Thanks to visit codestin.com
Credit goes to github.com

Skip to content

🪢 Langfuse Python SDK - Instrument your LLM app with decorators or low-level SDK and get detailed tracing/observability. Works with any LLM or framework

License

Notifications You must be signed in to change notification settings

qnnn/langfuse-python

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Langfuse Python SDK

MIT License CI test status PyPI Version GitHub Repo stars Discord YC W23

Installation

Important

The SDK was rewritten in v2 and released on December 17, 2023. Refer to the v2 migration guide for instructions on updating your code.

pip install langfuse

Full documentation: https://docs.langfuse.com/sdk/python

Langchain documentation: https://docs.langfuse.com/langchain

Development

Add Poetry plugins

poetry self add poetry-dotenv-plugin
poetry self add poetry-bumpversion

Install dependencies

poetry install --all-extras

Add Pre-commit

poetry run pre-commit install

Tests

Setup

  • Add .env based on .env.example

Run

  • Run all
    poetry run pytest -s -v --log-cli-level=INFO
    
  • Run a specific test
    poetry run pytest -s -v --log-cli-level=INFO tests/test_sdk.py::test_flush
    
  • E2E tests involving OpenAI and Serp API are usually skipped, remove skip decorators in tests/test_langchain.py to run them.

Update openapi spec

  1. Generate Fern Python SDK in langfuse and copy the files generated in generated/python into the langfuse/api folder in this repo.
  2. Execute the linter by running poetry run ruff format .
  3. Rebuild and deploy the package to PyPi.

Publish release

  1. poetry version patch
    • poetry version prepatch for pre-release versions
  2. poetry install
  3. poetry build
  4. git commit -am "chore: release v{version}"
  5. git push
  6. git tag v{version}
  7. git push --tags
  8. poetry publish
  9. Create a release on GitHub with the changelog

SDK Reference

The SDK reference is generated via pdoc. To update the reference, run the following command:

poetry run pdoc -o docs/ --docformat google langfuse

You need to have all extra dependencies installed to generate the reference.

poetry install --all-extras

About

🪢 Langfuse Python SDK - Instrument your LLM app with decorators or low-level SDK and get detailed tracing/observability. Works with any LLM or framework

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 100.0%