3.0.15

What's Changed

• Added emojis to README.md For better readability by @NishantRana07 in #312
• Added a contributing.md by @heysagnik in #315
• Error Handling: Always check if the response is OK (i.e., response.st… by @jatin9823 in #314
• Support for OTLP gRPC protocol
• Bugfixes
• Release 3.0.15 by @karthikscale3 in #317

New Contributors

• @NishantRana07 made their first contribution in #312
• @heysagnik made their first contribution in #315
• @jatin9823 made their first contribution in #314

Full Changelog: 3.0.14...3.0.15

3.0.14

What's Changed

• Support for tracing xAI models (https://x.ai/)
• Updates to README.md

Full Changelog: 3.0.13...3.0.14

3.0.13

What's Changed

• Release by @karthikscale3 in #303

Full Changelog: 3.0.12...3.0.13

3.0.12

What's Changed

• OTLP Protobuf exporter support
• CSV uploads for dataset
• Docs: Typo Fix by @Dnaynu in #294
• Release 3.0.12 by @karthikscale3 in #300

New Contributors

• @Dnaynu made their first contribution in #294

Full Changelog: 3.0.11...3.0.12

3.0.11

What's Changed

• Release 3.011 by @karthikscale3 in #293
• Added support for LiteLLM tracking
• Added cost tracking for Google Gemini family of models

Full Changelog: 3.0.10...3.0.11

3.0.10

What's Changed

• Release 3.0.10 by @karthikscale3 in #290

Full Changelog: 3.0.9...3.0.10

3.0.9

What's Changed

• Minor bugfixes
• Release 3.0.9 by @karthikscale3 in #286

Full Changelog: 3.0.8...3.0.9

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 running Evaluate() as part of your experiment where the traces specific to the Evaluate() 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

3.0.7

What's Changed

• Minor bugfix for live prompts @dylanzuber-scale3 in #278

Full Changelog: 3.0.6...3.0.7

3.0.6

What's Changed

• Cost tracking and playground support for OpenAI's latest models o1-preview and o1-mini
• Release 3.0.6 by @karthikscale3 in #276

Full Changelog: 3.0.5...3.0.6