v4.6.0rc1
📦 datadog-sdkView on GitHub →
✨ 6 features🐛 3 fixes⚡ 1 deprecations🔧 8 symbols
Summary
This release enhances LLM Observability by adding prompt retrieval, improved experiment span context, and dataset tagging capabilities. It also includes several bug fixes related to large dataset uploads and profiling initialization.
✨ New Features
- Experiments spans now contain config from the experiment initialization, allowing for searching of relevant spans using the experiment config.
- Experiments spans now contain the tags from the dataset records, allowing for searching of relevant spans using the dataset record tags.
- Introduces LLMObs.get_prompt() to retrieve managed prompts from Datadog's Prompt Registry. The method returns a ManagedPrompt object with a format() method for variable substitution.
- LLMObs.create_dataset supports a bulk_upload parameter to control data uploading behavior.
- LLMObs.create_dataset and LLMObs.create_dataset_from_csv now support specifying the deduplicate parameter.
- Subset of dataset records can now be pulled with tags by using the tags argument to LLMObs.pull_dataset, provided in a list of strings of key value pairs.
🐛 Bug Fixes
- Fix data duplication issue when uploading > 5MB datasets via LLMObs.create_dataset.
- A bug which could prevent Profiling from being enabled when the library is installed through Single Step Instrumentation was fixed.
- Fixes an issue where the profiler was patching the gevent module unnecessarily even when the profiler was not enabled.
Affected Symbols
⚡ Deprecations
- The type annotation for Span.parent_id will change from Optional[int] to int in v5.0.0.