Starstruk Logo MarkStarstruk

v2.6.0

microsoft/graphragv2.6.0Sep 22, 2025by AlonsoGuevara

AI Summary

A feature-rich release introducing LiteLLM integration, async processing, and vector store customization.

Key Highlights

  • Added LiteLLM chat and embedding model providers
  • Implemented NLP async mode
  • Added optional input documents to the indexing API
  • Added customization options for the vector store

New Features

  • LiteLLM chat and embedding model providers
  • NLP async mode
  • Optional input documents for indexing API
  • Vector store customization

Full Release Notes

## What's Changed
- minor: Add LiteLLM chat and embedding model providers.
- minor: Add LoggerFactory and clean up related API.
- minor: Add config for NLP async mode.
- minor: Add optional input documents to indexing API.
- minor: add customization to vector store
- patch: Add gpt-5 support by updating fnllm dependency.
- patch: Fix all human_readable_id fields to be 0-based.
- patch: Fix multi-index search.
- patch: Improve upon recent logging refactor
- patch: Make cache, storage, and vector_store factories consistent with similar registration support
- patch: Remove hard-coded community rate limiter.
- patch: generate_text_embeddings only loads tables if embedding field is specified.

## New Contributors
* @Wonderdch made their first contribution in https://github.com/microsoft/graphrag/pull/2038

**Full Changelog**: https://github.com/microsoft/graphrag/compare/v.2.5.0...v2.6.0