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

# LangChain SDK

> Use LangChain with Keywords AI

<Note> This integration is for the **Keywords AI gateway**. </Note>

## Overview

LangChain provides a powerful framework for building applications with language models. You can seamlessly integrate Keywords AI with LangChain's `ChatOpenAI` LLM with minimal code changes.

## Quickstart

### Step 1: Install LangChain

<CodeGroup>
  ```bash Python theme={"system"}
  pip install langchain-openai
  ```

  ```bash TypeScript theme={"system"}
  npm install @langchain/openai langchain
  ```
</CodeGroup>

### Step 2: Initialize LangChain with Keywords AI

<CodeGroup>
  ```python Python theme={"system"}
  from langchain_openai import ChatOpenAI

  llm = ChatOpenAI(
      base_url="https://api.keywordsai.co/api/",
      api_key="<Your Keywords AI API Key>",
      model="gpt-3.5-turbo",
      streaming=True,
  )
  ```

  ```typescript TypeScript theme={"system"}
  import { ChatOpenAI } from "@langchain/openai";

  const llm = new ChatOpenAI({
      configuration: {
          baseURL: "https://api.keywordsai.co/api/",
      },
      openAIApiKey: "<Your Keywords AI API Key>",
      modelName: "gpt-3.5-turbo",
      streaming: true,
  });
  ```
</CodeGroup>

### Step 3: Make Your First Request

<CodeGroup>
  ```python Python theme={"system"}
  response = llm.invoke("Hello, world!")
  print(response)
  ```

  ```typescript TypeScript theme={"system"}
  const response = await llm.invoke("Hello, world!");
  console.log(response);
  ```
</CodeGroup>

## Switch models

<CodeGroup>
  ```python Python theme={"system"}
  # OpenAI GPT models
  model = "gpt-4o"
  # model = "claude-3-5-sonnet-20241022"
  # model = "gemini-1.5-pro"

  llm = ChatOpenAI(
      base_url="https://api.keywordsai.co/api/",
      api_key="<Your Keywords AI API Key>",
      model=model,
  )
  ```

  ```typescript TypeScript theme={"system"}
  // OpenAI GPT models
  let model = "gpt-4o";
  // model = "claude-3-5-sonnet-20241022";
  // model = "gemini-1.5-pro";

  const llm = new ChatOpenAI({
      configuration: {
          baseURL: "https://api.keywordsai.co/api/",
      },
      openAIApiKey: "<Your Keywords AI API Key>",
      modelName: model,
  });
  ```
</CodeGroup>

<Note>
  See the [full model list](https://platform.keywordsai.co/platform/models) for all available models.
</Note>

## Supported parameters

### OpenAI parameters

We support all the [OpenAI parameters](/api-endpoints/develop/gateway/chat-completions#openai-compatible-parameters). You can pass them directly in the LangChain configuration.

<CodeGroup>
  ```python Python theme={"system"}
  llm = ChatOpenAI(
      base_url="https://api.keywordsai.co/api/",
      api_key="<Your Keywords AI API Key>",
      model="gpt-4o-mini",
      temperature=0.7,          # Control randomness
      max_tokens=1000,          # Limit response length
      streaming=True,           # Enable streaming
  )
  ```

  ```typescript TypeScript theme={"system"}
  const llm = new ChatOpenAI({
      configuration: {
          baseURL: "https://api.keywordsai.co/api/",
      },
      openAIApiKey: "<Your Keywords AI API Key>",
      modelName: "gpt-4o-mini",
      temperature: 0.7,         // Control randomness
      maxTokens: 1000,          // Limit response length
      streaming: true,          // Enable streaming
  });
  ```
</CodeGroup>

### Keywords AI Parameters

[Keywords AI parameters](/api-endpoints/develop/gateway/chat-completions#keywords-ai-parameters) can be passed using `extra_body` for better handling and customization.

<CodeGroup>
  ```python Python theme={"system"}
  llm = ChatOpenAI(
      base_url="https://api.keywordsai.co/api/",
      api_key="<Your Keywords AI API Key>",
      model="gpt-4o-mini",
      extra_body={
          "customer_identifier": "user_123",           # Track specific users
          "fallback_models": ["gpt-3.5-turbo"],       # Automatic fallbacks
          "metadata": {"session_id": "abc123"},        # Custom metadata
          "thread_identifier": "conversation_456",     # Group related messages
          "group_identifier": "team_alpha",           # Organize by groups
      }
  )
  ```

  ```typescript TypeScript theme={"system"}
  const llm = new ChatOpenAI({
      configuration: {
          baseURL: "https://api.keywordsai.co/api/",
      },
      openAIApiKey: "<Your Keywords AI API Key>",
      modelName: "gpt-4o-mini",
      modelKwargs: {
          extra_body: {
              customer_identifier: "user_123",           // Track specific users
              fallback_models: ["gpt-3.5-turbo"],       // Automatic fallbacks
              metadata: { session_id: "abc123" },        // Custom metadata
              thread_identifier: "conversation_456",     // Group related messages
              group_identifier: "team_alpha",           // Organize by groups
          }
      }
  });
  ```
</CodeGroup>

## Advanced Usage (optional)

### Using with Chains

<CodeGroup>
  ```python Python theme={"system"}
  from langchain.chains import ConversationChain
  from langchain_openai import ChatOpenAI

  llm = ChatOpenAI(
      base_url="https://api.keywordsai.co/api/",
      api_key="<Your Keywords AI API Key>",
      model="gpt-4o-mini",
  )

  chain = ConversationChain(llm=llm)
  response = chain.run("Tell me about artificial intelligence")
  print(response)
  ```

  ```typescript TypeScript theme={"system"}
  import { ConversationChain } from "langchain/chains";
  import { ChatOpenAI } from "@langchain/openai";

  const llm = new ChatOpenAI({
      configuration: {
          baseURL: "https://api.keywordsai.co/api/",
      },
      openAIApiKey: "<Your Keywords AI API Key>",
      modelName: "gpt-4o-mini",
  });

  const chain = new ConversationChain({ llm });

  async function main() {
      const response = await chain.call({
          input: "Tell me about artificial intelligence"
      });
      console.log(response);
  }

  main();
  ```
</CodeGroup>

<Card title="View your analytics" href="https://platform.keywordsai.co/platform/dashboard">
  Access your Keywords AI dashboard to see detailed analytics
</Card>

## Next Steps

<CardGroup cols={2}>
  <Card title="User Management" href="/documentation/products/users/customer-identifier">
    Track user behavior and patterns
  </Card>

  <Card title="Prompt Management" href="/documentation/products/prompt_management/quickstart">
    Manage and version your prompts
  </Card>
</CardGroup>