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

# OpenAI

> Integrate OpenAI with Weave for tracing, evaluation, and monitoring

<a target="_blank" href="https://colab.research.google.com/github/wandb/examples/blob/master/weave/docs/quickstart_openai.ipynb" aria-label="Open in Google Colab">
  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" />
</a>

<Note>
  Do you want to experiment with OpenAI models on Weave without any set up? Try the [LLM Playground](../tools/playground).
</Note>

## Tracing

It's important to store traces of LLM applications in a central database, both during development and in production. You'll use these traces for debugging and to help build a dataset of tricky examples to evaluate against while improving your application.

Weave can automatically capture traces for the [openai python library](https://developers.openai.com/api/docs/libraries).

Start capturing by calling `weave.init(<project-name>)` with a project name of your choice. OpenAI will be automatically patched regardless of when you import it.

If you don't specify a W\&B team when you call `weave.init()`, your default entity is used. To find or update your default entity, refer to [User Settings](https://docs.wandb.ai/platform/app/settings-page/user-settings/#default-team) in the W\&B Models documentation.

**Automatic Patching**

Weave automatically patches OpenAI whether imported before or after `weave.init()`:

<CodeGroup>
  ```python Python lines {4} theme={null}
  from openai import OpenAI
  import weave

  weave.init('emoji-bot')  # OpenAI is automatically patched!

  client = OpenAI()
  response = client.chat.completions.create(
    model="gpt-4",
    messages=[
      {
        "role": "system",
        "content": "You are AGI. You will be provided with a message, and your task is to respond using emojis only."
      },
      {
        "role": "user",
        "content": "How are you?"
      }
    ]
  )
  ```

  ```typescript TypeScript theme={null}
  import { OpenAI } from 'openai';
  import { wrapOpenAI } from '@wandb/weave';

  const openai = wrapOpenAI(new OpenAI());

  // This will now trace all calls to OpenAI
  openai.chat.completions.create(
    {
      model: "gpt-4",
      messages: [
        {
          role: "system",
          content: "You are AGI. You will be provided with a message, and your task is to respond using emojis only."
        },
        {
          role: "user",
          content: "How are you?"
        }
      ]
    }
  );
  ```
</CodeGroup>

**Explicit Patching (Optional)**

You can still explicitly patch if you want fine-grained control:

```python lines {3,4} theme={null}
import weave

weave.init('emoji-bot')
weave.integrations.patch_openai()  # Enable OpenAI tracing

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
  model="gpt-4",
  messages=[
    {"role": "user", "content": "Make me a emoji"}
  ]
)
```

[View a live trace](https://wandb.ai/capecape/emoji-bot/weave/calls/01928a78-6d8a-7e20-9b8c-0cbc8318a0c8)

<Tip>
  We capture the function calling tools for [OpenAI Functions](https://platform.openai.com/docs/guides/function-calling) and [OpenAI Assistants](https://platform.openai.com/docs/assistants/overview) as well.
</Tip>

## Structured outputs

Weave also supports structured outputs with OpenAI. This is useful for ensuring that your LLM responses follow a specific format.

<CodeGroup>
  ```python Python theme={null}
  from openai import OpenAI
  from pydantic import BaseModel
  import weave

  class UserDetail(BaseModel):
      name: str
      age: int

  client = OpenAI()
  weave.init('extract-user-details')

  completion = client.beta.chat.completions.parse(
      model="gpt-4o-2024-08-06",
      messages=[
          {"role": "system", "content": "Extract the user details from the message."},
          {"role": "user", "content": "My name is David and I am 30 years old."},
      ],
      response_format=UserDetail,
  )

  user_detail = completion.choices[0].message.parsed
  print(user_detail)
  ```
</CodeGroup>

## Async support

Weave also supports async functions for OpenAI.

<CodeGroup>
  ```python Python theme={null}
  from openai import AsyncOpenAI
  import weave

  client = AsyncOpenAI()
  weave.init('async-emoji-bot')

  async def call_openai():
      response = await client.chat.completions.create(
          model="gpt-4",
          messages=[
              {
                  "role": "system", 
                  "content": "You are AGI. You will be provided with a message, and your task is to respond using emojis only."
              },
              {
                  "role": "user",
                  "content": "How are you?"
              }
          ]
      )
      return response

  # Call the async function
  result = await call_openai()
  ```
</CodeGroup>

## Streaming support

Weave also supports streaming responses from OpenAI.

<CodeGroup>
  ```python Python theme={null}
  from openai import OpenAI
  import weave

  client = OpenAI()
  weave.init('streaming-emoji-bot')

  response = client.chat.completions.create(
      model="gpt-4",
      messages=[
          {
              "role": "system", 
              "content": "You are AGI. You will be provided with a message, and your task is to respond using emojis only."
          },
          {
              "role": "user",
              "content": "How are you?"
          }
      ],
      stream=True
  )

  for chunk in response:
      print(chunk.choices[0].delta.content or "", end="")
  ```
</CodeGroup>

## Tracing function calls

Weave also traces function calls made by OpenAI when using tools.

<CodeGroup>
  ```python Python theme={null}
  from openai import OpenAI
  import weave

  client = OpenAI()
  weave.init('function-calling-bot')

  tools = [
      {
          "type": "function",
          "function": {
              "name": "get_weather",
              "description": "Get the weather in a given location",
              "parameters": {
                  "type": "object",
                  "properties": {
                      "location": {
                          "type": "string",
                          "description": "The location to get the weather for"
                      },
                      "unit": {
                          "type": "string",
                          "enum": ["celsius", "fahrenheit"],
                          "description": "The unit to return the temperature in"
                      }
                  },
                  "required": ["location"]
              }
          }
      }
  ]

  response = client.chat.completions.create(
      model="gpt-4",
      messages=[
          {
              "role": "user",
              "content": "What's the weather like in New York?"
          }
      ],
      tools=tools
  )

  print(response.choices[0].message.tool_calls)
  ```
</CodeGroup>

## Batch API

Weave also supports the OpenAI Batch API for processing multiple requests.

<CodeGroup>
  ```python Python theme={null}
  from openai import OpenAI
  import weave

  client = OpenAI()
  weave.init('batch-processing')

  # Create a batch file
  batch_input = [
      {
          "custom_id": "request-1",
          "method": "POST",
          "url": "/v1/chat/completions",
          "body": {
              "model": "gpt-4",
              "messages": [{"role": "user", "content": "Hello, how are you?"}]
          }
      },
      {
          "custom_id": "request-2", 
          "method": "POST",
          "url": "/v1/chat/completions",
          "body": {
              "model": "gpt-4",
              "messages": [{"role": "user", "content": "What's the weather like?"}]
          }
      }
  ]

  # Submit the batch
  batch = client.batches.create(
      input_file_id="your-file-id",
      endpoint="/v1/chat/completions",
      completion_window="24h"
  )

  # Retrieve the batch results
  completed_batch = client.batches.retrieve(batch.id)
  ```
</CodeGroup>

## Assistants API

Weave also supports the OpenAI Assistants API for building conversational AI applications.

<CodeGroup>
  ```python Python theme={null}
  from openai import OpenAI
  import weave

  client = OpenAI()
  weave.init('assistant-bot')

  # Create an assistant
  assistant = client.beta.assistants.create(
      name="Math Assistant",
      instructions="You are a personal math tutor. Answer questions about math.",
      model="gpt-4"
  )

  # Create a thread
  thread = client.beta.threads.create()

  # Add a message to the thread
  message = client.beta.threads.messages.create(
      thread_id=thread.id,
      role="user",
      content="What is 2+2?"
  )

  # Run the assistant
  run = client.beta.threads.runs.create(
      thread_id=thread.id,
      assistant_id=assistant.id
  )

  # Get the assistant's response
  messages = client.beta.threads.messages.list(thread_id=thread.id)
  ```
</CodeGroup>

## Cost tracking

Weave automatically tracks the cost of your OpenAI API calls. You can view the cost breakdown in the Weave UI.

<Note>
  Cost tracking is available for all OpenAI models and is calculated based on the latest OpenAI pricing.
</Note>

## Tracing custom functions

You can also trace custom functions that use OpenAI by using the `@weave.op` decorator.

<CodeGroup>
  ```python Python theme={null}
  from openai import OpenAI
  import weave

  client = OpenAI()
  weave.init('custom-function-bot')

  @weave.op
  def generate_response(prompt: str) -> str:
      response = client.chat.completions.create(
          model="gpt-4",
          messages=[
              {
                  "role": "user",
                  "content": prompt
              }
          ]
      )
      return response.choices[0].message.content

  # This function call will be traced
  result = generate_response("Hello, how are you?")
  ```
</CodeGroup>

## Next steps

Now that you've set up tracing for OpenAI, you can:

1. **View traces in the Weave UI**: Go to your Weave project to see traces of your OpenAI calls
2. **Create evaluations**: Use your traces to build evaluation datasets
3. **Monitor performance**: Track latency, costs, and other metrics
4. **Debug issues**: Use traces to understand what's happening in your LLM application

For more information on these topics, check out our [evaluation guide](../evaluation/scorers) and [monitoring guide](../tracking).