Code

History

Commits on fix-git-https-support to crates/semantic_index/src/embedding.rs29
  1. Add LM Studio support to the Assistant (#23097)Yagil Burowski committed 1 year agoc038696
  2. Add a slash command for automatically retrieving relevant context (#17972)Max Brunsfeld committed 2 years agoe309fbd
  3. /auto (#16696)Richard Feldman committed 2 years ago91ffa02
  4. Semantic Index (#10329)Kyle Kelley committed 2 years ago49371b4
  5. move embedding provider to ai crateKCaverly committed 3 years ago68c37ca
  6. move api authentication to embedding providerKCaverly committed 3 years ago7b63369
  7. Refactor semantic searching of modified buffersAntonio Scandurra committed 3 years agoae85a52
  8. swap SystemTime for Instant throughout rate_limit_expiry trackingKCaverly committed 3 years agoe678c7d
  9. updated notify to accomodate for updated countdownKCaverly committed 3 years ago37915ec
  10. updated semantic_index reset status to leverage target reset system time as opposed to durationKCaverly committed 3 years agobf43f93
  11. initial outline for rate limiting status updatesKCaverly committed 3 years agoa5ee8fc
  12. update request timeout for open ai embeddingsKCaverly committed 3 years ago265d02a
  13. update token_count for OpenAIEmbeddings to accomodate for truncationKCaverly committed 3 years ago17237f7
  14. Reify `Embedding`/`Sha1` structs that can be (de)serialized from SQLAntonio Scandurra committed 3 years ago3001a46
  15. fix bug for truncation ensuring no valid inputs are sent to openaiKCaverly committed 3 years ago7d4d6c8
  16. move queuing to embedding_queue functionality and update embedding provider to include trait items for max tokens per batch"KCaverly committed 3 years ago76ce52d
  17. move truncation to parsing step leveraging the EmbeddingProvider traitKCaverly committed 3 years ago9781047
  18. add should_truncate to embedding providersKCaverly committed 3 years ago76caea8
  19. added token count to documents during parsingKCaverly committed 3 years agoe377ada
  20. add proper handling for open ai rate limit delaysKCaverly committed 3 years ago4f8b95c
  21. update rate limiting embeddings strategy to delay lessKCaverly committed 3 years ago3f9f742
  22. reworked ProjectState to include additional contextKCaverly committed 3 years agoced2b2a
  23. added sha1 encoding for each documentKCaverly committed 3 years ago3d89cd1
  24. parellelize embedding api callsKCaverly committed 3 years ago0e07191
  25. Populate project search results multi-buffer from semantic searchMax Brunsfeld committed 3 years ago8d0614c
  26. update logging for open ai embedding and remove redundant truncationKCaverly committed 3 years agoed1b1a5
  27. catch up with mainKCaverly committed 3 years agob9fdfd6
  28. Start work on exposing semantic search via project search viewMax Brunsfeld committed 3 years agoafc4c10
  29. rename vector_store crate to semantic_indexKCaverly committed 3 years ago8b42f5b