> ## Documentation Index
> Fetch the complete documentation index at: https://www.truefoundry.com/llms.txt
> Use this file to discover all available pages before exploring further.

# LangChain

> Learn how to use langchain with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples.

This guide provides instructions for integrating [LangChain](https://langchain.com/) with the TrueFoundry AI Gateway.

## What is LangChain?

LangChain is a framework for developing applications powered by large language models (LLMs). It provides a comprehensive suite of tools and integrations that streamline the entire lifecycle of LLM applications, from development to deployment and monitoring.

### Key Features of LangChain

* **[Modular Components](https://python.langchain.com/docs/introduction/)**: Offers a range of building blocks including chains, agents, prompt templates, and memory modules that can be composed together to create complex LLM applications
* **[Extensive Integrations](https://python.langchain.com/docs/integrations/providers/)**: Supports integrations with various LLM providers, embedding models, vector stores, and external tools, facilitating seamless connectivity within the AI ecosystem
* **[Production-Ready Tools](https://python.langchain.com/docs/introduction/)**: Includes LangGraph for building stateful agents and LangSmith for monitoring and evaluating applications, ensuring robust deployment and maintenance of LLM-powered solutions

## Quickstart Guide

TrueFoundry is compatible with the OpenAI signature, so you can connect to TrueFoundry's unified LLM gateway through the `ChatOpenAI` interface.

### Installation & Setup

1. Sign up for a [TrueFoundry account](https://www.truefoundry.com/register)
2. Follow the steps in our [Gateway Quick Start Guide](https://docs.truefoundry.com/gateway/quick-start)

You will get your base URL and model name directly from the unified code snippet:

<Frame>
  <img src="https://mintcdn.com/truefoundry/n3EuZuJ0K8wBFp1G/images/new-code-snippet.png?fit=max&auto=format&n=n3EuZuJ0K8wBFp1G&q=85&s=3634c2dc8c3565fd77ab896d3fd07ed9" alt="TrueFoundry playground showing unified code snippet with base URL and model name" width="2940" height="1664" data-path="images/new-code-snippet.png" />
</Frame>

* Set the `base_url` to your TrueFoundry endpoint
* Use TrueFoundry model names in the format `provider-main/model-name`

### Installation

```bash lines theme={"dark"}
pip install langchain-openai
```

### Basic Setup

Connect to TrueFoundry by updating the `ChatOpenAI` model in LangChain:

```python lines theme={"dark"}
from langchain_openai import ChatOpenAI

TRUEFOUNDRY_PAT = "..."  # Your TrueFoundry Personal Access Token
TRUEFOUNDRY_BASE_URL = "{GATEWAY_BASE_URL}"

llm = ChatOpenAI(
    api_key=TRUEFOUNDRY_PAT,
    base_url=TRUEFOUNDRY_BASE_URL,
    model="openai-main/gpt-4o" #similarly you can call any model from any model provider like anthropic, gemini
)

llm.invoke("What is the meaning of life, universe and everything?")
```

The request is routed through your TrueFoundry gateway to the specified model provider. TrueFoundry automatically handles authentication, routing, and logging.

### Advanced Example with LangGraph

```python lines theme={"dark"}
from langgraph.graph import StateGraph, MessagesState
from langchain_core.messages import HumanMessage

# Build workflow
workflow = StateGraph(MessagesState)
workflow.add_node("agent", call_model)
workflow.set_entry_point("agent")
workflow.set_finish_point("agent")

app = workflow.compile()

# Run agent through TrueFoundry
result = app.invoke({"messages": [HumanMessage(content="Hello!")]})
```

### Observability and Governance

Monitor your LangChain applications through TrueFoundry's metrics tab:

<img src="https://mintcdn.com/truefoundry/yRoKH_fkKi2nPtuV/images/gateway-metrics.png?fit=max&auto=format&n=yRoKH_fkKi2nPtuV&q=85&s=5a442952b4a398bcf6ab277d2392ca2c" alt="TrueFoundry metrics" width="3840" height="1984" data-path="images/gateway-metrics.png" />

With TrueFoundry's AI Gateway, you can monitor and analyze:

* **Performance Metrics**: Track key latency metrics like Request Latency, Time to First Token (TTFS), and Inter-Token Latency (ITL) with P99, P90, and P50 percentiles
* **Cost and Token Usage**: Gain visibility into your application's costs with detailed breakdowns of input/output tokens and the associated expenses for each model
* **Usage Patterns**: Understand how your application is being used with detailed analytics on user activity, model distribution, and team-based usage
* **Rate Limiting and Virtual Models**: Set up rate limiting and configure [Virtual Models](/docs/ai-gateway/virtual-model) for intelligent routing and fallback across your models