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

# Metadata

PromptLayer allows you to attach multiple key value pairs as metadata to a request. In the dashboard, you can look up requests and analyze analytics using metadata.

Metadata enriches [request logs](/features/observability/request-logs). Return to [Configure Request Logging](/features/observability/request-logs) for the other enrichment options.

We recommend using this for things like session IDs, user IDs, or error messages. Metadata is useful for [searching request logs](/features/search-and-analytics/search) and analyzing grouped results.

## Add metadata when running a prompt

Pass metadata directly into `client.run()` when you already know the request context, such as the user, session, or feature that triggered the prompt.

```python Python theme={null}
response = client.run(
    prompt_name="cake-recipe",
    input_variables={"cake_type": "Chocolate", "serving_size": "8"},
    tags=["production", "recipe-feature"],
    metadata={
        "user_id": "user_123",
        "session_id": "sess_abc"
    }
)

client.track.score(request_id=response["request_id"], score=95)
```

Your metadata and tags appear in the log details, letting you filter and search by user or feature.

<Frame>
  <img src="https://mintcdn.com/promptlayer/2Nw4D0YQ3AERsqEA/new-quickstart-images/metadata-search.png?fit=max&auto=format&n=2Nw4D0YQ3AERsqEA&q=85&s=47ca4b7b678fcade8aa60b57700ec6e2" alt="Log with metadata" width="890" height="1184" data-path="new-quickstart-images/metadata-search.png" />
</Frame>

## Add metadata after a request

Use `track.metadata()` when you need to attach or update metadata after a request has already run.

[Endpoint Reference](/reference/track-metadata)

<CodeGroup>
  ```python Python theme={null}
  promptlayer_client.track.metadata(
    request_id=pl_request_id,
    metadata={
        "user_id":"1abf2345f",
        "post_id": "2cef2345f"
    }
  )
  ```

  ```js JavaScript theme={null}
  promptLayerClient.track.metadata({
    request_id: pl_request_id,
    metadata: {
        "user_id":"1abf2345f",
        "post_id": "2cef2345f"
    }
  })
  ```

  ```java Java theme={null}
  ```

  ```bash REST theme={null}
  curl --request POST \
    --url https://api.promptlayer.com/rest/track-metadata \
    --header 'Content-Type: application/json' \
    --header 'X-API-KEY: pl_<YOUR API KEY>' \
    --data '{
      "request_id": "<REQUEST ID>",
      "metadata": {
        "user_id":"1abf2345f",
        "post_id": "2cef2345f"
      }
    }'
  ```
</CodeGroup>

Things to note:

1. Currently keys and values need to be strings in PromptLayer.
2. If you track a key that was already tracked before for a specific request\_id, the value that corresponds to that key will be replaced.

***

Once metadata is added, you will then be able to see it in the web UI.

<img src="https://mintcdn.com/promptlayer/jUVR1Bx755pIFGwB/images/metadata-ui.png?fit=max&auto=format&n=jUVR1Bx755pIFGwB&q=85&s=240bbb2b1105d461328cd5f70fb67d20" alt="score" width="596" height="652" data-path="images/metadata-ui.png" />

Metadata is optimized for high-cardinality, request-specific values such as user IDs, session IDs, and error messages. For a smaller set of categories, such as environment, app, feature, or pipeline stage, use [tags](/features/observability/request-logs/tags) instead.

## Attaching metadata via OpenTelemetry

If you instrument your app with OpenTelemetry, you can attach metadata directly from span attributes — no `track.metadata()` call required. PromptLayer automatically maps standard attributes like `user.id` and `gen_ai.conversation.id`, and also reads arbitrary `promptlayer.metadata.<key>` attributes.

See [Attaching User Identity & Metadata](/features/observability/traces/opentelemetry#attaching-user-identity-%26-metadata) in the OpenTelemetry guide for details.