What's Changed

• patch: Add CSVTableProvider
• patch: Add DataReader class for typed dataframe loading from TableProvider across indexing workflows and query CLI
• patch: Add TableProvider abstraction for table-based storage operations
• patch: Add async iterator support to InputReader and use it in load_input_documents and load_update_documents workflows.
• patch: Add table provider factory.
• patch: Fix missed py 3.13.
• patch: Move document ID, human_readable_id, and raw_data initialization from create_final_documents into load_input_documents and load_update_documents.
• patch: Remove NetworkX dependency from graph utilities; move to DataFrame-based implementations in graphrag.graphs package.
• patch: Remove unnecessary response format check. Fixes: #2203
• patch: add profiling to get memory usage
• patch: update notebooks

Full Changelog: v3.0.1...v3.0.2

What's Changed

• patch: Fix missing dependency.

Full Changelog: https://github.com/microsoft/graphrag/compare/v3.0.0..v3.0.1

What's Changed

• major: Monorepo restructure

  New Packages:

  • graphrag-cache
  • graphrag-chunking
  • graphrag-common
  • graphrag-input
  • graphrag-llm
  • graphrag-storage
  • graphrag-vectors

  Changes:

  • New config: run graphrag init --force to reinitialize config with new layout and options.

Full Changelog: v2.7.1...v3.0.0

What's Changed

• patch: Pin pandas==2.3.3.

Full Changelog: v2.7.0...v2.7.1

What's Changed

• minor: Set LiteLLM as default in init_content.
• patch: Fix Azure auth scope issue with LiteLLM.
• patch: Housekeeping before 3.0

Full Changelog: v2.6.0...v2.7.0

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 #2038

Full Changelog: v.2.5.0...v2.6.0

What's Changed

• minor: Add additional context variable to build index signature for custom parameter bag
• minor: swap package management from Poetry -> UV

Full Changelog: v.2.4.0...v.2.5.0

What's Changed

• minor: Allow injection of custom pipelines.
• minor: Refactored StorageFactory to use a registration-based approach
• patch: Fix default values for tpm and rpm limiters on embeddings
• patch: Update typer.
• patch: cleaned up logging to follow python standards.

Full Changelog: v2.3.0...v.2.4.0

What's Changed

• minor: Remove Dynamic Max Retries support. Refactor typer typing in cli interface
• minor: Update fnllm to latest. Update default graphrag configuration
• patch: A few fixes and enhancements for better reuse and flow.
• patch: Add full llm response to LLM PRovider output
• patch: Fix Drift Reduce Response for non streaming calls
• patch: Fix global search prompt to include missing formatting key
• patch: Upgrade pyarrow dependency to >=17.0.0 to fix CVE-2024-52338

Full Changelog: v2.2.1...v2.3.0

What's Changed

• patch: Fix Community Report prompt tuning response
• patch: Fix graph creation missing edge weights.
• patch: Update as workflows

Full Changelog: v2.2.0...v2.2.1