- Train or fine-tune models on the production traces in ABV. E.g. to create a small model after having used a large model in production for a specific use case.
- Collect few-shot examples to improve quality of output.
- Programmatically create datasets.
New data is typically available for querying within 15-30 seconds of ingestion, though processing times may vary at times. Please visit status page if you encounter any issues.
SDKs
Via the SDKs for Python and JS/TS you can easily query the API without having to write the HTTP requests yourself.Python SDK
api namespace is auto-generated from the Public API (OpenAPI). Method names mirror REST resources and support filters and pagination.
Traces
Observations
Sessions
Scores
Prompts
Please refer to the prompt management documentation on fetching prompts.Datasets
Metrics
Async equivalents
Common filtering & pagination
- limit, cursor (pagination)
- time range filters (e.g., start_time, end_time)
- entity filters: user_id, session_id, trace_id, type, name, tags, level, etc.
JS/TS SDK
The dedicated
fetch* methods for core entities are covered by tests and semantic versioning. The methods on the abv.api are auto-generated from the API reference and cover all entities..env
fetchTraces()fetchTrace()fetchObservations()fetchObservation()fetchSessions()