Starstruk Logo MarkStarstruk

v0.9.0

airweave-ai/airweavev0.9.0Feb 27, 2026by marc-rutzou

AI Summary

Major release that externalizes embedding model configuration with new required environment variables, adds Linear cursor with incremental sync, OAuth services, and new connectors for Coda and Slab.

Key Highlights

  • Breaking change: Externalized embedding model configuration with 3 new required environment variables (DENSE_EMBEDDER, SPARSE_EMBEDDER, EMBEDDING_DIMENSIONS)
  • Removed connections API and all components
  • Added LinearCursor with incremental sync support for LinearSource
  • Implemented OAuthFlowService and OauthCallbackService with API layer integration
  • Added new connectors: Coda and Slab

Breaking Changes

  • Embedding model configuration externalized - requires DENSE_EMBEDDER, SPARSE_EMBEDDER, and EMBEDDING_DIMENSIONS environment variables to be set
  • Changing embedding model or dimensions makes existing synced data incompatible (collections must be deleted and re-synced)

New Features

  • LinearCursor with incremental sync for LinearSource
  • OAuthFlowService and OauthCallbackService
  • Coda connector
  • Slab connector
  • Embedding models refactoring

Full Release Notes

## Breaking Changes
                                                                                                                                                                                                                                  
This release externalizes the embedding model configuration. Three new required environment variables must be set before upgrading:                                                                                           

  DENSE_EMBEDDER=(openai_text_embedding_3_large / openai_text_embedding_3_small / mistral_embed / local_minilm)
  SPARSE_EMBEDDER=fastembed_bm25
  EMBEDDING_DIMENSIONS=(<=3072 for openai large / <= 1536 for openai small / ==1024 for mistral / ==384 for minilm)

If you want to keep your existing data: set these variables to match the models and dimensions your instance was already using. No re-sync needed.

If you want to switch to a different model or different dimension: set the variables to your desired configuration. Note that changing the embedding model or dimensions makes existing synced data incompatible -> all collections will need to be deleted and re-synced.

## What's Changed
* chore: remove connections API and remove all components by @felixschmetz in https://github.com/airweave-ai/airweave/pull/1487
* feat: add LinearCursor and support incremental sync for LinearSource by @EwanTauran in https://github.com/airweave-ai/airweave/pull/1486
* [code blue] OauthFlowService and OauthCallbackService + hook into API layer by @felixschmetz in https://github.com/airweave-ai/airweave/pull/1472
* Add `coda` to `self-hosted.integrations.yaml` by @viralpraxis in https://github.com/airweave-ai/airweave/pull/1474
* feat: ENG-15: Implement `slab` connector by @viralpraxis in https://github.com/airweave-ai/airweave/pull/1481
* Refactor/embedding models code blue by @marc-rutzou in https://github.com/airweave-ai/airweave/pull/1479


**Full Changelog**: https://github.com/airweave-ai/airweave/compare/v0.8.99...v0.9.0