mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-08 22:21:35 +00:00
docs: remove sections from Elasticsearch logging tutorial
This commit is contained in:
parent
631f9a8952
commit
05514681cc
1 changed files with 0 additions and 36 deletions
|
|
@ -271,40 +271,4 @@ curl -X GET "localhost:9200/_search" -H "Content-Type: application/json" -d '{
|
|||
}
|
||||
}
|
||||
}'
|
||||
```
|
||||
|
||||
## What's Logged
|
||||
|
||||
LiteLLM sends OpenTelemetry traces for every request including:
|
||||
|
||||
- **Trace & Span Data**: Structured trace information with parent-child relationships
|
||||
- **Attributes**: Model, token usage, costs, response times, user metadata
|
||||
- **Events**: Request input, response output, and error information
|
||||
- **Resource Info**: Service name, version, and deployment information
|
||||
- **Timing**: Precise start/end times and duration measurements
|
||||
|
||||
The data follows OpenTelemetry semantic conventions for better standardization and tooling compatibility.
|
||||
|
||||
## Advanced Configuration
|
||||
|
||||
**Custom span attributes:**
|
||||
```python
|
||||
import litellm
|
||||
|
||||
# Add custom metadata to traces
|
||||
response = litellm.completion(
|
||||
model="gpt-4.1",
|
||||
messages=[{"role": "user", "content": "Hello!"}],
|
||||
metadata={
|
||||
"user_id": "user123",
|
||||
"session_id": "session456",
|
||||
"environment": "production"
|
||||
}
|
||||
)
|
||||
```
|
||||
|
||||
**Debug OTEL logging:**
|
||||
```bash
|
||||
export DEBUG_OTEL=true
|
||||
litellm --config config.yaml --detailed_debug
|
||||
```
|
||||
Loading…
Add table
Reference in a new issue