Release 2.3.22

[karthikscale3]

Description

This PR introduces support for the following:

• Support for LiteLLM
• Experiment tracking for DSPy experiments. Note that, for experiments to show up, pass the following additional attributes using the inject_additional_attributes. This way Langtrace knows that you are running an experiment:

1. (Required) experiment - Experiment name. Ex: experiment 1.
2. (Optional) description - Some useful description about the experiment.
3. (Optional) run_id - When you want to associate traces to a specific runs, pass a unique run ID. This is useful when you are running Evaluate() as part of your experiment where the traces specific to the Evaluate() will appear as an individual entry.

• The Eval Chart on Langtrace Client will appear when you run Evaluate(). Note: Currently the score ranges it supports are between 0 and 100. So if you have scores that do not fall within this range, it could cause some UI issues.

from langtrace_python_sdk import inject_additional_attributes

predictor = inject_additional_attributes(lambda: compiled_rag(my_question), {'experiment': 'experiment 1', 'description': 'some useful description', 'run_id': 'run_1'})

Checklist for adding new integration:

• Defined APIS in constants folder.
• Updated SERVICE_PROVIDERS in common.py
• Created a folder under instrumentation with the name of the integration with atleast patch.py and instrumentation.py files.
• Added instrumentation in all_instrumentations in langtrace.py and to the InstrumentationType in types.py files.
• Added examples for the new integration in the examples folder.
• Updated pyproject.toml to install new dependencies
• Updated the README.md of langtrace-python-sdk to include the new integration in the supported integrations table.
• Updated the README.md of Langtrace's repository to include the new integration in the supported integrations table.
• Added new integration page to supported integrations in Langtrace Docs