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

# Tags

A Tag object includes the tag's key, and its value. You can use tags to add extra information to a trace or request.

```python theme={null}
client.tag(key: str, value: str, metadata: Dict, tag_type: str) -> Tag:
```

### Arguments

<ParamField path="key" type="string" required />

<ParamField path="value" type="string/numeric/boolean/object/array" required />

<ParamField path="metadata" type="object" />

<ParamField path="tag_type" type="string">
  The type of tag. Default tag types are `tag`, `log`, `variable`, and
  `feedback`.
</ParamField>

### Instructions

With a traced OpenAI client, after it is created:

```python theme={null}
client.tag (key="project", value="customer support")
```

### Adding tags to a completed trace or completion

After a trace or completion has completed, you may want to add extra tags based on feedback collected later. To do this, store the <code>trace\_id</code> and, for completions, the <code>completion\_id</code>. Use the <code>tag</code>, <code>log</code>, or <code>feedback</code> functions to add tags, specifying `trace_id` and `completion_id` as needed.

```python theme={null}
from baserun import OpenAI, log, feedback

client = OpenAI(name="trace to be resumed")
completion = client.chat.completions.create(
    name="completion to be resumed",
    model="gpt-4o",
    messages=[{"role": "user", "content": "What are three activities to do in Paris?"}],
)

# Store these values
trace_id = client.trace_id
completion_id = completion.completion_id

# A few moments later...
log("Tagging resumed", trace_id=trace_id, completion_id=completion_id)
feedback("User satisfaction", 0.9, trace_id=trace_id, completion_id=completion_id)
```