Spaces:
Runtime error
Runtime error
Commit History
feat: add support for anthropic on vertex (#958) 61e5613 unverified
Fix context of logger (#1112) f862a80 unverified
Fix OpenAI Embeddings Auth Issue (#1077) 77340d8 unverified
[VertexAI] Add support for tools parameter (#1065) 61d56f7 unverified
Use pino for logs (#1086) 486ffa7 unverified
set `sameSite` to `lax` when allowing insecure cookies (#1078) 002aebe unverified
Add `ALLOW_INSECURE_COOKIES` feature flag (#1076) 9c0ebc6 unverified
Use TEI space in prod (#1051) 8cb1f84 unverified
Support Gemini 1.5 Pro from Vertex AI (#1041) 15042e9 unverified
Always dispose of pipeline for embeddings after use (#1048) 622c26c unverified
Dispose of embeddings pipeline occasionally to clear memory (#1047) e5a85ec unverified
Kill app on tokenizer load fail (#1044) ca2ac64 unverified
return empty if error on hfapi endpoint (#1038) 9911143 unverified
Use inference API for embeddings in huggingchat prod (#1037) cc2dafe unverified
Switch task model and add max tokens limits (#1036) 66fa870 unverified
Add logs to tokenizer fetch (#1030) 623e026 unverified
Add langserve endpoint (#1009) f1cd31d unverified
Antonio Ramos antoniora commited on
Move default template so it doesn't override tokenizer (#987) 7451c63 unverified
Set ChatML as default chat prompt template (#985) 69b890b unverified
quick fix error message (#977) fa62a1a unverified
Add support for cohere endpoints (#976) 70cdf7a unverified
Use jinja template for chat formatting (#730) (#744) 144112e unverified
Implement Cloudflare Workers AI endpoint (#907) (#972) 987575f unverified
Google Vertex API support (#950) d5625b9 unverified
[Assistants] trending feature (#938) 1b76365 unverified
[Websearch] change context schema (#944) a4dc062 unverified
Mishig commited on
Count system prompt tokens (#850) ff934bb unverified
Enhance Dynamic User Attribute Handling in OIDC Integration (#885) 3f0bce1 unverified
Prepend domain filters in search query generation (#932) 36be130 unverified
Show error when webpage cannot be reached or parsed (#930) 6fb5de7 unverified
Fix multi domains for assistants (#929) c4489ae unverified
Anthropic Endpoint Support (#923) 58c3781 unverified
Liam Dyer commited on
Fix prompt caching on llama.cpp endpoints (#920) d96c921 unverified
Add openai embeddings (#915) 8c28b44 unverified
Include last chunk in websearch context (#912) c4e8b4e unverified
Make sure preprompt is set on open ai endpoint type (#913) c78cb53 unverified
Add limits on API endpoints (#886) 6d03e59 unverified
[Assistants] Filter on names (#841) 5340dfb unverified
Fix issue with "continue" feature on llama.cpp endpoints (#898) 379bd53 unverified
Bug Fix: Json Decoder aggessively pulls json (#867) 606fbf7 unverified
Pass websearch to `preprocessMessages` (#876) a1ae290 unverified
Add gemma model to prod config (#854) ebe2ba8 unverified
✨ Add stats on conversations (#828) e2f48a3 unverified
[Mongo] Optimize `reports` collection query (v2) (#834) df4a841 unverified
Mishig commited on