docs: relocate the langchain and langgraph integration documents

docs/export-observability-data/basic-guide.md

@@ -22,7 +22,7 @@ Good starting points:
 - [Basic Guide: Adding Scopes and Marks](../instrument-applications/adding-scopes-and-marks.md)
 - [Basic Guide: Instrument a Tool Call](../instrument-applications/instrument-tool-call.md)
 - [Basic Guide: Instrument an LLM Call](../instrument-applications/instrument-llm-call.md)
-- [Python Quick Start](../getting-started/python.md)
+- [Python Quick Start](../getting-started/python/index.md)
 - [Node.js Quick Start](../getting-started/nodejs.md)
 - [Rust Quick Start](../getting-started/rust.md)
 

docs/getting-started/python.md → docs/getting-started/python/index.md

@@ -5,8 +5,9 @@ SPDX-License-Identifier: Apache-2.0
 
 # Python Quick Start
 
-This quick start shows the smallest Python workflow that emits scope, tool, and LLM
-events.
+This quick start shows the smallest Python workflow that emits scope, tool, and LLM events.
+
+[LangChain](https://www.langchain.com/langchain) and [LangGraph](https://www.langchain.com/langgraph) users should start with the [LangChain integration](langchain.md) or [LangGraph integration](langgraph.md) guides for the best experience in those frameworks.
 
 ## Choose an Install Path
 
@@ -126,6 +127,20 @@ These modules are the main Python APIs to use from applications and integrations
 
 Use these links to continue from the quick start into the core runtime concepts.
 
-- [Scopes](../about/concepts/scopes.md)
-- [Middleware](../about/concepts/middleware.md)
-- [Plugins](../about/concepts/plugins.md)
+- [LangChain integration](langchain.md)
+- [LangGraph integration](langgraph.md)
+- [Scopes](../../about/concepts/scopes.md)
+- [Middleware](../../about/concepts/middleware.md)
+- [Plugins](../../about/concepts/plugins.md)
+
+## Framework Integrations
+
+Use these guides when your Python application already uses LangChain or
+LangGraph and you want NeMo Flow observability through their public APIs.
+
+```{toctree}
+:maxdepth: 1
+
+LangChain Integration <langchain>
+LangGraph Integration <langgraph>
+```

python/nemo_flow/integrations/langchain/README.md → docs/getting-started/python/langchain.md

@@ -5,18 +5,59 @@ SPDX-License-Identifier: Apache-2.0
 
 # NeMo Flow LangChain Integration
 
-This directory contains the `nemo_flow.integrations.langchain` package which provides observability integration for LangChain.
+Use the `nemo_flow.integrations.langchain` package to add NeMo Flow
+observability to [LangChain](https://www.langchain.com/langchain) agents.
 
-The intent of this project is to enable as much NeMo Flow functionality as possible using public LangChain APIs without requiring changes to LangChain itself.
+## Setup
 
-For an alternate approach refer to [the patch-based integration in `third_party/langchain`](../../../../third_party/README-langchain.md).
+Install the LangChain integration extra in your application environment.
 
-## Setup
+::::{tab-set}
+:sync-group: install-tool
+
+:::{tab-item} uv
+:selected:
+:sync: uv
+
+```bash
+uv add "nemo-flow[langchain]"
+```
+:::
+
+:::{tab-item} pip
+:sync: pip
+
+```bash
+pip install "nemo-flow[langchain]"
+```
+:::
+
+::::
+
+The example below uses the NVIDIA LangChain provider. Install that provider
+extra too if you want to run the example as written:
+
+::::{tab-set}
+:sync-group: install-tool
+
+:::{tab-item} uv
+:selected:
+:sync: uv
+
+```bash
+uv add "nemo-flow[langchain,langchain-nvidia]"
+```
+:::
+
+:::{tab-item} pip
+:sync: pip
 
 ```bash
-uv sync --all-groups --all-extras
-just build-python
+pip install "nemo-flow[langchain,langchain-nvidia]"
 ```
+:::
+
+::::
 
 ## Usage Example
 
@@ -28,11 +69,13 @@ from langchain.agents import create_agent
 from langchain_core.tools import tool
 from nemo_flow.integrations.langchain import NemoFlowCallbackHandler, NemoFlowMiddleware
 
+
 @tool
 def get_weather(location: str) -> str:
     """Get the current weather for a location."""
     return f"The weather in {location} is sunny and 72 degrees."
 
+
 agent = create_agent(
     model="nvidia:nvidia/nemotron-3-nano-30b-a3b",
     tools=[get_weather],
@@ -50,16 +93,14 @@ input_payload = {
 }
 
 with nemo_flow.scope.scope("langchain-request", nemo_flow.ScopeType.Agent):
-    result = asyncio.run(agent.ainvoke(input_payload, config={"callbacks": [NemoFlowCallbackHandler()]}))
+    result = asyncio.run(
+        agent.ainvoke(input_payload, config={"callbacks": [NemoFlowCallbackHandler()]})
+    )
 
 final_message = result["messages"][-1]
 print(f"Final response: {final_message.content}")
 ```
 
-## Validation
+## Observability
 
-Run tests for the LangChain integration package to validate the integration:
-
-```bash
-uv run pytest python/tests/integrations/langchain
-```
+Refer to [Export Observability Data](../../export-observability-data/about.md) for details on exporting NeMo Flow observability data to third-party systems.

python/nemo_flow/integrations/langgraph/README.md → docs/getting-started/python/langgraph.md

@@ -5,20 +5,37 @@ SPDX-License-Identifier: Apache-2.0
 
 # NeMo Flow LangGraph Integration
 
-This directory contains the `nemo_flow.integrations.langgraph` package, which provides public-API LangGraph integration for NeMo Flow.
+Use the `nemo_flow.integrations.langgraph` package to add NeMo Flow
+observability to [LangGraph](https://www.langchain.com/langgraph) workflows through public LangGraph APIs.
 
-The integration builds on `nemo_flow.integrations.langchain`: `NemoFlowCallbackHandler` inherits the LangChain callback handler, and `NemoFlowMiddleware` is re-exported for LangChain agents used inside LangGraph workflows.
+## Setup
 
-For an alternate approach refer to [the patch-based integration in `third_party/langchain`](../../../../third_party/README-langgraph.md).
+Install the LangGraph integration extra in your application environment.
 
-## Setup
+::::{tab-set}
+:sync-group: install-tool
+
+:::{tab-item} uv
+:selected:
+:sync: uv
 
 ```bash
-uv sync --all-groups --extra langgraph
-just build-python
+uv add "nemo-flow[langgraph]"
 ```
+:::
 
-Installing the `langgraph` extra also installs the LangChain integration dependencies.
+:::{tab-item} pip
+:sync: pip
+
+```bash
+pip install "nemo-flow[langgraph]"
+```
+:::
+
+::::
+
+Installing the `langgraph` extra also installs the LangChain integration
+dependencies.
 
 ## Usage Example
 
@@ -54,7 +71,9 @@ with nemo_flow.scope.scope("langgraph-request", nemo_flow.ScopeType.Agent):
 print(result)
 ```
 
-For LangChain agents inside a LangGraph workflow, use `NemoFlowMiddleware` from this package the same way as the LangChain integration and pass the LangGraph `config` into the nested agent call:
+For LangChain agents inside a LangGraph workflow, use `NemoFlowMiddleware` from
+this package the same way as the LangChain integration and pass the LangGraph
+`config` into the nested agent call:
 
 ```python
 from langchain.agents import create_agent
@@ -72,8 +91,31 @@ def agent_node(state: dict, config: RunnableConfig) -> dict:
     return agent.invoke({"messages": state["messages"]}, config=config)
 ```
 
-## Validation
+Install the NVIDIA LangChain provider if you want to run the nested agent
+example as written:
+
+::::{tab-set}
+:sync-group: install-tool
+
+:::{tab-item} uv
+:selected:
+:sync: uv
+
+```bash
+uv add "nemo-flow[langgraph,langchain-nvidia]"
+```
+:::
+
+:::{tab-item} pip
+:sync: pip
 
 ```bash
-uv run pytest python/tests/integrations/langgraph
+pip install "nemo-flow[langgraph,langchain-nvidia]"
 ```
+:::
+
+::::
+
+## Observability
+
+Refer to [Export Observability Data](../../export-observability-data/about.md) for details on exporting NeMo Flow observability data to third-party systems.

docs/getting-started/quick-start.md

@@ -10,7 +10,7 @@ Choose the Quick Start guide for the primary binding that you plan to use.
 ```{toctree}
 :maxdepth: 1
 
-Python Quick Start <python>
+Python Quick Start <python/index>
 Node.js Quick Start <nodejs>
 Rust Quick Start <rust>
 ```

docs/instrument-applications/adding-scopes-and-marks.md

@@ -17,7 +17,7 @@ Scopes give emitted work ownership. Marks record point-in-time checkpoints insid
 
 Complete one binding Quick Start guide first:
 
-- [Python Quick Start](../getting-started/python.md)
+- [Python Quick Start](../getting-started/python/index.md)
 - [Node.js Quick Start](../getting-started/nodejs.md)
 - [Rust Quick Start](../getting-started/rust.md)
 

docs/instrument-applications/instrument-llm-call.md

@@ -22,7 +22,7 @@ You will wrap one existing LLM provider invocation with the managed LLM executio
 
 Complete one binding Quick Start guide first:
 
-- [Python Quick Start](../getting-started/python.md)
+- [Python Quick Start](../getting-started/python/index.md)
 - [Node.js Quick Start](../getting-started/nodejs.md)
 - [Rust Quick Start](../getting-started/rust.md)
 

docs/instrument-applications/instrument-tool-call.md

@@ -21,7 +21,7 @@ You will wrap one existing tool callback with the managed tool execution API. Th
 
 Complete one binding Quick Start guide first:
 
-- [Python Quick Start](../getting-started/python.md)
+- [Python Quick Start](../getting-started/python/index.md)
 - [Node.js Quick Start](../getting-started/nodejs.md)
 - [Rust Quick Start](../getting-started/rust.md)
 

docs/integrate-frameworks/about.md

@@ -29,6 +29,10 @@ Use these signals to decide whether this documentation path matches your current
 - Are building or reviewing third-party integration patches
 
 If you own the application call sites directly, use [Instrument Applications](../instrument-applications/about.md) first.
+If your application uses [LangChain](https://www.langchain.com/langchain) or
+[LangGraph](https://www.langchain.com/langgraph), start with
+[LangChain Integration](../getting-started/python/langchain.md) or
+[LangGraph Integration](../getting-started/python/langgraph.md).
 
 ## Guides
 

docs/reference/api/python/index.md

@@ -64,7 +64,7 @@ nemo_flow <_generated/nemo_flow/index>
 Use these links to continue from the API reference into task-focused guides.
 
 - [Quick Start](../../../getting-started/quick-start.md)
-- [Python Quick Start](../../../getting-started/python.md)
+- [Python Quick Start](../../../getting-started/python/index.md)
 - [Scopes](../../../about/concepts/scopes.md)
 - [Middleware](../../../about/concepts/middleware.md)
 - [Subscribers](../../../about/concepts/subscribers.md)

docs/resources/support-and-faqs.md

@@ -120,7 +120,7 @@ Start with Python, Node.js, or Rust. These are the primary documented bindings
 and have the broadest getting-started, concept, guide, and generated API
 coverage.
 
-- Use [Python Quick Start](../getting-started/python.md) when you are adding
+- Use [Python Quick Start](../getting-started/python/index.md) when you are adding
   NeMo Flow to Python application code or agent harnesses.
 - Use [Node.js Quick Start](../getting-started/nodejs.md) when your application,
   framework integration, or plugin-facing code runs in Node.js.

python/nemo_flow/README.md

@@ -62,6 +62,53 @@ If you are not using `uv`, install it with `pip`:
 pip install nemo-flow
 ```
 
+### Optional Dependencies
+
+#### LangChain Integration
+
+[LangChain](https://www.langchain.com/langchain) integration is available with the `langchain` extra:
+
+```bash
+# With uv
+uv add "nemo-flow[langchain]"
+
+# With pip
+pip install "nemo-flow[langchain]"
+```
+
+#### LangGraph Integration
+
+[LangGraph](https://www.langchain.com/langgraph) integration is available with the `langgraph` extra, this builds upon and includes the `langchain` extra as well.
+
+```bash
+# With uv
+uv add "nemo-flow[langgraph]"
+
+# With pip
+pip install "nemo-flow[langgraph]"
+```
+
+#### LangChain NVIDIA Integration
+
+The [LangChain NVIDIA](https://github.com/langchain-ai/langchain-nvidia) extra builds upon the `langchain` extra adding a compatible version of the `langchain-nvidia-ai-endpoints` package.
+
+```bash
+# With uv
+uv add "nemo-flow[langchain-nvidia]"
+
+# With pip
+pip install "nemo-flow[langchain-nvidia]"
+```
+
+To install this along with the `langgraph` extra, use:
+
+```bash
+# With uv
+uv add nemo-flow[langgraph,langchain-nvidia]
+# With pip
+pip install nemo-flow[langgraph,langchain-nvidia]
+```
+
 ## Getting Started
 
 Register a subscriber, create a scope, and emit a mark event:
@@ -98,6 +145,11 @@ The public package modules are:
 - `nemo_flow.typed`
 - `nemo_flow.codecs`
 
+### Integrations
+
+- `nemo_flow.integrations.langchain`
+- `nemo_flow.integrations.langgraph`
+
 The compiled extension is exposed as `nemo_flow._native`.
 
 ## Documentation