Repository navigation

feat(knowledge): add embedding model selection and Cohere reranker - #4349

Merged

waleedlatif1 merged 22 commits into

stagingfrom

waleedlatif1/embedding-model-research

Apr 30, 2026

Merged

feat(knowledge): add embedding model selection and Cohere reranker#4349
waleedlatif1 merged 22 commits into
stagingfrom
waleedlatif1/embedding-model-research

Commits on Apr 30, 2026
- feat(knowledge): add embedding model selection and Cohere reranker
  waleedlatif1
  committed
  9614a28
- fix(knowledge): split reranker model constants into client-safe module
  waleedlatif1
  committed
  c56b7a4
- fix(knowledge): bill rerank on every successful API call and fix MDX docs literal
  waleedlatif1
  committed
  5d1446f
- test(knowledge): align embedding tests with provider abstraction changes
  
  waleedlatif1
  and
  claude
  committed
  553021a
- fix(knowledge): require explicit Azure deployment per OpenAI embedding model
  
  waleedlatif1
  and
  claude
  committed
  542d2ed
- fix(knowledge): skip platform reranker billing for BYOK Cohere keys
  
  waleedlatif1
  and
  claude
  committed
  d70ac8f
- fix(knowledge): match search tokenizer to embedding provider; remove dead var
  
  waleedlatif1
  and
  claude
  committed
  57589cb
- fix(knowledge): match chunk tokenizer to KB embedding provider
  
  waleedlatif1
  and
  claude
  committed
  96cf4dd
- refactor(knowledge): centralize tokenizer mapping on EmbeddingModelInfo
  
  waleedlatif1
  and
  claude
  committed
  14538a1
- refactor(knowledge): lock embedding model to KB_EMBEDDING_MODEL env var
  
  waleedlatif1
  and
  claude
  committed
  7a9ba8b
- fix(knowledge): use provider tokenizer for chunks and bound rerank indices
  
  waleedlatif1
  and
  claude
  committed
  53624f3
- fix(knowledge): use .count from estimateTokenCount return value
  
  waleedlatif1
  and
  claude
  committed
  97fa4d5
- fix(knowledge): only enforce single embedding model when query is present
  
  waleedlatif1
  and
  claude
  committed
  b1643ee
- fix(knowledge): use getConfiguredEmbeddingModel in copilot KB creation
  
  waleedlatif1
  and
  claude
  committed
  78d6af7
- fix(knowledge): make EMBEDDING_DIMENSIONS a literal type
  
  waleedlatif1
  and
  claude
  committed
  687b7f5
- fix(knowledge): use per-KB embedding model in v1 search route
  
  waleedlatif1
  and
  claude
  committed
  f7eef61
- chore(knowledge): polish embedding/reranker implementation
  
  waleedlatif1
  and
  claude
  committed
  cb1cab7
- fix(knowledge): resolve type errors and unhandled rejection in search routes
  
  waleedlatif1
  and
  claude
  committed
  5dfaed2
- fix(knowledge): pass Gemini API key via x-goog-api-key header
  
  waleedlatif1
  and
  claude
  committed
  b73c218
- fix(knowledge): default Azure deployment name to embedding model name
  
  waleedlatif1
  and
  claude
  committed
  64a17db
- fix(knowledge): cap Gemini batches at 100 items, add singular GEMINI_API_KEY fallback
  
  waleedlatif1
  and
  claude
  committed
  99743d9
- fix(knowledge): prefer singular Cohere key before rotation
  
  waleedlatif1
  and
  claude
  committed
  8fd0557

Commits

Commits on Apr 30, 2026