v0.2.20

Key Updates

Separate configuration of embedding provider

It’s now possible to independently configure the LLM and embedding providers during setup!
Through the beeai env setup CLI flow, users can now:

1. Select their preferred LLM provider.
2. Then choose a separate embedding provider.

Initial groundworks for beeai-sdk

This release also introduces the initial BeeAI1 SDK, marking the beginning of the platform’s transition to Agent-to-Agent (A2A) as the primary communication protocol.

• Initial SDK structure established.
• A CLI example is included to demonstrate usage.

What's Changed

• fix(server): file_type column migration integrity error by @jezekra1 in #941
• feat(ui): show citations without indices by @PetrBulanek in #942
• chore(ui): bump react-hook-form by @kapetr in #950
• feat(server): add separate embedding provider setup by @jezekra1 in #944
• feat(beeai-sdk): add initial skeleton by @JanPokorny in #952
• feat(beeai-sdk): add CLI example by @JanPokorny in #943
• fix(gpt-researcher): colliding env variable by @jezekra1 in #956

Full Changelog: v0.2.17...v0.2.20