3.0.8
What's Changed
This release includes the following changes:
-
DSPy project type
-
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: -
(Required)
experiment
- Experiment name. Ex:experiment 1
. -
(Optional)
description
- Some useful description about the experiment. -
(Optional)
run_id
- When you want to associate traces to a specific runs, pass a unique run ID. This is useful when you are runningEvaluate()
as part of your experiment where the traces specific to theEvaluate()
will appear as an individual entry. -
The Eval Chart 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. -
By default, checkpoints are traced for DSPy pipelines. If you would like to disable it, set the following env var in your application code,
TRACE_DSPY_CHECKPOINT=false
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'})
- Bug fixes and query performance improvements
Full Changelog: 3.0.7...3.0.8