> ## Documentation Index
> Fetch the complete documentation index at: https://wb-21fd5541-feature-automate-reference-docs-generation.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Track LLM inputs & outputs

> Follow these steps to track your first call

<Info>
  Try the new W\&B Inference service free. It gives you access to AI models through an API and the Weave Playground.

  * [Developer docs](./guides/integrations/inference)
  * [Product page](https://wandb.ai/site/inference)
</Info>

Follow these steps to track your first call. You can also <a className="inline-flex items-center" target="_blank" href="http://wandb.me/weave_colab"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" /></a>

## 1. Install Weave and get your API key

**Install weave**

First, install the weave library:

<CodeGroup>
  ```bash Python
  pip install weave
  ```

  ```bash TypeScript
  pnpm install weave
  ```
</CodeGroup>

**Get your API key**

Create a W\&B account at [https://wandb.ai](https://wandb.ai). Then copy your API key from [https://wandb.ai/authorize](https://wandb.ai/authorize).

## 2. Log a trace to a new project

Follow these steps to track your first project:

* Import the `weave` library
* Call `weave.init('project-name')` to start tracking
  * The system asks for your API key if you haven't logged in yet
  * To log to a team, use `team-name/project-name`
  * Set the `WANDB_API_KEY` environment variable to skip the login prompt
* Add `@weave.op()` to the functions you want to track

*This example uses OpenAI. You need an OpenAI [API key](https://platform.openai.com/docs/quickstart/step-2-setup-your-api-key).*

<CodeGroup>
  ```python Python
  import weave
  from openai import OpenAI

  client = OpenAI()

  # Weave tracks the inputs, outputs and code of this function
  @weave.op()
  def extract_dinos(sentence):
      response = client.chat.completions.create(
          model="gpt-4o",
          messages=[
              {
                  "role": "system",
                  "content": """Extract dinosaurs from the text. Return JSON with:
  - dinosaurs: list of dinosaurs
  - name: scientific name  
  - common_name: nickname
  - diet: herbivore or carnivore."""
              },
              {
                  "role": "user",
                  "content": sentence
              }
          ],
          response_format={ "type": "json_object" }
      )
      return response.choices[0].message.content


  # Start the weave project
  weave.init('jurassic-park')

  sentence = """I saw a T. rex chase a Triceratops. 
  The T. rex eats meat. The Triceratops eats plants.
  A Brachiosaurus ate leaves from tall trees nearby."""

  result = extract_dinos(sentence)
  print(result)
  ```

  ```typescript TypeScript
  import OpenAI from 'openai';
  import * as weave from 'weave';

  const openai = new OpenAI();

  async function extractDinos(input) {
    const response = await openai.chat.completions.create({
      model: 'gpt-4o',
      messages: [
        {
          role: 'user',
          content: `Extract dinosaurs from this text. Return JSON with name, common_name, and diet: ${input}`,
        },
      ],
    });
    return response.choices[0].message.content;
  }

  const extractDinosOp = weave.op(extractDinos);

  async function main() {
    await weave.init('examples');
    const result = await extractDinosOp(
      'I saw a T. rex chase a Triceratops. The T. rex eats meat. The Triceratops eats plants. A Brachiosaurus ate leaves from tall trees nearby.'
    );
    console.log(result);
  }

  main();
  ```
</CodeGroup>

When you call `extract_dinos`, Weave shows a link to view your trace.

## 3. Automatic AI library logging

Weave tracks calls to many AI services:

* OpenAI
* Anthropic
* [Many more AI libraries](./guides/integrations/index)

Weave logs:

* AI model info
* Token usage
* Cost

To track other AI tools, wrap them with `@weave.op()`.

## 4. See traces in your project

Great job. Now Weave captures data every time you call your function. It also tracks code changes.

![Weave Trace Outputs 1](https://mintlify.s3.us-west-1.amazonaws.com/wb-21fd5541-feature-automate-reference-docs-generation/images/tutorial_trace_1.png)

## Next steps

* Learn to [track data flow](./tutorial-tracing_2) in your app
* Read about [Tracing](./guides/tracking/tracing) to see how Weave works
* Check out [Integrations](./guides/integrations/index) for all AI providers
* Try the [Playground](./guides/tools/playground) to test different models