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

# Vercel AI Integration

> How to integrate Vercel AI with Lytix

With a couple of lines of code, you can start using Lytix to manage your evaluation and usage via the Vercel AI SDK.

<Info>
  **Prerequisite** First create a lytix account [here](https://lab.lytix.co/home/login)
</Info>

# Anthropic

### Step 1: Install the SDK

<CodeGroup>
  ```sh Typescript
  npm i @ai-sdk/anthropic ai
  ```
</CodeGroup>

### Step 2: Update You Client

<CodeGroup>
  ```js Typescript
  import { createAnthropic } from "@ai-sdk/anthropic";

  const anthropic = createAnthropic({
      baseURL: "https://api.lytix.co/proxy/v1/anthropic",
      apiKey: "$LYTIX_API_KEY",
      headers: {
        anthropicApiKey: "$ANTHROPIC_API_KEY",
      },
  });
  ```
</CodeGroup>

<Info>
  **🇪🇺 Note** You will need to use `https://eu.api.lytix.co/proxy/v1/anthropic` if you are in the EU region.
</Info>

### Step 3: Start Querying

<CodeGroup>
  ```js Typescript
  import { generateText } from "ai";

  const response = await generateText({
      // Choose your model here
      model: anthropic("claude-3-5-sonnet-20240620"),

      /**
       * Either
       */
      prompt: "What is the meaning of life?",
      system: "Always respond with a JSON object",

      /**
       * Or
       */
      messages: [
          { role: "user", content: "What is the meaning of life?" },
          { role: "system", content: "Always respond with a JSON object" },
      ],
      temperature: 0.5,
      maxTokens: 1000,
      headers: {
          // ...see extra headers below
      },
  });
  ```
</CodeGroup>

# OpenAI

### Step 1: Install the SDK

<CodeGroup>
  ```sh Typescript
  npm i @ai-sdk/openai ai
  ```
</CodeGroup>

### Step 2: Update You Client

<CodeGroup>
  ```js Typescript
  import { createOpenAI } from "@ai-sdk/openai";

  const openai = createOpenAI({
      baseURL: "https://api.lytix.co/proxy/v1/openai",
      apiKey: "$LYTIX_API_KEY",
      headers: {
        openaiKey: "$OPENAI_API_KEY",
      },
  });
  ```
</CodeGroup>

<Info>
  **🇪🇺 Note** You will need to use `https://eu.api.lytix.co/proxy/v1/openai` if you are in the EU region.
</Info>

### Step 3: Start Querying

<CodeGroup>
  ```js Typescript
  import { generateText } from "ai";

  const response = await generateText({
      // Choose your model here
      model: openai("gpt-4o-mini"),

      /**
       * Either
       */
      prompt: "What is the meaning of life?",
      system: "Always respond with a JSON object",

      /**
       * Or
       */
      messages: [
          { role: "user", content: "What is the meaning of life?" },
          { role: "system", content: "Always respond with a JSON object" },
      ],
      temperature: 0.5,
      maxTokens: 1000,
      headers: {
          // ...see extra headers below
      },
  });
  ```
</CodeGroup>

# Groq

### Step 1: Install the SDK

<CodeGroup>
  ```sh Typescript
  npm i @ai-sdk/xai ai
  ```
</CodeGroup>

### Step 2: Update You Client

<CodeGroup>
  ```js Typescript
  import { createXai } from "@ai-sdk/xai";

  const groq = createXai({
      baseURL: "https://api.lytix.co/proxy/v2/groq",
      apiKey: "$LYTIX_API_KEY",
      headers: {
        groqApiKey: "$GROQ_API_KEY",
      },
  });
  ```
</CodeGroup>

<Info>
  **🇪🇺 Note** You will need to use `https://eu.api.lytix.co/proxy/v2/groq` if you are in the EU region.
</Info>

### Step 3: Start Querying

<CodeGroup>
  ```js Typescript
  import { generateText } from "ai";

  const response = await generateText({
      // Choose your model here
      model: xai("gemma2-9b-it"),

      /**
       * Either
       */
      prompt: "What is the meaning of life?",
      system: "Always respond with a JSON object",

      /**
       * Or
       */
      messages: [
          { role: "user", content: "What is the meaning of life?" },
          { role: "system", content: "Always respond with a JSON object" },
      ],
      temperature: 0.5,
      maxTokens: 1000,
      headers: {
          // ...see extra headers below
      },
  });
  ```
</CodeGroup>

# Extra Headers

When querying you can pass the following headers to the client:

* `workflowName` - The name of the workflow to create (see [workflow setup](/Workflows/workflows-setup) for more information)
* `userId` - The id of the user
* `sessionId` - The id of the session to group calls together
* `cacheTTL` - The number of seconds to cache the response for. Please see [caching](/Caching/caching-setup) to setup your cache.