Change8

v0.14.22

📦 llamaindexView on GitHub →
2 features🐛 5 fixes🔧 7 symbols

Summary

This release primarily focuses on dependency updates across numerous packages via mass uv lock upgrades and introduces Multimodal synthesis support in llama-index-core. Several minor bug fixes address issues related to instrumentation, caching, and token counting.

✨ New Features

  • Enabled Multimodal synthesis in llama-index-core.
  • SparseEmbeddingStartEvent now inherits from EmbeddingStartEvent in instrumentation.

🐛 Bug Fixes

  • Preserved cache writes from multiprocessing workers in IngestionPipeline.
  • Avoided mutating response.raw in LLM event model_dump methods.
  • Handled DocumentBlock in Memory._estimate_token_count.
  • Propagated contextvars in sync_to_async for FunctionTool.
  • Removed stale exports from public __all__ lists.

Affected Symbols