(\"Describe Alex\")\n",
-    "alex"
+    "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",
    "metadata": {},
    "source": [
-    "### Extracting data about Claudia"
+    "## Tool Calling\n",
+    "\n",
+    "### OllamaFunctions.bind_tools()\n",
+    "\n",
+    "With `OllamaFunctions.bind_tools`, we can easily pass in Pydantic classes, dict schemas, LangChain tools, or even functions as tools to the model. Under the hood these are converted to a tool definition schemas, which looks like:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-04-26T04:59:31.509846Z",
-     "start_time": "2024-04-26T04:59:30.165662Z"
-    }
-   },
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class GetWeather(BaseModel):\n",
+    "    \"\"\"Get the current weather in a given location\"\"\"\n",
+    "\n",
+    "    location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
+    "\n",
+    "\n",
+    "llm_with_tools = llm.bind_tools([GetWeather])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Person(name='Claudia', height=6.0, hair_color='brunette')"
+       "AIMessage(content='', id='run-b9769435-ec6a-4cb8-8545-5a5035fc19bd-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'San Francisco, CA'}, 'id': 'call_064c4e1cb27e4adb9e4e7ed60362ecc9'}])"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "claudia = chain.invoke(\"Describe Claudia\")\n",
-    "claudia"
+    "ai_msg = llm_with_tools.invoke(\n",
+    "    \"what is the weather like in San Francisco\",\n",
+    ")\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### AIMessage.tool_calls\n",
+    "\n",
+    "Notice that the AIMessage has a `tool_calls` attribute. This contains in a standardized `ToolCall` format that is model-provider agnostic."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'GetWeather',\n",
+       "  'args': {'location': 'San Francisco, CA'},\n",
+       "  'id': 'call_064c4e1cb27e4adb9e4e7ed60362ecc9'}]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": "For more on binding tools and tool call outputs, head to the [tool calling](docs/how_to/function_calling) docs."
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ToolCallingLLM features and configurations head to the API reference: https://api.python.langchain.com/en/latest/llms/langchain_experimental.llms.ollama_functions.OllamaFunctions.html\n"
    ]
   }
  ],
@@ -253,7 +311,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/openai.ipynb

@@ -41,7 +41,7 @@
     "| [ChatOpenAI](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html) | [langchain-openai](https://api.python.langchain.com/en/latest/openai_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-openai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-openai?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 | 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",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | Image input | 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",
@@ -426,7 +426,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/perplexity.ipynb

@@ -45,7 +45,7 @@
     "The code provided assumes that your PPLX_API_KEY is set in your environment variables. If you would like to manually specify your API key and also choose a different model, you can use the following code:\n",
     "\n",
     "```python\n",
-    "chat = ChatPerplexity(temperature=0, pplx_api_key=\"YOUR_API_KEY\", model=\"pplx-70b-online\")\n",
+    "chat = ChatPerplexity(temperature=0, pplx_api_key=\"YOUR_API_KEY\", model=\"llama-3-sonar-small-32k-online\")\n",
     "```\n",
     "\n",
     "You can check a list of available models [here](https://docs.perplexity.ai/docs/model-cards). For reproducibility, we can set the API key dynamically by taking it as an input in this notebook."
@@ -78,7 +78,7 @@
    },
    "outputs": [],
    "source": [
-    "chat = ChatPerplexity(temperature=0, model=\"pplx-70b-online\")"
+    "chat = ChatPerplexity(temperature=0, model=\"llama-3-sonar-small-32k-online\")"
    ]
   },
   {
@@ -146,7 +146,7 @@
     }
    ],
    "source": [
-    "chat = ChatPerplexity(temperature=0, model=\"pplx-70b-online\")\n",
+    "chat = ChatPerplexity(temperature=0, model=\"llama-3-sonar-small-32k-online\")\n",
     "prompt = ChatPromptTemplate.from_messages([(\"human\", \"Tell me a joke about {topic}\")])\n",
     "chain = prompt | chat\n",
     "response = chain.invoke({\"topic\": \"cats\"})\n",
@@ -195,7 +195,7 @@
     }
    ],
    "source": [
-    "chat = ChatPerplexity(temperature=0.7, model=\"pplx-70b-online\")\n",
+    "chat = ChatPerplexity(temperature=0.7, model=\"llama-3-sonar-small-32k-online\")\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [(\"human\", \"Give me a list of famous tourist attractions in Pakistan\")]\n",
     ")\n",

docs/docs/integrations/document_loaders/async_chromium.ipynb

@@ -13,7 +13,7 @@
     "\n",
     "Headless mode means that the browser is running without a graphical user interface.\n",
     "\n",
-    "`AsyncChromiumLoader` loads the page, and then we use `Html2TextTransformer` to transform to text."
+    "In the below example we'll use the `AsyncChromiumLoader` to loads the page, and then the [`Html2TextTransformer`](/docs/integrations/document_transformers/html2text/) to strip out the HTML tags and other semantic information."
    ]
   },
   {
@@ -23,48 +23,22 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  playwright beautifulsoup4\n",
+    "%pip install --upgrade --quiet playwright beautifulsoup4 html2text\n",
     "!playwright install"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "dd2cdea7",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'<!DOCTYPE html><html lang=\"en\"><head><script src=\"https://s0.2mdn.net/instream/video/client.js\" asyn'"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_community.document_loaders import AsyncChromiumLoader\n",
-    "\n",
-    "urls = [\"https://www.wsj.com\"]\n",
-    "loader = AsyncChromiumLoader(urls, user_agent=\"MyAppUserAgent\")\n",
-    "docs = loader.load()\n",
-    "docs[0].page_content[0:100]"
-   ]
-  },
   {
    "cell_type": "markdown",
-   "id": "c64e7df9",
+   "id": "00487c0f",
    "metadata": {},
    "source": [
-    "If you are using Jupyter notebooks, you might need to apply `nest_asyncio` before loading the documents."
+    "**Note:** If you are using Jupyter notebooks, you might also need to install and apply `nest_asyncio` before loading the documents like this:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5f2fe3c0",
+   "id": "d374eef4",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -74,6 +48,40 @@
     "nest_asyncio.apply()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "dd2cdea7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'<!DOCTYPE html><html lang=\"en\" dir=\"ltr\" class=\"docs-wrapper docs-doc-page docs-version-2.0 plugin-d'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_community.document_loaders import AsyncChromiumLoader\n",
+    "\n",
+    "urls = [\"https://docs.smith.langchain.com/\"]\n",
+    "loader = AsyncChromiumLoader(urls, user_agent=\"MyAppUserAgent\")\n",
+    "docs = loader.load()\n",
+    "docs[0].page_content[0:100]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7eb5e6aa",
+   "metadata": {},
+   "source": [
+    "Now let's transform the documents into a more readable syntax using the transformer:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 6,
@@ -83,7 +91,7 @@
     {
      "data": {
       "text/plain": [
-       "\"Skip to Main ContentSkip to SearchSkip to... Select * Top News * What's News *\\nFeatured Stories * Retirement * Life & Arts * Hip-Hop * Sports * Video *\\nEconomy * Real Estate * Sports * CMO * CIO * CFO * Risk & Compliance *\\nLogistics Report * Sustainable Business * Heard on the Street * Barron’s *\\nMarketWatch * Mansion Global * Penta * Opinion * Journal Reports * Sponsored\\nOffers Explore Our Brands * WSJ * * * * * Barron's * * * * * MarketWatch * * *\\n* * IBD # The Wall Street Journal SubscribeSig\""
+       "'Skip to main content\\n\\nGo to API Docs\\n\\nSearch`⌘``K`\\n\\nGo to App\\n\\n  * Quick start\\n  * Tutorials\\n\\n  * How-to guides\\n\\n  * Concepts\\n\\n  * Reference\\n\\n  * Pricing\\n  * Self-hosting\\n\\n  * LangGraph Cloud\\n\\n  *   * Quick start\\n\\nOn this page\\n\\n# Get started with LangSmith\\n\\n**LangSmith** is a platform for building production-grade LLM applications. It\\nallows you to closely monitor and evaluate your application, so you can ship\\nquickly and with confidence. Use of LangChain is not necessary - LangSmith\\nworks on it'"
       ]
      },
      "execution_count": 6,
@@ -116,7 +124,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/email.ipynb

@@ -7,7 +7,9 @@
    "source": [
     "# Email\n",
     "\n",
-    "This notebook shows how to load email (`.eml`) or `Microsoft Outlook` (`.msg`) files."
+    "This notebook shows how to load email (`.eml`) or `Microsoft Outlook` (`.msg`) files.\n",
+    "\n",
+    "Please see [this guide](/docs/integrations/providers/unstructured/) for more instructions on setting up Unstructured locally, including setting up required system dependencies."
    ]
   },
   {
@@ -27,49 +29,13 @@
    },
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  unstructured"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "40cd9806",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import UnstructuredEmailLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "2d20b852",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredEmailLoader(\"example_data/fake-email.eml\")"
+    "%pip install --upgrade --quiet unstructured"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "579fa702",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "90c1d899",
+   "id": "2d20b852",
    "metadata": {
     "tags": []
    },
@@ -77,15 +43,21 @@
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='This is a test email to use for unit tests.\\n\\nImportant points:\\n\\nRoses are red\\n\\nViolets are blue', metadata={'source': 'example_data/fake-email.eml'})]"
+       "[Document(page_content='This is a test email to use for unit tests.\\n\\nImportant points:\\n\\nRoses are red\\n\\nViolets are blue', metadata={'source': './example_data/fake-email.eml'})]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import UnstructuredEmailLoader\n",
+    "\n",
+    "loader = UnstructuredEmailLoader(\"./example_data/fake-email.eml\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data"
    ]
   },
@@ -101,42 +73,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "b9592eaf",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredEmailLoader(\"example_data/fake-email.eml\", mode=\"elements\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "0b16d03f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "d7bdc5e5",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'filename': 'fake-email.eml', 'file_directory': 'example_data', 'date': '2022-12-16T17:04:16-05:00', 'filetype': 'message/rfc822', 'sent_from': ['Matthew Robinson <mrobinson@unstructured.io>'], 'sent_to': ['Matthew Robinson <mrobinson@unstructured.io>'], 'subject': 'Test Email', 'category': 'NarrativeText'})"
+       "Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'file_directory': 'example_data', 'filename': 'fake-email.eml', 'last_modified': '2022-12-16T17:04:16-05:00', 'sent_from': ['Matthew Robinson <mrobinson@unstructured.io>'], 'sent_to': ['Matthew Robinson <mrobinson@unstructured.io>'], 'subject': 'Test Email', 'languages': ['eng'], 'filetype': 'message/rfc822', 'category': 'NarrativeText'})"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "loader = UnstructuredEmailLoader(\"example_data/fake-email.eml\", mode=\"elements\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   },
@@ -152,46 +108,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 5,
    "id": "6539f166",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredEmailLoader(\n",
-    "    \"example_data/fake-email.eml\",\n",
-    "    mode=\"elements\",\n",
-    "    process_attachments=True,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "aebead38",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "ddeb60f4",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'filename': 'fake-email.eml', 'file_directory': 'example_data', 'date': '2022-12-16T17:04:16-05:00', 'filetype': 'message/rfc822', 'sent_from': ['Matthew Robinson <mrobinson@unstructured.io>'], 'sent_to': ['Matthew Robinson <mrobinson@unstructured.io>'], 'subject': 'Test Email', 'category': 'NarrativeText'})"
+       "Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'file_directory': 'example_data', 'filename': 'fake-email.eml', 'last_modified': '2022-12-16T17:04:16-05:00', 'sent_from': ['Matthew Robinson <mrobinson@unstructured.io>'], 'sent_to': ['Matthew Robinson <mrobinson@unstructured.io>'], 'subject': 'Test Email', 'languages': ['eng'], 'filetype': 'message/rfc822', 'category': 'NarrativeText'})"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "loader = UnstructuredEmailLoader(\n",
+    "    \"example_data/fake-email.eml\",\n",
+    "    mode=\"elements\",\n",
+    "    process_attachments=True,\n",
+    ")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   },
@@ -210,57 +150,33 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  extract_msg"
+    "%pip install --upgrade --quiet extract_msg"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "1e7a8444",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import OutlookMessageLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "77a055e6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = OutlookMessageLoader(\"example_data/fake-email.msg\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "789882de",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "46aa0632",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='This is a test email to experiment with the MS Outlook MSG Extractor\\r\\n\\r\\n\\r\\n-- \\r\\n\\r\\n\\r\\nKind regards\\r\\n\\r\\n\\r\\n\\r\\n\\r\\nBrian Zhou\\r\\n\\r\\n', metadata={'subject': 'Test for TIF files', 'sender': 'Brian Zhou <brizhou@gmail.com>', 'date': 'Mon, 18 Nov 2013 16:26:24 +0800'})"
+       "Document(page_content='This is a test email to experiment with the MS Outlook MSG Extractor\\r\\n\\r\\n\\r\\n-- \\r\\n\\r\\n\\r\\nKind regards\\r\\n\\r\\n\\r\\n\\r\\n\\r\\nBrian Zhou\\r\\n\\r\\n', metadata={'source': 'example_data/fake-email.msg', 'subject': 'Test for TIF files', 'sender': 'Brian Zhou <brizhou@gmail.com>', 'date': datetime.datetime(2013, 11, 18, 0, 26, 24, tzinfo=zoneinfo.ZoneInfo(key='America/Los_Angeles'))})"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import OutlookMessageLoader\n",
+    "\n",
+    "loader = OutlookMessageLoader(\"example_data/fake-email.msg\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   },
@@ -289,7 +205,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/example_data/state_of_the_union.txt

@@ -0,0 +1,723 @@
+Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.  
+
+Last year COVID-19 kept us apart. This year we are finally together again. 
+
+Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. 
+
+With a duty to one another to the American people to the Constitution. 
+
+And with an unwavering resolve that freedom will always triumph over tyranny. 
+
+Six days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. 
+
+He thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. 
+
+He met the Ukrainian people. 
+
+From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. 
+
+Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. 
+
+In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight. 
+
+Let each of us here tonight in this Chamber send an unmistakable signal to Ukraine and to the world. 
+
+Please rise if you are able and show that, Yes, we the United States of America stand with the Ukrainian people. 
+
+Throughout our history we’ve learned this lesson when dictators do not pay a price for their aggression they cause more chaos.   
+
+They keep moving.   
+
+And the costs and the threats to America and the world keep rising.   
+
+That’s why the NATO Alliance was created to secure peace and stability in Europe after World War 2. 
+
+The United States is a member along with 29 other nations. 
+
+It matters. American diplomacy matters. American resolve matters. 
+
+Putin’s latest attack on Ukraine was premeditated and unprovoked. 
+
+He rejected repeated efforts at diplomacy. 
+
+He thought the West and NATO wouldn’t respond. And he thought he could divide us at home. Putin was wrong. We were ready.  Here is what we did.   
+
+We prepared extensively and carefully. 
+
+We spent months building a coalition of other freedom-loving nations from Europe and the Americas to Asia and Africa to confront Putin. 
+
+I spent countless hours unifying our European allies. We shared with the world in advance what we knew Putin was planning and precisely how he would try to falsely justify his aggression.  
+
+We countered Russia’s lies with truth.   
+
+And now that he has acted the free world is holding him accountable. 
+
+Along with twenty-seven members of the European Union including France, Germany, Italy, as well as countries like the United Kingdom, Canada, Japan, Korea, Australia, New Zealand, and many others, even Switzerland. 
+
+We are inflicting pain on Russia and supporting the people of Ukraine. Putin is now isolated from the world more than ever. 
+
+Together with our allies –we are right now enforcing powerful economic sanctions. 
+
+We are cutting off Russia’s largest banks from the international financial system.  
+
+Preventing Russia’s central bank from defending the Russian Ruble making Putin’s $630 Billion “war fund” worthless.   
+
+We are choking off Russia’s access to technology that will sap its economic strength and weaken its military for years to come.  
+
+Tonight I say to the Russian oligarchs and corrupt leaders who have bilked billions of dollars off this violent regime no more. 
+
+The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs.  
+
+We are joining with our European allies to find and seize your yachts your luxury apartments your private jets. We are coming for your ill-begotten gains. 
+
+And tonight I am announcing that we will join our allies in closing off American air space to all Russian flights – further isolating Russia – and adding an additional squeeze –on their economy. The Ruble has lost 30% of its value. 
+
+The Russian stock market has lost 40% of its value and trading remains suspended. Russia’s economy is reeling and Putin alone is to blame. 
+
+Together with our allies we are providing support to the Ukrainians in their fight for freedom. Military assistance. Economic assistance. Humanitarian assistance. 
+
+We are giving more than $1 Billion in direct assistance to Ukraine. 
+
+And we will continue to aid the Ukrainian people as they defend their country and to help ease their suffering.  
+
+Let me be clear, our forces are not engaged and will not engage in conflict with Russian forces in Ukraine.  
+
+Our forces are not going to Europe to fight in Ukraine, but to defend our NATO Allies – in the event that Putin decides to keep moving west.  
+
+For that purpose we’ve mobilized American ground forces, air squadrons, and ship deployments to protect NATO countries including Poland, Romania, Latvia, Lithuania, and Estonia. 
+
+As I have made crystal clear the United States and our Allies will defend every inch of territory of NATO countries with the full force of our collective power.  
+
+And we remain clear-eyed. The Ukrainians are fighting back with pure courage. But the next few days weeks, months, will be hard on them.  
+
+Putin has unleashed violence and chaos.  But while he may make gains on the battlefield – he will pay a continuing high price over the long run. 
+
+And a proud Ukrainian people, who have known 30 years  of independence, have repeatedly shown that they will not tolerate anyone who tries to take their country backwards.  
+
+To all Americans, I will be honest with you, as I’ve always promised. A Russian dictator, invading a foreign country, has costs around the world. 
+
+And I’m taking robust action to make sure the pain of our sanctions  is targeted at Russia’s economy. And I will use every tool at our disposal to protect American businesses and consumers. 
+
+Tonight, I can announce that the United States has worked with 30 other countries to release 60 Million barrels of oil from reserves around the world.  
+
+America will lead that effort, releasing 30 Million barrels from our own Strategic Petroleum Reserve. And we stand ready to do more if necessary, unified with our allies.  
+
+These steps will help blunt gas prices here at home. And I know the news about what’s happening can seem alarming. 
+
+But I want you to know that we are going to be okay. 
+
+When the history of this era is written Putin’s war on Ukraine will have left Russia weaker and the rest of the world stronger. 
+
+While it shouldn’t have taken something so terrible for people around the world to see what’s at stake now everyone sees it clearly. 
+
+We see the unity among leaders of nations and a more unified Europe a more unified West. And we see unity among the people who are gathering in cities in large crowds around the world even in Russia to demonstrate their support for Ukraine.  
+
+In the battle between democracy and autocracy, democracies are rising to the moment, and the world is clearly choosing the side of peace and security. 
+
+This is a real test. It’s going to take time. So let us continue to draw inspiration from the iron will of the Ukrainian people. 
+
+To our fellow Ukrainian Americans who forge a deep bond that connects our two nations we stand with you. 
+
+Putin may circle Kyiv with tanks, but he will never gain the hearts and souls of the Ukrainian people. 
+
+He will never extinguish their love of freedom. He will never weaken the resolve of the free world. 
+
+We meet tonight in an America that has lived through two of the hardest years this nation has ever faced. 
+
+The pandemic has been punishing. 
+
+And so many families are living paycheck to paycheck, struggling to keep up with the rising cost of food, gas, housing, and so much more. 
+
+I understand. 
+
+I remember when my Dad had to leave our home in Scranton, Pennsylvania to find work. I grew up in a family where if the price of food went up, you felt it. 
+
+That’s why one of the first things I did as President was fight to pass the American Rescue Plan.  
+
+Because people were hurting. We needed to act, and we did. 
+
+Few pieces of legislation have done more in a critical moment in our history to lift us out of crisis. 
+
+It fueled our efforts to vaccinate the nation and combat COVID-19. It delivered immediate economic relief for tens of millions of Americans.  
+
+Helped put food on their table, keep a roof over their heads, and cut the cost of health insurance. 
+
+And as my Dad used to say, it gave people a little breathing room. 
+
+And unlike the $2 Trillion tax cut passed in the previous administration that benefitted the top 1% of Americans, the American Rescue Plan helped working people—and left no one behind. 
+
+And it worked. It created jobs. Lots of jobs. 
+
+In fact—our economy created over 6.5 Million new jobs just last year, more jobs created in one year  
+than ever before in the history of America. 
+
+Our economy grew at a rate of 5.7% last year, the strongest growth in nearly 40 years, the first step in bringing fundamental change to an economy that hasn’t worked for the working people of this nation for too long.  
+
+For the past 40 years we were told that if we gave tax breaks to those at the very top, the benefits would trickle down to everyone else. 
+
+But that trickle-down theory led to weaker economic growth, lower wages, bigger deficits, and the widest gap between those at the top and everyone else in nearly a century. 
+
+Vice President Harris and I ran for office with a new economic vision for America. 
+
+Invest in America. Educate Americans. Grow the workforce. Build the economy from the bottom up  
+and the middle out, not from the top down.  
+
+Because we know that when the middle class grows, the poor have a ladder up and the wealthy do very well. 
+
+America used to have the best roads, bridges, and airports on Earth. 
+
+Now our infrastructure is ranked 13th in the world. 
+
+We won’t be able to compete for the jobs of the 21st Century if we don’t fix that. 
+
+That’s why it was so important to pass the Bipartisan Infrastructure Law—the most sweeping investment to rebuild America in history. 
+
+This was a bipartisan effort, and I want to thank the members of both parties who worked to make it happen. 
+
+We’re done talking about infrastructure weeks. 
+
+We’re going to have an infrastructure decade. 
+
+It is going to transform America and put us on a path to win the economic competition of the 21st Century that we face with the rest of the world—particularly with China.  
+
+As I’ve told Xi Jinping, it is never a good bet to bet against the American people. 
+
+We’ll create good jobs for millions of Americans, modernizing roads, airports, ports, and waterways all across America. 
+
+And we’ll do it all to withstand the devastating effects of the climate crisis and promote environmental justice. 
+
+We’ll build a national network of 500,000 electric vehicle charging stations, begin to replace poisonous lead pipes—so every child—and every American—has clean water to drink at home and at school, provide affordable high-speed internet for every American—urban, suburban, rural, and tribal communities. 
+
+4,000 projects have already been announced. 
+
+And tonight, I’m announcing that this year we will start fixing over 65,000 miles of highway and 1,500 bridges in disrepair. 
+
+When we use taxpayer dollars to rebuild America – we are going to Buy American: buy American products to support American jobs. 
+
+The federal government spends about $600 Billion a year to keep the country safe and secure. 
+
+There’s been a law on the books for almost a century 
+to make sure taxpayers’ dollars support American jobs and businesses. 
+
+Every Administration says they’ll do it, but we are actually doing it. 
+
+We will buy American to make sure everything from the deck of an aircraft carrier to the steel on highway guardrails are made in America. 
+
+But to compete for the best jobs of the future, we also need to level the playing field with China and other competitors. 
+
+That’s why it is so important to pass the Bipartisan Innovation Act sitting in Congress that will make record investments in emerging technologies and American manufacturing. 
+
+Let me give you one example of why it’s so important to pass it. 
+
+If you travel 20 miles east of Columbus, Ohio, you’ll find 1,000 empty acres of land. 
+
+It won’t look like much, but if you stop and look closely, you’ll see a “Field of dreams,” the ground on which America’s future will be built. 
+
+This is where Intel, the American company that helped build Silicon Valley, is going to build its $20 billion semiconductor “mega site”. 
+
+Up to eight state-of-the-art factories in one place. 10,000 new good-paying jobs. 
+
+Some of the most sophisticated manufacturing in the world to make computer chips the size of a fingertip that power the world and our everyday lives. 
+
+Smartphones. The Internet. Technology we have yet to invent. 
+
+But that’s just the beginning. 
+
+Intel’s CEO, Pat Gelsinger, who is here tonight, told me they are ready to increase their investment from  
+$20 billion to $100 billion. 
+
+That would be one of the biggest investments in manufacturing in American history. 
+
+And all they’re waiting for is for you to pass this bill. 
+
+So let’s not wait any longer. Send it to my desk. I’ll sign it.  
+
+And we will really take off. 
+
+And Intel is not alone. 
+
+There’s something happening in America. 
+
+Just look around and you’ll see an amazing story. 
+
+The rebirth of the pride that comes from stamping products “Made In America.” The revitalization of American manufacturing.   
+
+Companies are choosing to build new factories here, when just a few years ago, they would have built them overseas. 
+
+That’s what is happening. Ford is investing $11 billion to build electric vehicles, creating 11,000 jobs across the country. 
+
+GM is making the largest investment in its history—$7 billion to build electric vehicles, creating 4,000 jobs in Michigan. 
+
+All told, we created 369,000 new manufacturing jobs in America just last year. 
+
+Powered by people I’ve met like JoJo Burgess, from generations of union steelworkers from Pittsburgh, who’s here with us tonight. 
+
+As Ohio Senator Sherrod Brown says, “It’s time to bury the label “Rust Belt.” 
+
+It’s time. 
+
+But with all the bright spots in our economy, record job growth and higher wages, too many families are struggling to keep up with the bills.  
+
+Inflation is robbing them of the gains they might otherwise feel. 
+
+I get it. That’s why my top priority is getting prices under control. 
+
+Look, our economy roared back faster than most predicted, but the pandemic meant that businesses had a hard time hiring enough workers to keep up production in their factories. 
+
+The pandemic also disrupted global supply chains. 
+
+When factories close, it takes longer to make goods and get them from the warehouse to the store, and prices go up. 
+
+Look at cars. 
+
+Last year, there weren’t enough semiconductors to make all the cars that people wanted to buy. 
+
+And guess what, prices of automobiles went up. 
+
+So—we have a choice. 
+
+One way to fight inflation is to drive down wages and make Americans poorer.  
+
+I have a better plan to fight inflation. 
+
+Lower your costs, not your wages. 
+
+Make more cars and semiconductors in America. 
+
+More infrastructure and innovation in America. 
+
+More goods moving faster and cheaper in America. 
+
+More jobs where you can earn a good living in America. 
+
+And instead of relying on foreign supply chains, let’s make it in America. 
+
+Economists call it “increasing the productive capacity of our economy.” 
+
+I call it building a better America. 
+
+My plan to fight inflation will lower your costs and lower the deficit. 
+
+17 Nobel laureates in economics say my plan will ease long-term inflationary pressures. Top business leaders and most Americans support my plan. And here’s the plan: 
+
+First – cut the cost of prescription drugs. Just look at insulin. One in ten Americans has diabetes. In Virginia, I met a 13-year-old boy named Joshua Davis.  
+
+He and his Dad both have Type 1 diabetes, which means they need insulin every day. Insulin costs about $10 a vial to make.  
+
+But drug companies charge families like Joshua and his Dad up to 30 times more. I spoke with Joshua’s mom. 
+
+Imagine what it’s like to look at your child who needs insulin and have no idea how you’re going to pay for it.  
+
+What it does to your dignity, your ability to look your child in the eye, to be the parent you expect to be. 
+
+Joshua is here with us tonight. Yesterday was his birthday. Happy birthday, buddy.  
+
+For Joshua, and for the 200,000 other young people with Type 1 diabetes, let’s cap the cost of insulin at $35 a month so everyone can afford it.  
+
+Drug companies will still do very well. And while we’re at it let Medicare negotiate lower prices for prescription drugs, like the VA already does. 
+
+Look, the American Rescue Plan is helping millions of families on Affordable Care Act plans save $2,400 a year on their health care premiums. Let’s close the coverage gap and make those savings permanent. 
+
+Second – cut energy costs for families an average of $500 a year by combatting climate change.  
+
+Let’s provide investments and tax credits to weatherize your homes and businesses to be energy efficient and you get a tax credit; double America’s clean energy production in solar, wind, and so much more;  lower the price of electric vehicles, saving you another $80 a month because you’ll never have to pay at the gas pump again. 
+
+Third – cut the cost of child care. Many families pay up to $14,000 a year for child care per child.  
+
+Middle-class and working families shouldn’t have to pay more than 7% of their income for care of young children.  
+
+My plan will cut the cost in half for most families and help parents, including millions of women, who left the workforce during the pandemic because they couldn’t afford child care, to be able to get back to work. 
+
+My plan doesn’t stop there. It also includes home and long-term care. More affordable housing. And Pre-K for every 3- and 4-year-old.  
+
+All of these will lower costs. 
+
+And under my plan, nobody earning less than $400,000 a year will pay an additional penny in new taxes. Nobody.  
+
+The one thing all Americans agree on is that the tax system is not fair. We have to fix it.  
+
+I’m not looking to punish anyone. But let’s make sure corporations and the wealthiest Americans start paying their fair share. 
+
+Just last year, 55 Fortune 500 corporations earned $40 billion in profits and paid zero dollars in federal income tax.  
+
+That’s simply not fair. That’s why I’ve proposed a 15% minimum tax rate for corporations. 
+
+We got more than 130 countries to agree on a global minimum tax rate so companies can’t get out of paying their taxes at home by shipping jobs and factories overseas. 
+
+That’s why I’ve proposed closing loopholes so the very wealthy don’t pay a lower tax rate than a teacher or a firefighter.  
+
+So that’s my plan. It will grow the economy and lower costs for families. 
+
+So what are we waiting for? Let’s get this done. And while you’re at it, confirm my nominees to the Federal Reserve, which plays a critical role in fighting inflation.  
+
+My plan will not only lower costs to give families a fair shot, it will lower the deficit. 
+
+The previous Administration not only ballooned the deficit with tax cuts for the very wealthy and corporations, it undermined the watchdogs whose job was to keep pandemic relief funds from being wasted. 
+
+But in my administration, the watchdogs have been welcomed back. 
+
+We’re going after the criminals who stole billions in relief money meant for small businesses and millions of Americans.  
+
+And tonight, I’m announcing that the Justice Department will name a chief prosecutor for pandemic fraud. 
+
+By the end of this year, the deficit will be down to less than half what it was before I took office.  
+
+The only president ever to cut the deficit by more than one trillion dollars in a single year. 
+
+Lowering your costs also means demanding more competition. 
+
+I’m a capitalist, but capitalism without competition isn’t capitalism. 
+
+It’s exploitation—and it drives up prices. 
+
+When corporations don’t have to compete, their profits go up, your prices go up, and small businesses and family farmers and ranchers go under. 
+
+We see it happening with ocean carriers moving goods in and out of America. 
+
+During the pandemic, these foreign-owned companies raised prices by as much as 1,000% and made record profits. 
+
+Tonight, I’m announcing a crackdown on these companies overcharging American businesses and consumers. 
+
+And as Wall Street firms take over more nursing homes, quality in those homes has gone down and costs have gone up.  
+
+That ends on my watch. 
+
+Medicare is going to set higher standards for nursing homes and make sure your loved ones get the care they deserve and expect. 
+
+We’ll also cut costs and keep the economy going strong by giving workers a fair shot, provide more training and apprenticeships, hire them based on their skills not degrees. 
+
+Let’s pass the Paycheck Fairness Act and paid leave.  
+
+Raise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty. 
+
+Let’s increase Pell Grants and increase our historic support of HBCUs, and invest in what Jill—our First Lady who teaches full-time—calls America’s best-kept secret: community colleges. 
+
+And let’s pass the PRO Act when a majority of workers want to form a union—they shouldn’t be stopped.  
+
+When we invest in our workers, when we build the economy from the bottom up and the middle out together, we can do something we haven’t done in a long time: build a better America. 
+
+For more than two years, COVID-19 has impacted every decision in our lives and the life of the nation. 
+
+And I know you’re tired, frustrated, and exhausted. 
+
+But I also know this. 
+
+Because of the progress we’ve made, because of your resilience and the tools we have, tonight I can say  
+we are moving forward safely, back to more normal routines.  
+
+We’ve reached a new moment in the fight against COVID-19, with severe cases down to a level not seen since last July.  
+
+Just a few days ago, the Centers for Disease Control and Prevention—the CDC—issued new mask guidelines. 
+
+Under these new guidelines, most Americans in most of the country can now be mask free.   
+
+And based on the projections, more of the country will reach that point across the next couple of weeks. 
+
+Thanks to the progress we have made this past year, COVID-19 need no longer control our lives.  
+
+I know some are talking about “living with COVID-19”. Tonight – I say that we will never just accept living with COVID-19. 
+
+We will continue to combat the virus as we do other diseases. And because this is a virus that mutates and spreads, we will stay on guard. 
+
+Here are four common sense steps as we move forward safely.  
+
+First, stay protected with vaccines and treatments. We know how incredibly effective vaccines are. If you’re vaccinated and boosted you have the highest degree of protection. 
+
+We will never give up on vaccinating more Americans. Now, I know parents with kids under 5 are eager to see a vaccine authorized for their children. 
+
+The scientists are working hard to get that done and we’ll be ready with plenty of vaccines when they do. 
+
+We’re also ready with anti-viral treatments. If you get COVID-19, the Pfizer pill reduces your chances of ending up in the hospital by 90%.  
+
+We’ve ordered more of these pills than anyone in the world. And Pfizer is working overtime to get us 1 Million pills this month and more than double that next month.  
+
+And we’re launching the “Test to Treat” initiative so people can get tested at a pharmacy, and if they’re positive, receive antiviral pills on the spot at no cost.  
+
+If you’re immunocompromised or have some other vulnerability, we have treatments and free high-quality masks. 
+
+We’re leaving no one behind or ignoring anyone’s needs as we move forward. 
+
+And on testing, we have made hundreds of millions of tests available for you to order for free.   
+
+Even if you already ordered free tests tonight, I am announcing that you can order more from covidtests.gov starting next week. 
+
+Second – we must prepare for new variants. Over the past year, we’ve gotten much better at detecting new variants. 
+
+If necessary, we’ll be able to deploy new vaccines within 100 days instead of many more months or years.  
+
+And, if Congress provides the funds we need, we’ll have new stockpiles of tests, masks, and pills ready if needed. 
+
+I cannot promise a new variant won’t come. But I can promise you we’ll do everything within our power to be ready if it does.  
+
+Third – we can end the shutdown of schools and businesses. We have the tools we need. 
+
+It’s time for Americans to get back to work and fill our great downtowns again.  People working from home can feel safe to begin to return to the office.   
+
+We’re doing that here in the federal government. The vast majority of federal workers will once again work in person. 
+
+Our schools are open. Let’s keep it that way. Our kids need to be in school. 
+
+And with 75% of adult Americans fully vaccinated and hospitalizations down by 77%, most Americans can remove their masks, return to work, stay in the classroom, and move forward safely. 
+
+We achieved this because we provided free vaccines, treatments, tests, and masks. 
+
+Of course, continuing this costs money. 
+
+I will soon send Congress a request. 
+
+The vast majority of Americans have used these tools and may want to again, so I expect Congress to pass it quickly.   
+
+Fourth, we will continue vaccinating the world.     
+
+We’ve sent 475 Million vaccine doses to 112 countries, more than any other nation. 
+
+And we won’t stop. 
+
+We have lost so much to COVID-19. Time with one another. And worst of all, so much loss of life. 
+
+Let’s use this moment to reset. Let’s stop looking at COVID-19 as a partisan dividing line and see it for what it is: A God-awful disease.  
+
+Let’s stop seeing each other as enemies, and start seeing each other for who we really are: Fellow Americans.  
+
+We can’t change how divided we’ve been. But we can change how we move forward—on COVID-19 and other issues we must face together. 
+
+I recently visited the New York City Police Department days after the funerals of Officer Wilbert Mora and his partner, Officer Jason Rivera. 
+
+They were responding to a 9-1-1 call when a man shot and killed them with a stolen gun. 
+
+Officer Mora was 27 years old. 
+
+Officer Rivera was 22. 
+
+Both Dominican Americans who’d grown up on the same streets they later chose to patrol as police officers. 
+
+I spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves. 
+
+I’ve worked on these issues a long time. 
+
+I know what works: Investing in crime prevention and community police officers who’ll walk the beat, who’ll know the neighborhood, and who can restore trust and safety. 
+
+So let’s not abandon our streets. Or choose between safety and equal justice. 
+
+Let’s come together to protect our communities, restore trust, and hold law enforcement accountable. 
+
+That’s why the Justice Department required body cameras, banned chokeholds, and restricted no-knock warrants for its officers. 
+
+That’s why the American Rescue Plan provided $350 Billion that cities, states, and counties can use to hire more police and invest in proven strategies like community violence interruption—trusted messengers breaking the cycle of violence and trauma and giving young people hope.  
+
+We should all agree: The answer is not to Defund the police. The answer is to FUND the police with the resources and training they need to protect our communities. 
+
+I ask Democrats and Republicans alike: Pass my budget and keep our neighborhoods safe.  
+
+And I will keep doing everything in my power to crack down on gun trafficking and ghost guns you can buy online and make at home—they have no serial numbers and can’t be traced. 
+
+And I ask Congress to pass proven measures to reduce gun violence. Pass universal background checks. Why should anyone on a terrorist list be able to purchase a weapon? 
+
+Ban assault weapons and high-capacity magazines. 
+
+Repeal the liability shield that makes gun manufacturers the only industry in America that can’t be sued. 
+
+These laws don’t infringe on the Second Amendment. They save lives. 
+
+The most fundamental right in America is the right to vote – and to have it counted. And it’s under assault. 
+
+In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. 
+
+We cannot let this happen. 
+
+Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. 
+
+Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. 
+
+One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. 
+
+And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. 
+
+A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. 
+
+And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. 
+
+We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  
+
+We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  
+
+We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. 
+
+We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders. 
+
+We can do all this while keeping lit the torch of liberty that has led generations of immigrants to this land—my forefathers and so many of yours. 
+
+Provide a pathway to citizenship for Dreamers, those on temporary status, farm workers, and essential workers. 
+
+Revise our laws so businesses have the workers they need and families don’t wait decades to reunite. 
+
+It’s not only the right thing to do—it’s the economically smart thing to do. 
+
+That’s why immigration reform is supported by everyone from labor unions to religious leaders to the U.S. Chamber of Commerce. 
+
+Let’s get it done once and for all. 
+
+Advancing liberty and justice also requires protecting the rights of women. 
+
+The constitutional right affirmed in Roe v. Wade—standing precedent for half a century—is under attack as never before. 
+
+If we want to go forward—not backward—we must protect access to health care. Preserve a woman’s right to choose. And let’s continue to advance maternal health care in America. 
+
+And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. 
+
+As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. 
+
+While it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. 
+
+And soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. 
+
+So tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together.  
+
+First, beat the opioid epidemic. 
+
+There is so much we can do. Increase funding for prevention, treatment, harm reduction, and recovery.  
+
+Get rid of outdated rules that stop doctors from prescribing treatments. And stop the flow of illicit drugs by working with state and local law enforcement to go after traffickers. 
+
+If you’re suffering from addiction, know you are not alone. I believe in recovery, and I celebrate the 23 million Americans in recovery. 
+
+Second, let’s take on mental health. Especially among our children, whose lives and education have been turned upside down.  
+
+The American Rescue Plan gave schools money to hire teachers and help students make up for lost learning.  
+
+I urge every parent to make sure your school does just that. And we can all play a part—sign up to be a tutor or a mentor. 
+
+Children were also struggling before the pandemic. Bullying, violence, trauma, and the harms of social media. 
+
+As Frances Haugen, who is here with us tonight, has shown, we must hold social media platforms accountable for the national experiment they’re conducting on our children for profit. 
+
+It’s time to strengthen privacy protections, ban targeted advertising to children, demand tech companies stop collecting personal data on our children. 
+
+And let’s get all Americans the mental health services they need. More people they can turn to for help, and full parity between physical and mental health care. 
+
+Third, support our veterans. 
+
+Veterans are the best of us. 
+
+I’ve always believed that we have a sacred obligation to equip all those we send to war and care for them and their families when they come home. 
+
+My administration is providing assistance with job training and housing, and now helping lower-income veterans get VA care debt-free.  
+
+Our troops in Iraq and Afghanistan faced many dangers. 
+
+One was stationed at bases and breathing in toxic smoke from “burn pits” that incinerated wastes of war—medical and hazard material, jet fuel, and more. 
+
+When they came home, many of the world’s fittest and best trained warriors were never the same. 
+
+Headaches. Numbness. Dizziness. 
+
+A cancer that would put them in a flag-draped coffin. 
+
+I know. 
+
+One of those soldiers was my son Major Beau Biden. 
+
+We don’t know for sure if a burn pit was the cause of his brain cancer, or the diseases of so many of our troops. 
+
+But I’m committed to finding out everything we can. 
+
+Committed to military families like Danielle Robinson from Ohio. 
+
+The widow of Sergeant First Class Heath Robinson.  
+
+He was born a soldier. Army National Guard. Combat medic in Kosovo and Iraq. 
+
+Stationed near Baghdad, just yards from burn pits the size of football fields. 
+
+Heath’s widow Danielle is here with us tonight. They loved going to Ohio State football games. He loved building Legos with their daughter. 
+
+But cancer from prolonged exposure to burn pits ravaged Heath’s lungs and body. 
+
+Danielle says Heath was a fighter to the very end. 
+
+He didn’t know how to stop fighting, and neither did she. 
+
+Through her pain she found purpose to demand we do better. 
+
+Tonight, Danielle—we are. 
+
+The VA is pioneering new ways of linking toxic exposures to diseases, already helping more veterans get benefits. 
+
+And tonight, I’m announcing we’re expanding eligibility to veterans suffering from nine respiratory cancers. 
+
+I’m also calling on Congress: pass a law to make sure veterans devastated by toxic exposures in Iraq and Afghanistan finally get the benefits and comprehensive health care they deserve. 
+
+And fourth, let’s end cancer as we know it. 
+
+This is personal to me and Jill, to Kamala, and to so many of you. 
+
+Cancer is the #2 cause of death in America–second only to heart disease. 
+
+Last month, I announced our plan to supercharge  
+the Cancer Moonshot that President Obama asked me to lead six years ago. 
+
+Our goal is to cut the cancer death rate by at least 50% over the next 25 years, turn more cancers from death sentences into treatable diseases.  
+
+More support for patients and families. 
+
+To get there, I call on Congress to fund ARPA-H, the Advanced Research Projects Agency for Health. 
+
+It’s based on DARPA—the Defense Department project that led to the Internet, GPS, and so much more.  
+
+ARPA-H will have a singular purpose—to drive breakthroughs in cancer, Alzheimer’s, diabetes, and more. 
+
+A unity agenda for the nation. 
+
+We can do this. 
+
+My fellow Americans—tonight , we have gathered in a sacred space—the citadel of our democracy. 
+
+In this Capitol, generation after generation, Americans have debated great questions amid great strife, and have done great things. 
+
+We have fought for freedom, expanded liberty, defeated totalitarianism and terror. 
+
+And built the strongest, freest, and most prosperous nation the world has ever known. 
+
+Now is the hour. 
+
+Our moment of responsibility. 
+
+Our test of resolve and conscience, of history itself. 
+
+It is in this moment that our character is formed. Our purpose is found. Our future is forged. 
+
+Well I know this nation.  
+
+We will meet the test. 
+
+To protect freedom and liberty, to expand fairness and opportunity. 
+
+We will save democracy. 
+
+As hard as these times have been, I am more optimistic about America today than I have been my whole life. 
+
+Because I see the future that is within our grasp. 
+
+Because I know there is simply nothing beyond our capacity. 
+
+We are the only nation on Earth that has always turned every crisis we have faced into an opportunity. 
+
+The only nation that can be defined by a single word: possibilities. 
+
+So on this night, in our 245th year as a nation, I have come to report on the State of the Union. 
+
+And my report is this: the State of the Union is strong—because you, the American people, are strong. 
+
+We are stronger today than we were a year ago. 
+
+And we will be stronger a year from now than we are today. 
+
+Now is our moment to meet and overcome the challenges of our time. 
+
+And we will, as one people. 
+
+One America. 
+
+The United States of America. 
+
+May God bless you all. May God protect our troops.

docs/docs/integrations/document_loaders/image.ipynb

@@ -7,7 +7,9 @@
    "source": [
     "# Images\n",
     "\n",
-    "This covers how to load images such as `JPG` or `PNG` into a document format that we can use downstream."
+    "This covers how to load images into a document format that we can use downstream with other LangChain modules.\n",
+    "\n",
+    "It uses [Unstructured](https://unstructured.io/) to handle a wide variety of image formats, such as `.jpg` and `.png`. Please see [this guide](/docs/integrations/providers/unstructured/) for more instructions on setting up Unstructured locally, including setting up required system dependencies."
    ]
   },
   {
@@ -27,63 +29,35 @@
    },
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  pdfminer"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "0cc0cd42",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders.image import UnstructuredImageLoader"
+    "%pip install --upgrade --quiet \"unstructured[all-docs]\""
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "082d557c",
+   "id": "0cc0cd42",
    "metadata": {
     "tags": []
    },
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredImageLoader(\"layout-parser-paper-fast.jpg\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "df11c953",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "4284d44c",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content=\"LayoutParser: A Unified Toolkit for Deep\\nLearning Based Document Image Analysis\\n\\n\\n‘Zxjiang Shen' (F3}, Ruochen Zhang”, Melissa Dell*, Benjamin Charles Germain\\nLeet, Jacob Carlson, and Weining LiF\\n\\n\\nsugehen\\n\\nshangthrows, et\\n\\n“Abstract. Recent advanocs in document image analysis (DIA) have been\\n‘pimarliy driven bythe application of neural networks dell roar\\n{uteomer could be aly deployed in production and extended fo farther\\n[nvetigtion. However, various factory ke lcely organize codebanee\\nsnd sophisticated modal cnigurations compat the ey ree of\\n‘erin! innovation by wide sence, Though there have been sng\\n‘Hors to improve reuablty and simplify deep lees (DL) mode\\n‘aon, sone of them ae optimized for challenge inthe demain of DIA,\\nThis roprscte a major gap in the extng fol, sw DIA i eal to\\nscademic research acon wie range of dpi in the social ssencee\\n[rary for streamlining the sage of DL in DIA research and appicn\\n‘tons The core LayoutFaraer brary comes with a sch of simple and\\nIntative interfaee or applying and eutomiing DI. odel fr Inyo de\\npltfom for sharing both protrined modes an fal document dist\\n{ation pipeline We demonutate that LayootPareer shea fr both\\nlightweight and lrgeseledgtieation pipelines in eal-word uae ces\\nThe leary pblely smal at Btspe://layost-pareergsthab So\\n\\n\\n\\n‘Keywords: Document Image Analysis» Deep Learning Layout Analysis\\n‘Character Renguition - Open Serres dary « Tol\\n\\n\\nIntroduction\\n\\n\\n‘Deep Learning(DL)-based approaches are the state-of-the-art for a wide range of\\ndoctiment image analysis (DIA) tea including document image clasiffeation [I]\\n\", lookup_str='', metadata={'source': 'layout-parser-paper-fast.jpg'}, lookup_index=0)"
+       "Document(page_content='2021\\n\\n2103.15348v2 [cs.CV] 21 Jun\\n\\narXiv\\n\\nLayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis\\n\\nZejiang Shen! (&4), Ruochen Zhang?, Melissa Dell?, Benjamin Charles Germain Lee*, Jacob Carlson?, and Weining Li?\\n\\n1\\n\\nAllen Institute for AI shannons@allenai.org ? Brown University ruochen_zhang@brown. edu 3 Harvard University {melissadell, jacob_carlson}@fas.harvard.edu 4 University of Washington begl@cs.washington.edu 5 University of Waterloo w4221i@uwaterloo.ca\\n\\nAbstract. Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy reuse of im- portant innovations by a wide audience. Though there have been on-going efforts to improve reusability and simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applica- tions. The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout de- tection, character recognition, and many other document processing tasks. To promote extensibility, LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digiti- zation pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at https: //layout-parser.github. io.\\n\\nKeywords: Document Image Analysis - Deep Learning - Layout Analysis - Character Recognition - Open Source library - Toolkit.\\n\\n1 Introduction\\n\\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of document image analysis (DIA) tasks including document image classification [11,', metadata={'source': './example_data/layout-parser-paper-screenshot.png'})"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_loaders.image import UnstructuredImageLoader\n",
+    "\n",
+    "loader = UnstructuredImageLoader(\"./example_data/layout-parser-paper-screenshot.png\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   },
@@ -94,47 +68,33 @@
    "source": [
     "### Retain Elements\n",
     "\n",
-    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
+    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can keep that separation by specifying `mode=\"elements\"`."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "id": "0fab833b",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredImageLoader(\"layout-parser-paper-fast.jpg\", mode=\"elements\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "c3e8ff1b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "43c23d2d",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='LayoutParser: A Unified Toolkit for Deep\\nLearning Based Document Image Analysis\\n', lookup_str='', metadata={'source': 'layout-parser-paper-fast.jpg', 'filename': 'layout-parser-paper-fast.jpg', 'page_number': 1, 'category': 'Title'}, lookup_index=0)"
+       "Document(page_content='2021', metadata={'source': './example_data/layout-parser-paper-screenshot.png', 'coordinates': {'points': ((47.0, 492.0), (47.0, 591.0), (83.0, 591.0), (83.0, 492.0)), 'system': 'PixelSpace', 'layout_width': 1624, 'layout_height': 1920}, 'last_modified': '2024-07-01T10:38:29', 'filetype': 'PNG', 'languages': ['eng'], 'page_number': 1, 'file_directory': './example_data', 'filename': 'layout-parser-paper-screenshot.png', 'category': 'UncategorizedText'})"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "loader = UnstructuredImageLoader(\n",
+    "    \"./example_data/layout-parser-paper-screenshot.png\", mode=\"elements\"\n",
+    ")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   }
@@ -155,7 +115,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/microsoft_excel.ipynb

@@ -7,17 +7,19 @@
    "source": [
     "# Microsoft Excel\n",
     "\n",
-    "The `UnstructuredExcelLoader` is used to load `Microsoft Excel` files. The loader works with both `.xlsx` and `.xls` files. The page content will be the raw text of the Excel file. If you use the loader in `\"elements\"` mode, an HTML representation of the Excel file will be available in the document metadata under the `text_as_html` key."
+    "The `UnstructuredExcelLoader` is used to load `Microsoft Excel` files. The loader works with both `.xlsx` and `.xls` files. The page content will be the raw text of the Excel file. If you use the loader in `\"elements\"` mode, an HTML representation of the Excel file will be available in the document metadata under the `text_as_html` key.\n",
+    "\n",
+    "Please see [this guide](/docs/integrations/providers/unstructured/) for more instructions on setting up Unstructured locally, including setting up required system dependencies."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "e6616e3a",
+   "execution_count": null,
+   "id": "0b01ee46",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.document_loaders import UnstructuredExcelLoader"
+    "%pip install --upgrade --quiet langchain-community unstructured openpyxl"
    ]
   },
   {
@@ -26,10 +28,20 @@
    "id": "a654e4d9",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "Document(page_content='\\n  \\n    \\n      Team\\n      Location\\n      Stanley Cups\\n    \\n    \\n      Blues\\n      STL\\n      1\\n    \\n    \\n      Flyers\\n      PHI\\n      2\\n    \\n    \\n      Maple Leafs\\n      TOR\\n      13\\n    \\n  \\n', metadata={'source': 'example_data/stanley-cups.xlsx', 'filename': 'stanley-cups.xlsx', 'file_directory': 'example_data', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'page_number': 1, 'page_name': 'Stanley Cups', 'text_as_html': '<table border=\"1\" class=\"dataframe\">\\n  <tbody>\\n    <tr>\\n      <td>Team</td>\\n      <td>Location</td>\\n      <td>Stanley Cups</td>\\n    </tr>\\n    <tr>\\n      <td>Blues</td>\\n      <td>STL</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <td>Flyers</td>\\n      <td>PHI</td>\\n      <td>2</td>\\n    </tr>\\n    <tr>\\n      <td>Maple Leafs</td>\\n      <td>TOR</td>\\n      <td>13</td>\\n    </tr>\\n  </tbody>\\n</table>', 'category': 'Table'})"
+       "[Document(page_content='Stanley Cups', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups', 'page_number': 1, 'languages': ['eng'], 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Title'}),\n",
+       " Document(page_content='\\n\\n\\nTeam\\nLocation\\nStanley Cups\\n\\n\\nBlues\\nSTL\\n1\\n\\n\\nFlyers\\nPHI\\n2\\n\\n\\nMaple Leafs\\nTOR\\n13\\n\\n\\n', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups', 'page_number': 1, 'text_as_html': '<table border=\"1\" class=\"dataframe\">\\n  <tbody>\\n    <tr>\\n      <td>Team</td>\\n      <td>Location</td>\\n      <td>Stanley Cups</td>\\n    </tr>\\n    <tr>\\n      <td>Blues</td>\\n      <td>STL</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <td>Flyers</td>\\n      <td>PHI</td>\\n      <td>2</td>\\n    </tr>\\n    <tr>\\n      <td>Maple Leafs</td>\\n      <td>TOR</td>\\n      <td>13</td>\\n    </tr>\\n  </tbody>\\n</table>', 'languages': ['eng'], 'parent_id': '17e9a90f9616f2abed8cf32b5bd3810d', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Table'}),\n",
+       " Document(page_content='Stanley Cups Since 67', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups Since 67', 'page_number': 2, 'languages': ['eng'], 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Title'}),\n",
+       " Document(page_content='\\n\\n\\nTeam\\nLocation\\nStanley Cups\\n\\n\\nBlues\\nSTL\\n1\\n\\n\\nFlyers\\nPHI\\n2\\n\\n\\nMaple Leafs\\nTOR\\n0\\n\\n\\n', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups Since 67', 'page_number': 2, 'text_as_html': '<table border=\"1\" class=\"dataframe\">\\n  <tbody>\\n    <tr>\\n      <td>Team</td>\\n      <td>Location</td>\\n      <td>Stanley Cups</td>\\n    </tr>\\n    <tr>\\n      <td>Blues</td>\\n      <td>STL</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <td>Flyers</td>\\n      <td>PHI</td>\\n      <td>2</td>\\n    </tr>\\n    <tr>\\n      <td>Maple Leafs</td>\\n      <td>TOR</td>\\n      <td>0</td>\\n    </tr>\\n  </tbody>\\n</table>', 'languages': ['eng'], 'parent_id': 'ee34bd8c186b57e3530d5443ffa58122', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Table'})]"
       ]
      },
      "execution_count": 2,
@@ -38,9 +50,14 @@
     }
    ],
    "source": [
-    "loader = UnstructuredExcelLoader(\"example_data/stanley-cups.xlsx\", mode=\"elements\")\n",
+    "from langchain_community.document_loaders import UnstructuredExcelLoader\n",
+    "\n",
+    "loader = UnstructuredExcelLoader(\"./example_data/stanley-cups.xlsx\", mode=\"elements\")\n",
     "docs = loader.load()\n",
-    "docs[0]"
+    "\n",
+    "print(len(docs))\n",
+    "\n",
+    "docs"
    ]
   },
   {
@@ -76,7 +93,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  langchain langchain-community azure-ai-documentintelligence"
+    "%pip install --upgrade --quiet langchain langchain-community azure-ai-documentintelligence"
    ]
   },
   {
@@ -115,7 +132,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/microsoft_powerpoint.ipynb

@@ -9,7 +9,9 @@
     "\n",
     ">[Microsoft PowerPoint](https://en.wikipedia.org/wiki/Microsoft_PowerPoint) is a presentation program by Microsoft.\n",
     "\n",
-    "This covers how to load `Microsoft PowerPoint` documents into a document format that we can use downstream."
+    "This covers how to load `Microsoft PowerPoint` documents into a document format that we can use downstream.\n",
+    "\n",
+    "Please see [this guide](/docs/integrations/providers/unstructured/) for more instructions on setting up Unstructured locally, including setting up required system dependencies."
    ]
   },
   {
@@ -25,46 +27,10 @@
     "%pip install python-pptx"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "721c48aa",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import UnstructuredPowerPointLoader"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "9d3d0e35",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredPowerPointLoader(\"example_data/fake-power-point.pptx\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "06073f91",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "c9adc5cb",
+   "id": "721c48aa",
    "metadata": {
     "tags": []
    },
@@ -72,15 +38,21 @@
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='Adding a Bullet Slide\\n\\nFind the bullet slide layout\\n\\nUse _TextFrame.text for first bullet\\n\\nUse _TextFrame.add_paragraph() for subsequent bullets\\n\\nHere is a lot of text!\\n\\nHere is some text in a text box!', metadata={'source': 'example_data/fake-power-point.pptx'})]"
+       "[Document(page_content='Adding a Bullet Slide\\n\\nFind the bullet slide layout\\n\\nUse _TextFrame.text for first bullet\\n\\nUse _TextFrame.add_paragraph() for subsequent bullets\\n\\nHere is a lot of text!\\n\\nHere is some text in a text box!', metadata={'source': './example_data/fake-power-point.pptx'})]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import UnstructuredPowerPointLoader\n",
+    "\n",
+    "loader = UnstructuredPowerPointLoader(\"./example_data/fake-power-point.pptx\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data"
    ]
   },
@@ -94,38 +66,16 @@
     "Under the hood, `Unstructured` creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "064f9162",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredPowerPointLoader(\n",
-    "    \"example_data/fake-power-point.pptx\", mode=\"elements\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "abefbbdb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "a547c534",
+   "id": "064f9162",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='Adding a Bullet Slide', lookup_str='', metadata={'source': 'example_data/fake-power-point.pptx'}, lookup_index=0)"
+       "Document(page_content='Adding a Bullet Slide', metadata={'source': './example_data/fake-power-point.pptx', 'category_depth': 0, 'file_directory': './example_data', 'filename': 'fake-power-point.pptx', 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'languages': ['eng'], 'filetype': 'application/vnd.openxmlformats-officedocument.presentationml.presentation', 'category': 'Title'})"
       ]
      },
      "execution_count": 4,
@@ -134,6 +84,12 @@
     }
    ],
    "source": [
+    "loader = UnstructuredPowerPointLoader(\n",
+    "    \"./example_data/fake-power-point.pptx\", mode=\"elements\"\n",
+    ")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   },
@@ -209,7 +165,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/microsoft_word.ipynb

@@ -24,7 +24,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "7b80ea891",
    "metadata": {},
    "outputs": [],
@@ -34,52 +34,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "7b80ea89",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import Docx2txtLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "99a12031",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = Docx2txtLoader(\"example_data/fake.docx\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "b92f68b0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "d83dd755",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='Lorem ipsum dolor sit amet.', metadata={'source': 'example_data/fake.docx'})]"
+       "[Document(page_content='Lorem ipsum dolor sit amet.', metadata={'source': './example_data/fake.docx'})]"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import Docx2txtLoader\n",
+    "\n",
+    "loader = Docx2txtLoader(\"./example_data/fake.docx\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data"
    ]
   },
@@ -88,57 +64,35 @@
    "id": "8d40727d",
    "metadata": {},
    "source": [
-    "## Using Unstructured"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "721c48aa",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import UnstructuredWordDocumentLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "9d3d0e35",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredWordDocumentLoader(\"example_data/fake.docx\")"
+    "## Using Unstructured\n",
+    "\n",
+    "Please see [this guide](/docs/integrations/providers/unstructured/) for more instructions on setting up Unstructured locally, including setting up required system dependencies."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "06073f91",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "c9adc5cb",
+   "id": "721c48aa",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'fake.docx'}, lookup_index=0)]"
+       "[Document(page_content='Lorem ipsum dolor sit amet.', metadata={'source': 'example_data/fake.docx'})]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import UnstructuredWordDocumentLoader\n",
+    "\n",
+    "loader = UnstructuredWordDocumentLoader(\"example_data/fake.docx\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data"
    ]
   },
@@ -157,39 +111,23 @@
    "execution_count": 5,
    "id": "064f9162",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredWordDocumentLoader(\"example_data/fake.docx\", mode=\"elements\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "abefbbdb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "a547c534",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'fake.docx', 'filename': 'fake.docx', 'category': 'Title'}, lookup_index=0)"
+       "Document(page_content='Lorem ipsum dolor sit amet.', metadata={'source': './example_data/fake.docx', 'category_depth': 0, 'file_directory': './example_data', 'filename': 'fake.docx', 'last_modified': '2023-12-19T13:42:18', 'languages': ['por', 'cat'], 'filetype': 'application/vnd.openxmlformats-officedocument.wordprocessingml.document', 'category': 'Title'})"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "loader = UnstructuredWordDocumentLoader(\"./example_data/fake.docx\", mode=\"elements\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   },
@@ -263,7 +201,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/odt.ipynb

@@ -19,29 +19,21 @@
    "execution_count": 1,
    "id": "e6616e3a",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import UnstructuredODTLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "a654e4d9",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='Lorem ipsum dolor sit amet.', metadata={'source': 'example_data/fake.odt', 'filename': 'example_data/fake.odt', 'category': 'Title'})"
+       "Document(page_content='Lorem ipsum dolor sit amet.', metadata={'source': 'example_data/fake.odt', 'category_depth': 0, 'file_directory': 'example_data', 'filename': 'fake.odt', 'last_modified': '2023-12-19T13:42:18', 'languages': ['por', 'cat'], 'filetype': 'application/vnd.oasis.opendocument.text', 'category': 'Title'})"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import UnstructuredODTLoader\n",
+    "\n",
     "loader = UnstructuredODTLoader(\"example_data/fake.odt\", mode=\"elements\")\n",
     "docs = loader.load()\n",
     "docs[0]"
@@ -72,7 +64,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/org_mode.ipynb

@@ -22,35 +22,23 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import UnstructuredOrgModeLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredOrgModeLoader(file_path=\"example_data/README.org\", mode=\"elements\")\n",
-    "docs = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "page_content='Example Docs' metadata={'source': 'example_data/README.org', 'filename': 'README.org', 'file_directory': 'example_data', 'filetype': 'text/org', 'page_number': 1, 'category': 'Title'}\n"
+      "page_content='Example Docs' metadata={'source': './example_data/README.org', 'category_depth': 0, 'last_modified': '2023-12-19T13:42:18', 'languages': ['eng'], 'filetype': 'text/org', 'file_directory': './example_data', 'filename': 'README.org', 'category': 'Title'}\n"
      ]
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import UnstructuredOrgModeLoader\n",
+    "\n",
+    "loader = UnstructuredOrgModeLoader(\n",
+    "    file_path=\"./example_data/README.org\", mode=\"elements\"\n",
+    ")\n",
+    "docs = loader.load()\n",
+    "\n",
     "print(docs[0])"
    ]
   },
@@ -78,7 +66,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/rst.ipynb

@@ -22,35 +22,21 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import UnstructuredRSTLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredRSTLoader(file_path=\"example_data/README.rst\", mode=\"elements\")\n",
-    "docs = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "page_content='Example Docs' metadata={'source': 'example_data/README.rst', 'filename': 'README.rst', 'file_directory': 'example_data', 'filetype': 'text/x-rst', 'page_number': 1, 'category': 'Title'}\n"
+      "page_content='Example Docs' metadata={'source': './example_data/README.rst', 'category_depth': 0, 'last_modified': '2023-12-19T13:42:18', 'languages': ['eng'], 'filetype': 'text/x-rst', 'file_directory': './example_data', 'filename': 'README.rst', 'category': 'Title'}\n"
      ]
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import UnstructuredRSTLoader\n",
+    "\n",
+    "loader = UnstructuredRSTLoader(file_path=\"./example_data/README.rst\", mode=\"elements\")\n",
+    "docs = loader.load()\n",
+    "\n",
     "print(docs[0])"
    ]
   },
@@ -78,7 +64,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/tsv.ipynb

@@ -22,27 +22,6 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders.tsv import UnstructuredTSVLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredTSVLoader(\n",
-    "    file_path=\"example_data/mlb_teams_2012.csv\", mode=\"elements\"\n",
-    ")\n",
-    "docs = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -51,6 +30,9 @@
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <tbody>\n",
       "    <tr>\n",
+      "      <td>Team, \"Payroll (millions)\", \"Wins\"</td>\n",
+      "    </tr>\n",
+      "    <tr>\n",
       "      <td>Nationals,     81.34, 98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
@@ -146,6 +128,13 @@
     }
    ],
    "source": [
+    "from langchain_community.document_loaders.tsv import UnstructuredTSVLoader\n",
+    "\n",
+    "loader = UnstructuredTSVLoader(\n",
+    "    file_path=\"./example_data/mlb_teams_2012.csv\", mode=\"elements\"\n",
+    ")\n",
+    "docs = loader.load()\n",
+    "\n",
     "print(docs[0].metadata[\"text_as_html\"])"
    ]
   },
@@ -173,7 +162,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/unstructured_file.ipynb

@@ -7,18 +7,31 @@
    "source": [
     "# Unstructured File\n",
     "\n",
-    "This notebook covers how to use `Unstructured` package to load files of many types. `Unstructured` currently supports loading of text files, powerpoints, html, pdfs, images, and more."
+    "This notebook covers how to use `Unstructured` package to load files of many types. `Unstructured` currently supports loading of text files, powerpoints, html, pdfs, images, and more.\n",
+    "\n",
+    "Please see [this guide](/docs/integrations/providers/unstructured/) for more instructions on setting up Unstructured locally, including setting up required system dependencies."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "2886982e",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.1.1\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
     "# # Install package\n",
-    "%pip install --upgrade --quiet  \"unstructured[all-docs]\""
+    "%pip install --upgrade --quiet \"unstructured[all-docs]\""
    ]
   },
   {
@@ -51,39 +64,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "79d3e549",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import UnstructuredFileLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "2593d1dc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredFileLoader(\"./example_data/state_of_the_union.txt\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "fe34e941",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "ee449788",
-   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -91,12 +74,18 @@
        "'Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.\\n\\nLast year COVID-19 kept us apart. This year we are finally together again.\\n\\nTonight, we meet as Democrats Republicans and Independents. But most importantly as Americans.\\n\\nWith a duty to one another to the American people to the Constit'"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import UnstructuredFileLoader\n",
+    "\n",
+    "loader = UnstructuredFileLoader(\"./example_data/state_of_the_union.txt\")\n",
+    "\n",
+    "docs = loader.load()\n",
+    "\n",
     "docs[0].page_content[:400]"
    ]
   },
@@ -110,41 +99,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "092d9a0b",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "files = [\"./example_data/whatsapp_chat.txt\", \"./example_data/layout-parser-paper.pdf\"]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f841c4f8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredFileLoader(files)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "993c240b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5ce4ff07",
-   "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'1/22/23, 6:30 PM - User 1: Hi! Im interested in your bag. Im offering $50. Let me know if you are interested. Thanks!\\n\\n1/22/23, 8:24 PM - User 2: Goodmorning! $50 is too low.\\n\\n1/23/23, 2:59 AM - User 1: How much do you want?\\n\\n1/23/23, 3:00 AM - User 2: Online is at least $100\\n\\n1/23/23, 3:01 AM - User 2: Here is $129\\n\\n1/23/23, 3:01 AM - User 2: <Media omitted>\\n\\n1/23/23, 3:01 AM - User 1: Im not int'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
+    "files = [\"./example_data/whatsapp_chat.txt\", \"./example_data/layout-parser-paper.pdf\"]\n",
+    "\n",
+    "loader = UnstructuredFileLoader(files)\n",
+    "\n",
+    "docs = loader.load()\n",
+    "\n",
     "docs[0].page_content[:400]"
    ]
   },
@@ -160,48 +136,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 5,
    "id": "ff5b616d",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredFileLoader(\n",
-    "    \"./example_data/state_of_the_union.txt\", mode=\"elements\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "feca3b6c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "fec5bbac",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
-       " Document(page_content='Last year COVID-19 kept us apart. This year we are finally together again.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
-       " Document(page_content='Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
-       " Document(page_content='With a duty to one another to the American people to the Constitution.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
-       " Document(page_content='And with an unwavering resolve that freedom will always triumph over tyranny.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)]"
+       "[Document(page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.', metadata={'source': './example_data/state_of_the_union.txt', 'file_directory': './example_data', 'filename': 'state_of_the_union.txt', 'last_modified': '2024-07-01T11:18:22', 'languages': ['eng'], 'filetype': 'text/plain', 'category': 'NarrativeText'}),\n",
+       " Document(page_content='Last year COVID-19 kept us apart. This year we are finally together again.', metadata={'source': './example_data/state_of_the_union.txt', 'file_directory': './example_data', 'filename': 'state_of_the_union.txt', 'last_modified': '2024-07-01T11:18:22', 'languages': ['eng'], 'filetype': 'text/plain', 'category': 'NarrativeText'}),\n",
+       " Document(page_content='Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans.', metadata={'source': './example_data/state_of_the_union.txt', 'file_directory': './example_data', 'filename': 'state_of_the_union.txt', 'last_modified': '2024-07-01T11:18:22', 'languages': ['eng'], 'filetype': 'text/plain', 'category': 'NarrativeText'}),\n",
+       " Document(page_content='With a duty to one another to the American people to the Constitution.', metadata={'source': './example_data/state_of_the_union.txt', 'file_directory': './example_data', 'filename': 'state_of_the_union.txt', 'last_modified': '2024-07-01T11:18:22', 'languages': ['eng'], 'filetype': 'text/plain', 'category': 'UncategorizedText'}),\n",
+       " Document(page_content='And with an unwavering resolve that freedom will always triumph over tyranny.', metadata={'source': './example_data/state_of_the_union.txt', 'file_directory': './example_data', 'filename': 'state_of_the_union.txt', 'last_modified': '2024-07-01T11:18:22', 'languages': ['eng'], 'filetype': 'text/plain', 'category': 'NarrativeText'})]"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "loader = UnstructuredFileLoader(\n",
+    "    \"./example_data/state_of_the_union.txt\", mode=\"elements\"\n",
+    ")\n",
+    "\n",
+    "docs = loader.load()\n",
+    "\n",
     "docs[:5]"
    ]
   },
@@ -217,59 +177,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 9,
    "id": "767238a4",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import UnstructuredFileLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "9518b425",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredFileLoader(\n",
-    "    \"layout-parser-paper-fast.pdf\", strategy=\"fast\", mode=\"elements\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "645f29e9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "60685353",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='1', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
-       " Document(page_content='2', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
-       " Document(page_content='0', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
-       " Document(page_content='2', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
-       " Document(page_content='n', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'Title'}, lookup_index=0)]"
+       "[Document(page_content='2 v 8 4 3 5 1 . 3 0 1 2 : v i X r a', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 393.9), (16.34, 560.0), (36.34, 560.0), (36.34, 393.9)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'parent_id': '89565df026a24279aaea20dc08cedbec', 'filetype': 'application/pdf', 'category': 'UncategorizedText'}),\n",
+       " Document(page_content='LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((157.62199999999999, 114.23496279999995), (157.62199999999999, 146.5141628), (457.7358962799999, 146.5141628), (457.7358962799999, 114.23496279999995)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'Title'}),\n",
+       " Document(page_content='Zejiang Shen1 ((cid:0)), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain Lee4, Jacob Carlson3, and Weining Li5', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((134.809, 168.64029940800003), (134.809, 192.2517444), (480.5464199080001, 192.2517444), (480.5464199080001, 168.64029940800003)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'UncategorizedText'}),\n",
+       " Document(page_content='1 Allen Institute for AI shannons@allenai.org 2 Brown University ruochen zhang@brown.edu 3 Harvard University {melissadell,jacob carlson}@fas.harvard.edu 4 University of Washington bcgl@cs.washington.edu 5 University of Waterloo w422li@uwaterloo.ca', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((207.23000000000002, 202.57205439999996), (207.23000000000002, 311.8195408), (408.12676, 311.8195408), (408.12676, 202.57205439999996)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'UncategorizedText'}),\n",
+       " Document(page_content='Abstract. Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy reuse of im- portant innovations by a wide audience. Though there have been on-going efforts to improve reusability and simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applica- tions. The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout de- tection, character recognition, and many other document processing tasks. To promote extensibility, LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digiti- zation pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at https://layout-parser.github.io.', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((162.779, 338.45008160000003), (162.779, 566.8455408), (454.0372021523199, 566.8455408), (454.0372021523199, 338.45008160000003)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'links': [{'text': ':// layout - parser . github . io', 'url': 'https://layout-parser.github.io', 'start_index': 1477}], 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'NarrativeText'})]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "docs[:5]"
+    "from langchain_community.document_loaders import UnstructuredFileLoader\n",
+    "\n",
+    "loader = UnstructuredFileLoader(\n",
+    "    \"./example_data/layout-parser-paper.pdf\", strategy=\"fast\", mode=\"elements\"\n",
+    ")\n",
+    "\n",
+    "docs = loader.load()\n",
+    "\n",
+    "docs[5:10]"
    ]
   },
   {
@@ -287,59 +223,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "8ca8a648",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!wget  https://raw.githubusercontent.com/Unstructured-IO/unstructured/main/example-docs/layout-parser-paper.pdf -P \"../../\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 12,
    "id": "686e5eb4",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredFileLoader(\n",
-    "    \"./example_data/layout-parser-paper.pdf\", mode=\"elements\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c90f0e94",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "6ec859d8",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='LayoutParser : A Unified Toolkit for Deep Learning Based Document Image Analysis', lookup_str='', metadata={'source': '../../layout-parser-paper.pdf'}, lookup_index=0),\n",
-       " Document(page_content='Zejiang Shen 1 ( (ea)\\n ), Ruochen Zhang 2 , Melissa Dell 3 , Benjamin Charles Germain Lee 4 , Jacob Carlson 3 , and Weining Li 5', lookup_str='', metadata={'source': '../../layout-parser-paper.pdf'}, lookup_index=0),\n",
-       " Document(page_content='Allen Institute for AI shannons@allenai.org', lookup_str='', metadata={'source': '../../layout-parser-paper.pdf'}, lookup_index=0),\n",
-       " Document(page_content='Brown University ruochen zhang@brown.edu', lookup_str='', metadata={'source': '../../layout-parser-paper.pdf'}, lookup_index=0),\n",
-       " Document(page_content='Harvard University { melissadell,jacob carlson } @fas.harvard.edu', lookup_str='', metadata={'source': '../../layout-parser-paper.pdf'}, lookup_index=0)]"
+       "[Document(page_content='2 v 8 4 3 5 1 . 3 0 1 2 : v i X r a', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 393.9), (16.34, 560.0), (36.34, 560.0), (36.34, 393.9)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'parent_id': '89565df026a24279aaea20dc08cedbec', 'filetype': 'application/pdf', 'category': 'UncategorizedText'}),\n",
+       " Document(page_content='LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((157.62199999999999, 114.23496279999995), (157.62199999999999, 146.5141628), (457.7358962799999, 146.5141628), (457.7358962799999, 114.23496279999995)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'Title'}),\n",
+       " Document(page_content='Zejiang Shen1 ((cid:0)), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain Lee4, Jacob Carlson3, and Weining Li5', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((134.809, 168.64029940800003), (134.809, 192.2517444), (480.5464199080001, 192.2517444), (480.5464199080001, 168.64029940800003)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'UncategorizedText'}),\n",
+       " Document(page_content='1 Allen Institute for AI shannons@allenai.org 2 Brown University ruochen zhang@brown.edu 3 Harvard University {melissadell,jacob carlson}@fas.harvard.edu 4 University of Washington bcgl@cs.washington.edu 5 University of Waterloo w422li@uwaterloo.ca', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((207.23000000000002, 202.57205439999996), (207.23000000000002, 311.8195408), (408.12676, 311.8195408), (408.12676, 202.57205439999996)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'UncategorizedText'}),\n",
+       " Document(page_content='Abstract. Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy reuse of im- portant innovations by a wide audience. Though there have been on-going efforts to improve reusability and simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applica- tions. The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout de- tection, character recognition, and many other document processing tasks. To promote extensibility, LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digiti- zation pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at https://layout-parser.github.io.', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((162.779, 338.45008160000003), (162.779, 566.8455408), (454.0372021523199, 566.8455408), (454.0372021523199, 338.45008160000003)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'links': [{'text': ':// layout - parser . github . io', 'url': 'https://layout-parser.github.io', 'start_index': 1477}], 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'NarrativeText'})]"
       ]
      },
-     "execution_count": 1,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "docs[:5]"
+    "loader = UnstructuredFileLoader(\n",
+    "    \"./example_data/layout-parser-paper.pdf\", mode=\"elements\"\n",
+    ")\n",
+    "\n",
+    "docs = loader.load()\n",
+    "\n",
+    "docs[5:10]"
    ]
   },
   {
@@ -352,62 +262,38 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 14,
    "id": "112e5538",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import UnstructuredFileLoader\n",
-    "from unstructured.cleaners.core import clean_extra_whitespace"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "b9c5ac8d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredFileLoader(\n",
-    "    \"./example_data/layout-parser-paper.pdf\",\n",
-    "    mode=\"elements\",\n",
-    "    post_processors=[clean_extra_whitespace],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "c44d5def",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "b6f27929",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((157.62199999999999, 114.23496279999995), (157.62199999999999, 146.5141628), (457.7358962799999, 146.5141628), (457.7358962799999, 114.23496279999995)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'filename': 'layout-parser-paper.pdf', 'file_directory': './example_data', 'filetype': 'application/pdf', 'page_number': 1, 'category': 'Title'}),\n",
-       " Document(page_content='Zejiang Shen1 ((cid:0)), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain Lee4, Jacob Carlson3, and Weining Li5', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((134.809, 168.64029940800003), (134.809, 192.2517444), (480.5464199080001, 192.2517444), (480.5464199080001, 168.64029940800003)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'filename': 'layout-parser-paper.pdf', 'file_directory': './example_data', 'filetype': 'application/pdf', 'page_number': 1, 'category': 'UncategorizedText'}),\n",
-       " Document(page_content='1 Allen Institute for AI shannons@allenai.org 2 Brown University ruochen zhang@brown.edu 3 Harvard University {melissadell,jacob carlson}@fas.harvard.edu 4 University of Washington bcgl@cs.washington.edu 5 University of Waterloo w422li@uwaterloo.ca', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((207.23000000000002, 202.57205439999996), (207.23000000000002, 311.8195408), (408.12676, 311.8195408), (408.12676, 202.57205439999996)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'filename': 'layout-parser-paper.pdf', 'file_directory': './example_data', 'filetype': 'application/pdf', 'page_number': 1, 'category': 'UncategorizedText'}),\n",
-       " Document(page_content='1 2 0 2', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 213.36), (16.34, 253.36), (36.34, 253.36), (36.34, 213.36)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'filename': 'layout-parser-paper.pdf', 'file_directory': './example_data', 'filetype': 'application/pdf', 'page_number': 1, 'category': 'UncategorizedText'}),\n",
-       " Document(page_content='n u J', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 258.36), (16.34, 286.14), (36.34, 286.14), (36.34, 258.36)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'filename': 'layout-parser-paper.pdf', 'file_directory': './example_data', 'filetype': 'application/pdf', 'page_number': 1, 'category': 'Title'})]"
+       "[Document(page_content='2 v 8 4 3 5 1 . 3 0 1 2 : v i X r a', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 393.9), (16.34, 560.0), (36.34, 560.0), (36.34, 393.9)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'parent_id': '89565df026a24279aaea20dc08cedbec', 'filetype': 'application/pdf', 'category': 'UncategorizedText'}),\n",
+       " Document(page_content='LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((157.62199999999999, 114.23496279999995), (157.62199999999999, 146.5141628), (457.7358962799999, 146.5141628), (457.7358962799999, 114.23496279999995)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'Title'}),\n",
+       " Document(page_content='Zejiang Shen1 ((cid:0)), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain Lee4, Jacob Carlson3, and Weining Li5', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((134.809, 168.64029940800003), (134.809, 192.2517444), (480.5464199080001, 192.2517444), (480.5464199080001, 168.64029940800003)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'UncategorizedText'}),\n",
+       " Document(page_content='1 Allen Institute for AI shannons@allenai.org 2 Brown University ruochen zhang@brown.edu 3 Harvard University {melissadell,jacob carlson}@fas.harvard.edu 4 University of Washington bcgl@cs.washington.edu 5 University of Waterloo w422li@uwaterloo.ca', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((207.23000000000002, 202.57205439999996), (207.23000000000002, 311.8195408), (408.12676, 311.8195408), (408.12676, 202.57205439999996)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'UncategorizedText'}),\n",
+       " Document(page_content='Abstract. Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy reuse of im- portant innovations by a wide audience. Though there have been on-going efforts to improve reusability and simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applica- tions. The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout de- tection, character recognition, and many other document processing tasks. To promote extensibility, LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digiti- zation pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at https://layout-parser.github.io.', metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((162.779, 338.45008160000003), (162.779, 566.8455408), (454.0372021523199, 566.8455408), (454.0372021523199, 338.45008160000003)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2023-12-19T13:42:18', 'links': [{'text': ':// layout - parser . github . io', 'url': 'https://layout-parser.github.io', 'start_index': 1477}], 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'NarrativeText'})]"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "docs[:5]"
+    "from langchain_community.document_loaders import UnstructuredFileLoader\n",
+    "from unstructured.cleaners.core import clean_extra_whitespace\n",
+    "\n",
+    "loader = UnstructuredFileLoader(\n",
+    "    \"./example_data/layout-parser-paper.pdf\",\n",
+    "    mode=\"elements\",\n",
+    "    post_processors=[clean_extra_whitespace],\n",
+    ")\n",
+    "\n",
+    "docs = loader.load()\n",
+    "\n",
+    "docs[5:10]"
    ]
   },
   {
@@ -420,39 +306,6 @@
     "If you want to get up and running with less set up, you can simply run `pip install unstructured` and use `UnstructuredAPIFileLoader` or `UnstructuredAPIFileIOLoader`. That will process your document using the hosted Unstructured API. You can generate a free Unstructured API key [here](https://www.unstructured.io/api-key/). The [Unstructured documentation](https://unstructured-io.github.io/unstructured/) page will have instructions on how to generate an API key once they’re available. Check out the instructions [here](https://github.com/Unstructured-IO/unstructured-api#dizzy-instructions-for-using-the-docker-image) if you’d like to self-host the Unstructured API or run it locally."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "b50c70bc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import UnstructuredAPIFileLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "12b6d2cf",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "filenames = [\"example_data/fake.docx\", \"example_data/fake-email.eml\"]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "39a9894d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredAPIFileLoader(\n",
-    "    file_path=filenames[0],\n",
-    "    api_key=\"FAKE_API_KEY\",\n",
-    ")"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 4,
@@ -471,6 +324,15 @@
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import UnstructuredAPIFileLoader\n",
+    "\n",
+    "filenames = [\"example_data/fake.docx\", \"example_data/fake-email.eml\"]\n",
+    "\n",
+    "loader = UnstructuredAPIFileLoader(\n",
+    "    file_path=filenames[0],\n",
+    "    api_key=\"FAKE_API_KEY\",\n",
+    ")\n",
+    "\n",
     "docs = loader.load()\n",
     "docs[0]"
    ]
@@ -483,19 +345,6 @@
     "You can also batch multiple files through the Unstructured API in a single API using `UnstructuredAPIFileLoader`."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "79a18e7e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredAPIFileLoader(\n",
-    "    file_path=filenames,\n",
-    "    api_key=\"FAKE_API_KEY\",\n",
-    ")"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 6,
@@ -514,6 +363,11 @@
     }
    ],
    "source": [
+    "loader = UnstructuredAPIFileLoader(\n",
+    "    file_path=filenames,\n",
+    "    api_key=\"FAKE_API_KEY\",\n",
+    ")\n",
+    "\n",
     "docs = loader.load()\n",
     "docs[0]"
    ]
@@ -543,7 +397,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.0"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/xml.ipynb

@@ -17,29 +17,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.document_loaders import UnstructuredXMLLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "a654e4d9",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Document(page_content='United States\\n\\nWashington, DC\\n\\nJoe Biden\\n\\nBaseball\\n\\nCanada\\n\\nOttawa\\n\\nJustin Trudeau\\n\\nHockey\\n\\nFrance\\n\\nParis\\n\\nEmmanuel Macron\\n\\nSoccer\\n\\nTrinidad & Tobado\\n\\nPort of Spain\\n\\nKeith Rowley\\n\\nTrack & Field', metadata={'source': 'example_data/factbook.xml'})"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
+    "from langchain_community.document_loaders import UnstructuredXMLLoader\n",
+    "\n",
     "loader = UnstructuredXMLLoader(\n",
-    "    \"example_data/factbook.xml\",\n",
+    "    \"./example_data/factbook.xml\",\n",
     ")\n",
     "docs = loader.load()\n",
     "docs[0]"

docs/docs/integrations/document_transformers/html2text.ipynb

@@ -19,12 +19,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  html2text"
+    "%pip install --upgrade --quiet html2text"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
    "id": "8ca0974b",
    "metadata": {},
    "outputs": [
@@ -32,7 +32,8 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Fetching pages: 100%|############| 2/2 [00:00<00:00, 10.75it/s]\n"
+      "USER_AGENT environment variable not set, consider setting it to identify your requests.\n",
+      "Fetching pages: 100%|##########| 2/2 [00:00<00:00, 14.74it/s]\n"
      ]
     }
    ],
@@ -46,66 +47,107 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "ddf2be97",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_transformers import Html2TextTransformer"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "id": "a95a928c",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "## Fantasy\n",
+      "\n",
+      "  * Football\n",
+      "\n",
+      "  * Baseball\n",
+      "\n",
+      "  * Basketball\n",
+      "\n",
+      "  * Hockey\n",
+      "\n",
+      "## ESPN Sites\n",
+      "\n",
+      "  * ESPN Deportes\n",
+      "\n",
+      "  * Andscape\n",
+      "\n",
+      "  * espnW\n",
+      "\n",
+      "  * ESPNFC\n",
+      "\n",
+      "  * X Games\n",
+      "\n",
+      "  * SEC Network\n",
+      "\n",
+      "## ESPN Apps\n",
+      "\n",
+      "  * ESPN\n",
+      "\n",
+      "  * ESPN Fantasy\n",
+      "\n",
+      "  * Tournament Challenge\n",
+      "\n",
+      "## Follow ESPN\n",
+      "\n",
+      "  * Facebook\n",
+      "\n",
+      "  * X/Twitter\n",
+      "\n",
+      "  * Instagram\n",
+      "\n",
+      "  * Snapchat\n",
+      "\n",
+      "  * TikTok\n",
+      "\n",
+      "  * YouTube\n",
+      "\n",
+      "## Fresh updates to our NBA mock draft: Everything we're hearing hours before\n",
+      "Round 1\n",
+      "\n",
+      "With hours until Round 1 begins (8 p.m. ET on ESPN and ABC), ESPN draft\n",
+      "insiders Jonathan Givony and Jeremy Woo have new intel on lottery picks and\n",
+      "more.\n",
+      "\n",
+      "2hJonathan Givony and Jeremy Woo\n",
+      "\n",
+      "Illustration by ESPN\n",
+      "\n",
+      "## From No. 1 to 100: Ranking the 2024 NBA draft prospects\n",
+      "\n",
+      "Who's No. 1? Where do the Kentucky, Duke and UConn players rank? Here's our\n",
+      "final Top 100 Big Board.\n",
+      "\n",
+      "6hJonathan Givony and Jeremy Woo\n",
+      "\n",
+      "  * Full draft order: All 58 picks over two rounds\n",
+      "  * Trade tracker: Details for all deals\n",
+      "\n",
+      "  * Betting buzz: Lakers favorites to draft Bronny\n",
+      "  * Use our NBA draft simu\n",
+      "ent system, LLM functions as the agent's brain,\n",
+      "complemented by several key components:\n",
+      "\n",
+      "  * **Planning**\n",
+      "    * Subgoal and decomposition: The agent breaks down large tasks into smaller, manageable subgoals, enabling efficient handling of complex tasks.\n",
+      "    * Reflection and refinement: The agent can do self-criticism and self-reflection over past actions, learn from mistakes and refine them for future steps, thereby improving the quality of final results.\n",
+      "  * **Memory**\n",
+      "    * Short-term memory: I would consider all the in-context learning (See Prompt Engineering) as utilizing short-term memory of the model to learn.\n",
+      "    * Long-term memory: This provides the agent with the capability to retain and recall (infinite) information over extended periods, often by leveraging an external vector store and fast retrieval.\n",
+      "  * **Tool use**\n",
+      "    * The agent learns to call external APIs for extra information that is missing from the model weights (often hard to change after pre-training), including \n"
+     ]
+    }
+   ],
    "source": [
+    "from langchain_community.document_transformers import Html2TextTransformer\n",
+    "\n",
     "urls = [\"https://www.espn.com\", \"https://lilianweng.github.io/posts/2023-06-23-agent/\"]\n",
     "html2text = Html2TextTransformer()\n",
-    "docs_transformed = html2text.transform_documents(docs)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "18ef9fe9",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"  * ESPNFC\\n\\n  * X Games\\n\\n  * SEC Network\\n\\n## ESPN Apps\\n\\n  * ESPN\\n\\n  * ESPN Fantasy\\n\\n## Follow ESPN\\n\\n  * Facebook\\n\\n  * Twitter\\n\\n  * Instagram\\n\\n  * Snapchat\\n\\n  * YouTube\\n\\n  * The ESPN Daily Podcast\\n\\n2023 FIFA Women's World Cup\\n\\n## Follow live: Canada takes on Nigeria in group stage of Women's World Cup\\n\\n2m\\n\\nEPA/Morgan Hancock\\n\\n## TOP HEADLINES\\n\\n  * Snyder fined $60M over findings in investigation\\n  * NFL owners approve $6.05B sale of Commanders\\n  * Jags assistant comes out as gay in NFL milestone\\n  * O's alone atop East after topping slumping Rays\\n  * ACC's Phillips: Never condoned hazing at NU\\n\\n  * Vikings WR Addison cited for driving 140 mph\\n  * 'Taking his time': Patient QB Rodgers wows Jets\\n  * Reyna got U.S. assurances after Berhalter rehire\\n  * NFL Future Power Rankings\\n\\n## USWNT AT THE WORLD CUP\\n\\n### USA VS. VIETNAM: 9 P.M. ET FRIDAY\\n\\n## How do you defend against Alex Morgan? Former opponents sound off\\n\\nThe U.S. forward is unstoppable at this level, scoring 121 goals and adding 49\""
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "docs_transformed[0].page_content[1000:2000]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "6045d660",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"t's brain,\\ncomplemented by several key components:\\n\\n  * **Planning**\\n    * Subgoal and decomposition: The agent breaks down large tasks into smaller, manageable subgoals, enabling efficient handling of complex tasks.\\n    * Reflection and refinement: The agent can do self-criticism and self-reflection over past actions, learn from mistakes and refine them for future steps, thereby improving the quality of final results.\\n  * **Memory**\\n    * Short-term memory: I would consider all the in-context learning (See Prompt Engineering) as utilizing short-term memory of the model to learn.\\n    * Long-term memory: This provides the agent with the capability to retain and recall (infinite) information over extended periods, often by leveraging an external vector store and fast retrieval.\\n  * **Tool use**\\n    * The agent learns to call external APIs for extra information that is missing from the model weights (often hard to change after pre-training), including current information, code execution c\""
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "docs_transformed[1].page_content[1000:2000]"
+    "docs_transformed = html2text.transform_documents(docs)\n",
+    "\n",
+    "print(docs_transformed[0].page_content[1000:2000])\n",
+    "\n",
+    "print(docs_transformed[1].page_content[1000:2000])"
    ]
   }
  ],
@@ -125,7 +167,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

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/ai21.ipynb

@@ -17,7 +17,9 @@
    "source": [
     "# AI21LLM\n",
     "\n",
-    "This example goes over how to use LangChain to interact with `AI21` models.\n",
+    "This example goes over how to use LangChain to interact with `AI21` Jurassic models. To use the Jamba model, use the [ChatAI21 object](https://python.langchain.com/v0.2/docs/integrations/chat/ai21/) instead.\n",
+    "\n",
+    "[See a full list of AI21 models and tools on LangChain.](https://pypi.org/project/langchain-ai21/)\n",
     "\n",
     "## Installation"
    ]

docs/docs/integrations/llms/bedrock.ipynb

@@ -34,7 +34,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  boto3"
+    "%pip install --upgrade --quiet langchain_aws"
    ]
   },
   {
@@ -45,9 +45,9 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_community.llms import Bedrock\n",
+    "from langchain_aws import BedrockLLM\n",
     "\n",
-    "llm = Bedrock(\n",
+    "llm = BedrockLLM(\n",
     "    credentials_profile_name=\"bedrock-admin\", model_id=\"amazon.titan-text-express-v1\"\n",
     ")"
    ]
@@ -65,7 +65,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "custom_llm = Bedrock(\n",
+    "custom_llm = BedrockLLM(\n",
     "    credentials_profile_name=\"bedrock-admin\",\n",
     "    provider=\"cohere\",\n",
     "    model_id=\"<Custom model ARN>\",  # ARN like 'arn:aws:bedrock:...' obtained via provisioning the custom model\n",
@@ -108,7 +108,7 @@
     "\n",
     "\n",
     "# Guardrails for Amazon Bedrock with trace\n",
-    "llm = Bedrock(\n",
+    "llm = BedrockLLM(\n",
     "    credentials_profile_name=\"bedrock-admin\",\n",
     "    model_id=\"<Model_ID>\",\n",
     "    model_kwargs={},\n",
@@ -134,7 +134,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/platforms/aws.mdx

@@ -18,16 +18,6 @@ pip install langchain-community boto3
 
 ### Bedrock Chat
 
-See a [usage example](/docs/integrations/chat/bedrock).
-
-```python
-from langchain_aws import ChatBedrock
-```
-
-## LLMs
-
-### Bedrock
-
 >[Amazon Bedrock](https://aws.amazon.com/bedrock/) is a fully managed service that offers a choice of 
 > high-performing foundation models (FMs) from leading AI companies like `AI21 Labs`, `Anthropic`, `Cohere`, 
 > `Meta`, `Stability AI`, and `Amazon` via a single API, along with a broad set of capabilities you need to 
@@ -38,6 +28,15 @@ from langchain_aws import ChatBedrock
 > serverless, you don't have to manage any infrastructure, and you can securely integrate and deploy 
 > generative AI capabilities into your applications using the AWS services you are already familiar with.
 
+See a [usage example](/docs/integrations/chat/bedrock).
+
+```python
+from langchain_aws import ChatBedrock
+```
+
+## LLMs
+
+### Bedrock
  
 See a [usage example](/docs/integrations/llms/bedrock).
 

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/ibm.mdx

@@ -28,6 +28,16 @@ import os
 os.environ["WATSONX_APIKEY"] = "your IBM watsonx.ai api key"
 ```
 
+## Chat Model
+
+### ChatWatsonx
+
+See a [usage example](/docs/integrations/chat/ibm_watsonx).
+
+```python
+from langchain_ibm import ChatWatsonx
+```
+
 ## LLMs
 
 ### WatsonxLLM

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/index.md

@@ -0,0 +1,21 @@
+# Pebblo
+
+[Pebblo](https://www.daxa.ai/pebblo) enables developers to safely load and retrieve data to promote their Gen AI app to deployment without
+worrying about the organization’s compliance and security requirements. The Pebblo SafeLoader identifies semantic topics and entities found in the
+loaded data and the Pebblo SafeRetriever enforces identity and semantic controls on the retrieved context. The results are
+summarized on the UI or a PDF report.
+
+
+## Pebblo Overview:
+
+`Pebblo` provides a safe way to load and retrieve data for Gen AI applications. 
+It includes:
+1. **Identity-aware Safe Loader** that loads data and identifies semantic topics and entities.
+2. **SafeRetrieval**  that enforces identity and semantic controls on the retrieved context.
+3. **User Data Report** that summarizes the data loaded and retrieved.
+
+## Example Notebooks
+
+For a more detailed examples of using Pebblo, see the following notebooks:
+* [PebbloSafeLoader](/docs/integrations/document_loaders/pebblo) shows how to use Pebblo loader to safely load data.
+* [PebbloRetrievalQA](/docs/integrations/providers/pebblo/pebblo_retrieval_qa) shows how to use Pebblo retrieval QA chain to safely retrieve data.

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

@@ -0,0 +1,585 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "3ce451e9-f8f1-4f27-8c6b-4a93a406d504",
+   "metadata": {},
+   "source": [
+    "# Identity-enabled RAG using PebbloRetrievalQA\n",
+    "\n",
+    "> PebbloRetrievalQA is a Retrieval chain with Identity & Semantic Enforcement for question-answering\n",
+    "against a vector database.\n",
+    "\n",
+    "This notebook covers how to retrieve documents using Identity & Semantic Enforcement (Deny Topics/Entities).\n",
+    "For more details on Pebblo and its SafeRetriever feature visit [Pebblo documentation](https://daxa-ai.github.io/pebblo/retrieval_chain/)\n",
+    "\n",
+    "### Steps:\n",
+    "\n",
+    "1. **Loading Documents:**\n",
+    "We will load documents with authorization and semantic metadata into an in-memory Qdrant vectorstore. This vectorstore will be used as a retriever in PebbloRetrievalQA. \n",
+    "\n",
+    "> **Note:** It is recommended to use [PebbloSafeLoader](https://daxa-ai.github.io/pebblo/rag) as the counterpart for loading documents with authentication and semantic metadata on the ingestion side. `PebbloSafeLoader` guarantees the secure and efficient loading of documents while maintaining the integrity of the metadata.\n",
+    "\n",
+    "\n",
+    "\n",
+    "2. **Testing Enforcement Mechanisms**:\n",
+    "   We will test Identity and Semantic Enforcement separately. For each use case, we will define a specific \"ask\" function with the required contexts (*auth_context* and *semantic_context*) and then pose our questions.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4ee16b6b-5dac-4b5c-bb69-3ec87398a33c",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "### Dependencies\n",
+    "\n",
+    "We'll use an OpenAI LLM, OpenAI embeddings and a Qdrant vector store in this walkthrough.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e68494fa-f387-4481-9a6c-58294865d7b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet langchain langchain_core langchain-community langchain-openai qdrant_client"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "61498d51-0c38-40e2-adcd-19dfdf4d37ef",
+   "metadata": {},
+   "source": [
+    "### Identity-aware Data Ingestion\n",
+    "\n",
+    "Here we are using Qdrant as a vector database; however, you can use any of the supported vector databases.\n",
+    "\n",
+    "**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",
+    "\n",
+    "In this step, we capture the authorization and semantic information of the source document into the `authorized_identities`, `pebblo_semantic_topics`, and `pebblo_semantic_entities` fields within the metadata of the VectorDB entry for each chunk. \n",
+    "\n",
+    "\n",
+    "*NOTE: To use the PebbloRetrievalQA chain, you must always place authorization and semantic metadata in the specified fields. These fields must contain a list of strings.*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "ae4fcbc1-bdc3-40d2-b2df-8c82cad1f89c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Vectordb loaded.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_community.vectorstores.qdrant import Qdrant\n",
+    "from langchain_core.documents import Document\n",
+    "from langchain_openai.embeddings import OpenAIEmbeddings\n",
+    "from langchain_openai.llms import OpenAI\n",
+    "\n",
+    "llm = OpenAI()\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "collection_name = \"pebblo-identity-and-semantic-rag\"\n",
+    "\n",
+    "page_content = \"\"\"\n",
+    "**ACME Corp Financial Report**\n",
+    "\n",
+    "**Overview:**\n",
+    "ACME Corp, a leading player in the merger and acquisition industry, presents its financial report for the fiscal year ending December 31, 2020. \n",
+    "Despite a challenging economic landscape, ACME Corp demonstrated robust performance and strategic growth.\n",
+    "\n",
+    "**Financial Highlights:**\n",
+    "Revenue soared to $50 million, marking a 15% increase from the previous year, driven by successful deal closures and expansion into new markets. \n",
+    "Net profit reached $12 million, showcasing a healthy margin of 24%.\n",
+    "\n",
+    "**Key Metrics:**\n",
+    "Total assets surged to $80 million, reflecting a 20% growth, highlighting ACME Corp's strong financial position and asset base. \n",
+    "Additionally, the company maintained a conservative debt-to-equity ratio of 0.5, ensuring sustainable financial stability.\n",
+    "\n",
+    "**Future Outlook:**\n",
+    "ACME Corp remains optimistic about the future, with plans to capitalize on emerging opportunities in the global M&A landscape. \n",
+    "The company is committed to delivering value to shareholders while maintaining ethical business practices.\n",
+    "\n",
+    "**Bank Account Details:**\n",
+    "For inquiries or transactions, please refer to ACME Corp's US bank account:\n",
+    "Account Number: 123456789012\n",
+    "Bank Name: Fictitious Bank of America\n",
+    "\"\"\"\n",
+    "\n",
+    "documents = [\n",
+    "    Document(\n",
+    "        **{\n",
+    "            \"page_content\": page_content,\n",
+    "            \"metadata\": {\n",
+    "                \"pebblo_semantic_topics\": [\"financial-report\"],\n",
+    "                \"pebblo_semantic_entities\": [\"us-bank-account-number\"],\n",
+    "                \"authorized_identities\": [\"finance-team\", \"exec-leadership\"],\n",
+    "                \"page\": 0,\n",
+    "                \"source\": \"https://drive.google.com/file/d/xxxxxxxxxxxxx/view\",\n",
+    "                \"title\": \"ACME Corp Financial Report.pdf\",\n",
+    "            },\n",
+    "        }\n",
+    "    )\n",
+    "]\n",
+    "\n",
+    "vectordb = Qdrant.from_documents(\n",
+    "    documents,\n",
+    "    embeddings,\n",
+    "    location=\":memory:\",\n",
+    "    collection_name=collection_name,\n",
+    ")\n",
+    "\n",
+    "print(\"Vectordb loaded.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f630bb8b-67ba-41f9-8715-76d006207e75",
+   "metadata": {},
+   "source": [
+    "## Retrieval with Identity Enforcement\n",
+    "\n",
+    "PebbloRetrievalQA chain uses a SafeRetrieval to enforce that the snippets used for in-context are retrieved only from the documents authorized for the user. \n",
+    "To achieve this, the Gen-AI application needs to provide an authorization context for this retrieval chain. \n",
+    "This *auth_context* should be filled with the identity and authorization groups of the user accessing the Gen-AI app.\n",
+    "\n",
+    "\n",
+    "Here is the sample code for the `PebbloRetrievalQA` with `user_auth`(List of user authorizations, which may include their User ID and \n",
+    "    the groups they are part of) from the user accessing the RAG application, passed in `auth_context`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "e978bee6-3a8c-459f-ab82-d380d7499b36",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chains import PebbloRetrievalQA\n",
+    "from langchain_community.chains.pebblo_retrieval.models import AuthContext, ChainInput\n",
+    "\n",
+    "# Initialize PebbloRetrievalQA chain\n",
+    "qa_chain = PebbloRetrievalQA.from_chain_type(\n",
+    "    llm=llm,\n",
+    "    retriever=vectordb.as_retriever(),\n",
+    "    app_name=\"pebblo-identity-rag\",\n",
+    "    description=\"Identity Enforcement app using PebbloRetrievalQA\",\n",
+    "    owner=\"ACME Corp\",\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def ask(question: str, auth_context: dict):\n",
+    "    \"\"\"\n",
+    "    Ask a question to the PebbloRetrievalQA chain\n",
+    "    \"\"\"\n",
+    "    auth_context_obj = AuthContext(**auth_context) if auth_context else None\n",
+    "    chain_input_obj = ChainInput(query=question, auth_context=auth_context_obj)\n",
+    "    return qa_chain.invoke(chain_input_obj.dict())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7a267e96-70cb-468f-b830-83b65e9b7f6f",
+   "metadata": {},
+   "source": [
+    "### 1. Questions by Authorized User\n",
+    "\n",
+    "We ingested data for authorized identities `[\"finance-team\", \"exec-leadership\"]`, so a user with the authorized identity/group `finance-team` should receive the correct answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "2688fc18-1eac-45a5-be55-aabbe6b25af5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Question: Share the financial performance of ACME Corp for the year 2020\n",
+      "\n",
+      "Answer: \n",
+      "Revenue: $50 million (15% increase from previous year)\n",
+      "Net profit: $12 million (24% margin)\n",
+      "Total assets: $80 million (20% growth)\n",
+      "Debt-to-equity ratio: 0.5\n"
+     ]
+    }
+   ],
+   "source": [
+    "auth = {\n",
+    "    \"user_id\": \"finance-user@acme.org\",\n",
+    "    \"user_auth\": [\n",
+    "        \"finance-team\",\n",
+    "    ],\n",
+    "}\n",
+    "\n",
+    "question = \"Share the financial performance of ACME Corp for the year 2020\"\n",
+    "resp = ask(question, auth)\n",
+    "print(f\"Question: {question}\\n\\nAnswer: {resp['result']}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b4db6566-6562-4a49-b19c-6d99299b374e",
+   "metadata": {},
+   "source": [
+    "### 2. Questions by Unauthorized User\n",
+    "\n",
+    "Since the user's authorized identity/group `eng-support` is not included in the authorized identities `[\"finance-team\", \"exec-leadership\"]`, we should not receive an answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "2d736ce3-6e05-48d3-a5e1-fb4e7cccc1ee",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Question: Share the financial performance of ACME Corp for the year 2020\n",
+      "\n",
+      "Answer:  I don't know.\n"
+     ]
+    }
+   ],
+   "source": [
+    "auth = {\n",
+    "    \"user_id\": \"eng-user@acme.org\",\n",
+    "    \"user_auth\": [\n",
+    "        \"eng-support\",\n",
+    "    ],\n",
+    "}\n",
+    "\n",
+    "question = \"Share the financial performance of ACME Corp for the year 2020\"\n",
+    "resp = ask(question, auth)\n",
+    "print(f\"Question: {question}\\n\\nAnswer: {resp['result']}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "33a8afe1-3071-4118-9714-a17cba809ee4",
+   "metadata": {},
+   "source": [
+    "### 3. Using PromptTemplate to provide additional instructions\n",
+    "You can use PromptTemplate to provide additional instructions to the LLM for generating a custom response."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "59c055ba-fdd1-48c6-9bc9-2793eb47438d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import PromptTemplate\n",
+    "\n",
+    "prompt_template = PromptTemplate.from_template(\n",
+    "    \"\"\"\n",
+    "Answer the question using the provided context. \n",
+    "If no context is provided, just say \"I'm sorry, but that information is unavailable, or Access to it is restricted.\".\n",
+    "\n",
+    "Question: {question}\n",
+    "\"\"\"\n",
+    ")\n",
+    "\n",
+    "question = \"Share the financial performance of ACME Corp for the year 2020\"\n",
+    "prompt = prompt_template.format(question=question)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c4d27c00-73d9-4ce8-bc70-29535deaf0e2",
+   "metadata": {},
+   "source": [
+    "#### 3.1 Questions by Authorized User"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "e68a13a4-b735-421d-9655-2a9a087ba9e5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Question: Share the financial performance of ACME Corp for the year 2020\n",
+      "\n",
+      "Answer: \n",
+      "Revenue soared to $50 million, marking a 15% increase from the previous year, and net profit reached $12 million, showcasing a healthy margin of 24%. Total assets also grew by 20% to $80 million, and the company maintained a conservative debt-to-equity ratio of 0.5.\n"
+     ]
+    }
+   ],
+   "source": [
+    "auth = {\n",
+    "    \"user_id\": \"finance-user@acme.org\",\n",
+    "    \"user_auth\": [\n",
+    "        \"finance-team\",\n",
+    "    ],\n",
+    "}\n",
+    "resp = ask(prompt, auth)\n",
+    "print(f\"Question: {question}\\n\\nAnswer: {resp['result']}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7b97a9ca-bdc6-400a-923d-65a8536658be",
+   "metadata": {},
+   "source": [
+    "#### 3.2 Questions by Unauthorized Users"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "438e48c6-96a2-4d5e-81db-47f8c8f37739",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Question: Share the financial performance of ACME Corp for the year 2020\n",
+      "\n",
+      "Answer: \n",
+      "I'm sorry, but that information is unavailable, or Access to it is restricted.\n"
+     ]
+    }
+   ],
+   "source": [
+    "auth = {\n",
+    "    \"user_id\": \"eng-user@acme.org\",\n",
+    "    \"user_auth\": [\n",
+    "        \"eng-support\",\n",
+    "    ],\n",
+    "}\n",
+    "resp = ask(prompt, auth)\n",
+    "print(f\"Question: {question}\\n\\nAnswer: {resp['result']}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4306cab3-d070-405f-a23b-5c6011a61c50",
+   "metadata": {},
+   "source": [
+    "## Retrieval with Semantic Enforcement"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1c3757cf-832f-483e-aafe-cb09b5130ec0",
+   "metadata": {},
+   "source": [
+    "The PebbloRetrievalQA chain uses SafeRetrieval to ensure that the snippets used in context are retrieved only from documents that comply with the\n",
+    "provided semantic context.\n",
+    "To achieve this, the Gen-AI application must provide a semantic context for this retrieval chain.\n",
+    "This `semantic_context` should include the topics and entities that should be denied for the user accessing the Gen-AI app.\n",
+    "\n",
+    "Below is a sample code for PebbloRetrievalQA with `topics_to_deny` and `entities_to_deny`. These are passed in `semantic_context` to the chain input."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "daf37bf7-9a16-4102-8893-5b698cae1b07",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List, Optional\n",
+    "\n",
+    "from langchain_community.chains import PebbloRetrievalQA\n",
+    "from langchain_community.chains.pebblo_retrieval.models import (\n",
+    "    ChainInput,\n",
+    "    SemanticContext,\n",
+    ")\n",
+    "\n",
+    "# Initialize PebbloRetrievalQA chain\n",
+    "qa_chain = PebbloRetrievalQA.from_chain_type(\n",
+    "    llm=llm,\n",
+    "    retriever=vectordb.as_retriever(),\n",
+    "    app_name=\"pebblo-semantic-rag\",\n",
+    "    description=\"Semantic Enforcement app using PebbloRetrievalQA\",\n",
+    "    owner=\"ACME Corp\",\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def ask(\n",
+    "    question: str,\n",
+    "    topics_to_deny: Optional[List[str]] = None,\n",
+    "    entities_to_deny: Optional[List[str]] = None,\n",
+    "):\n",
+    "    \"\"\"\n",
+    "    Ask a question to the PebbloRetrievalQA chain\n",
+    "    \"\"\"\n",
+    "    semantic_context = dict()\n",
+    "    if topics_to_deny:\n",
+    "        semantic_context[\"pebblo_semantic_topics\"] = {\"deny\": topics_to_deny}\n",
+    "    if entities_to_deny:\n",
+    "        semantic_context[\"pebblo_semantic_entities\"] = {\"deny\": entities_to_deny}\n",
+    "\n",
+    "    semantic_context_obj = (\n",
+    "        SemanticContext(**semantic_context) if semantic_context else None\n",
+    "    )\n",
+    "    chain_input_obj = ChainInput(query=question, semantic_context=semantic_context_obj)\n",
+    "    return qa_chain.invoke(chain_input_obj.dict())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9718819b-f5cd-4212-9947-d18cd507c8b7",
+   "metadata": {},
+   "source": [
+    "### 1. Without semantic enforcement\n",
+    "\n",
+    "Since no semantic enforcement is applied, the system should return the answer without excluding any context due to the semantic labels associated with the context.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "69158be1-f223-4d14-b61f-f4afdf5af526",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Topics to deny: []\n",
+      "Entities to deny: []\n",
+      "Question: Share the financial performance of ACME Corp for the year 2020\n",
+      "Answer: \n",
+      "Revenue for ACME Corp increased by 15% to $50 million in 2020, with a net profit of $12 million and a strong asset base of $80 million. The company also maintained a conservative debt-to-equity ratio of 0.5.\n"
+     ]
+    }
+   ],
+   "source": [
+    "topic_to_deny = []\n",
+    "entities_to_deny = []\n",
+    "question = \"Share the financial performance of ACME Corp for the year 2020\"\n",
+    "resp = ask(question, topics_to_deny=topic_to_deny, entities_to_deny=entities_to_deny)\n",
+    "print(\n",
+    "    f\"Topics to deny: {topic_to_deny}\\nEntities to deny: {entities_to_deny}\\n\"\n",
+    "    f\"Question: {question}\\nAnswer: {resp['result']}\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c8789c58-0d64-404e-bc09-92f6952022ac",
+   "metadata": {},
+   "source": [
+    "### 2. Deny financial-report topic\n",
+    "\n",
+    "Data has been ingested with the topics: `[\"financial-report\"]`.\n",
+    "Therefore, an app that denies the `financial-report` topic should not receive an answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "9b17b2fc-eefb-4229-a41e-2f943d2eb48e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Topics to deny: ['financial-report']\n",
+      "Entities to deny: []\n",
+      "Question: Share the financial performance of ACME Corp for the year 2020\n",
+      "Answer: \n",
+      "\n",
+      "Unfortunately, I do not have access to the financial performance of ACME Corp for the year 2020.\n"
+     ]
+    }
+   ],
+   "source": [
+    "topic_to_deny = [\"financial-report\"]\n",
+    "entities_to_deny = []\n",
+    "question = \"Share the financial performance of ACME Corp for the year 2020\"\n",
+    "resp = ask(question, topics_to_deny=topic_to_deny, entities_to_deny=entities_to_deny)\n",
+    "print(\n",
+    "    f\"Topics to deny: {topic_to_deny}\\nEntities to deny: {entities_to_deny}\\n\"\n",
+    "    f\"Question: {question}\\nAnswer: {resp['result']}\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "894f21b0-2913-4ef6-b5ed-cbca8f74214d",
+   "metadata": {},
+   "source": [
+    "### 3. Deny us-bank-account-number entity\n",
+    "Since the entity `us-bank-account-number` is denied, the system should not return the answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "2b8abce3-7af3-437f-8999-2866a4b9beda",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Topics to deny: []\n",
+      "Entities to deny: ['us-bank-account-number']\n",
+      "Question: Share the financial performance of ACME Corp for the year 2020\n",
+      "Answer:  I don't have information about ACME Corp's financial performance for 2020.\n"
+     ]
+    }
+   ],
+   "source": [
+    "topic_to_deny = []\n",
+    "entities_to_deny = [\"us-bank-account-number\"]\n",
+    "question = \"Share the financial performance of ACME Corp for the year 2020\"\n",
+    "resp = ask(question, topics_to_deny=topic_to_deny, entities_to_deny=entities_to_deny)\n",
+    "print(\n",
+    "    f\"Topics to deny: {topic_to_deny}\\nEntities to deny: {entities_to_deny}\\n\"\n",
+    "    f\"Question: {question}\\nAnswer: {resp['result']}\"\n",
+    ")"
+   ]
+  }
+ ],
+ "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": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/providers/unstructured.mdx

@@ -14,14 +14,18 @@ its dependencies running locally.
 - Install the Python SDK with `pip install unstructured`.
     - You can install document specific dependencies with extras, i.e. `pip install "unstructured[docx]"`.
     - To install the dependencies for all document types, use `pip install "unstructured[all-docs]"`.
-- Install the following system dependencies if they are not already available on your system.
+- Install the following system dependencies if they are not already available on your system with e.g. `brew install` for Mac.
   Depending on what document types you're parsing, you may not need all of these.
     - `libmagic-dev` (filetype detection)
     - `poppler-utils` (images and PDFs)
     - `tesseract-ocr`(images and PDFs)
+    - `qpdf` (PDFs)
     - `libreoffice` (MS Office docs)
     - `pandoc` (EPUBs)
 
+When running locally, Unstructured also recommends using Docker [by following this guide](https://docs.unstructured.io/open-source/installation/docker-installation)
+to ensure all system dependencies are installed correctly.
+
 If you want to get up and running with less set up, you can
 simply run `pip install unstructured` and use `UnstructuredAPIFileLoader` or
 `UnstructuredAPIFileIOLoader`. That will process your document using the hosted Unstructured API.

docs/docs/integrations/text_embedding/azureopenai.ipynb

@@ -20,6 +20,16 @@
     "Let's load the Azure OpenAI Embedding class with environment variables set to indicate to use Azure endpoints."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "228faf0c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet langchain_openai"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -180,9 +190,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "poetry-venv"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -194,12 +204,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
-   }
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/text_embedding/jina.ipynb

@@ -5,9 +5,15 @@
    "id": "1c0cf975",
    "metadata": {},
    "source": [
-    "# Jina\n",
-    "\n",
-    "Let's load the Jina Embedding class."
+    "# Jina"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "da922b13-eaa8-4cdc-98dd-cf8f3d2e6ffa",
+   "metadata": {},
+   "source": [
+    "Install requirements"
    ]
   },
   {
@@ -20,6 +26,14 @@
     "pip install -U langchain-community"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "7911b286-130d-4971-b77c-7c7a077115b6",
+   "metadata": {},
+   "source": [
+    "Import libraries"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -34,6 +48,14 @@
     "from PIL import Image"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "59aa1c02-1216-43eb-8473-8e0468f0ddb6",
+   "metadata": {},
+   "source": [
+    "## Embed text and queries with Jina embedding models through JinaAI API"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -43,9 +65,7 @@
    "source": [
     "text_embeddings = JinaEmbeddings(\n",
     "    jina_api_key=\"jina_*\", model_name=\"jina-embeddings-v2-base-en\"\n",
-    ")\n",
-    "\n",
-    "image_embeddings = JinaEmbeddings(jina_api_key=\"jina_*\", model_name=\"jina-clip-v1\")"
+    ")"
    ]
   },
   {
@@ -55,15 +75,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "text = \"This is a test document.\"\n",
-    "\n",
-    "image = \"https://avatars.githubusercontent.com/u/126733545?v=4\"\n",
-    "\n",
-    "description = \"Logo of a parrot and a chain on green background\"\n",
-    "\n",
-    "im = Image.open(requests.get(image, stream=True).raw)\n",
-    "print(\"Image:\")\n",
-    "display(im)"
+    "text = \"This is a test document.\""
    ]
   },
   {
@@ -106,6 +118,40 @@
     "print(doc_result)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "338ea747-040e-4ed4-8ddf-9b2285987885",
+   "metadata": {},
+   "source": [
+    "## Embed images and queries with Jina CLIP through JinaAI API"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "575b5867-59fb-4fd1-911b-afee2eaca088",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "multimodal_embeddings = JinaEmbeddings(jina_api_key=\"jina_*\", model_name=\"jina-clip-v1\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a9b335f5-fa99-4931-95f6-7b187c0e2f30",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "image = \"https://avatars.githubusercontent.com/u/126733545?v=4\"\n",
+    "\n",
+    "description = \"Logo of a parrot and a chain on green background\"\n",
+    "\n",
+    "im = Image.open(requests.get(image, stream=True).raw)\n",
+    "print(\"Image:\")\n",
+    "display(im)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -113,7 +159,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "image_result = image_embeddings.embed_images([image])"
+    "image_result = multimodal_embeddings.embed_images([image])"
    ]
   },
   {
@@ -133,7 +179,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "description_result = image_embeddings.embed_documents([description])"
+    "description_result = multimodal_embeddings.embed_documents([description])"
    ]
   },
   {
@@ -167,14 +213,6 @@
    "source": [
     "print(cosine_similarity)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7f280807-a02b-4d4e-8ebd-01be33117999",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -193,7 +231,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.2"
+   "version": "3.9.13"
   }
  },
  "nbformat": 4,

docs/docs/integrations/toolkits/ainetwork.ipynb

@@ -26,7 +26,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  ain-py"
+    "%pip install --upgrade --quiet  ain-py langchain-community"
    ]
   },
   {

docs/docs/integrations/toolkits/airbyte_structured_qa.ipynb

@@ -11,6 +11,15 @@
     "Vectorstores often have a hard time answering questions that requires computing, grouping and filtering structured data so the high level idea is to use a `pandas` dataframe to help with these types of questions. "
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-community"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",

docs/docs/integrations/toolkits/amadeus.ipynb

@@ -24,6 +24,15 @@
     "%pip install --upgrade --quiet  amadeus > /dev/null"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-community"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},