langfuse-python
langfuse-python copied to clipboard
langfuse
🪢 Langfuse Python SDK - Instrument your LLM app with decorators or low-level SDK and get detailed tracing/observability. Works with any LLM or framework
> [!IMPORTANT] > `LangfuseBaseCallbackHandler` now converts `tags` to strings, allowing non-string elements. > > - **Behavior**: > - In `LangfuseBaseCallbackHandler.__init__`, `tags` are now converted to strings, allowing non-string elements (e.g.,...
https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses ---- > [!IMPORTANT] > Add support for parsing OpenAI responses using `parse` method in both sync and async contexts, with tests verifying functionality. > > - **Behavior**: > -...
> [!IMPORTANT] > Fix default mutable arguments, improve exception handling, and add missing class method decorator in various files. > > - **Behavior**: > - Fix default mutable arguments in...
> [!IMPORTANT] > Add optional `metadata` field to score-related models and methods for enhanced contextual data support. > > - **Models**: > - Add `metadata` field to `ScoreBody` in `score_body.py`....
Introduce BaseEventSerializer as an abstract base class This refactoring introduces a new BaseEventSerializer abstract base class that provides a common interface and shared functionality for JSON serialization. Key changes include:...
Add optional timestamp parameter to score creation methods This feature introduces a new `timestamp` argument to the `score` methods. Key changes include: - Add `timestamp` arg to to `LangFuse.score` method...
That's a suggestion for -> https://github.com/langfuse/langfuse/issues/4464 Honestly, I'm not sure about if we can consider it as a bug. Because the response comes from outside and there's no guarantee that...
> [!IMPORTANT] > Adds methods to Langfuse client for fetching and deleting dataset runs with error handling. > > - **Methods Added**: > - `get_dataset_run()`: Fetches a dataset run by...
> [!IMPORTANT] > Introduces a tiered pricing model in the API, adding new classes for pricing tiers and updating the `Model` class to support conditional pricing. > > - **Behavior**:...
This PR enhances the `create_evaluator_from_autoevals` function to properly propagate the `comment` field from the `autoevals` evaluator's `metadata` to the Langfuse `Evaluation` object. Previously, comments within `autoevals` metadata were not explicitly...
