Commit History
Support Gemini 1.5 Pro from Vertex AI (#1041)
2ce3b4b
unverified
Always dispose of pipeline for embeddings after use (#1048)
95ffbe4
unverified
Dispose of embeddings pipeline occasionally to clear memory (#1047)
6d253ff
unverified
Kill app on tokenizer load fail (#1044)
4af31ae
unverified
return empty if error on hfapi endpoint (#1038)
29f5c0c
unverified
Use inference API for embeddings in huggingchat prod (#1037)
04b77a5
unverified
Switch task model and add max tokens limits (#1036)
86bc2ea
unverified
Add logs to tokenizer fetch (#1030)
cc79662
unverified
Add support for Meta Llama 3 70B in HuggingChat (#1029)
8582ce1
unverified
Update marked from v4 to v12 (#1015)
305971b
unverified
Liam Dyer
commited on
Add langserve endpoint (#1009)
f12455d
unverified
Antonio Ramos
antoniora
commited on
Show the assistant model name in the chat input (#1006)
2435b95
unverified
Update models and add check for assistants model on startup (#998)
29b7d2a
unverified
Move default template so it doesn't override tokenizer (#987)
9437108
unverified
Set ChatML as default chat prompt template (#985)
619722b
unverified
quick fix error message (#977)
d323cb0
unverified
Add support for cohere endpoints (#976)
a99cca3
unverified
Use jinja template for chat formatting (#730) (#744)
0819256
unverified
Implement Cloudflare Workers AI endpoint (#907) (#972)
cb000d3
unverified
User count update (#970)
eb956bc
unverified
Fix button placement on assistant edit/create form (#962)
df27d77
unverified
Google Vertex API support (#950)
3ebd3a8
unverified
[Assistants] trending feature (#938)
a4c3fca
unverified
[Websearch] change context schema (#944)
2e2f16c
unverified
Mishig
commited on
Count system prompt tokens (#850)
50d8483
unverified
Enhance Dynamic User Attribute Handling in OIDC Integration (#885)
c6129c3
unverified
feat: smooth and combine token output (#936)
8583cf1
unverified
Liam Dyer
commited on
Modals: dont close if text is selected (#943)
999407a
unverified
Update AssistantSettings.svelte (#941)
2ce726f
unverified
Store user agent in conversation (#940)
d196c64
unverified
Prepend domain filters in search query generation (#932)
233d2a9
unverified
Show error when webpage cannot be reached or parsed (#930)
e04d4e8
unverified
Fix multi domains for assistants (#929)
cbf4205
unverified
Remove extra > in URLs (#931)
89f9b29
unverified
Anthropic Endpoint Support (#923)
5a31018
unverified
Liam Dyer
commited on
Fix prompt caching on llama.cpp endpoints (#920)
eb071be
unverified
fix: Prompt bypasses login (#921)
2edb278
unverified
Kartik Shetty
commited on
Add openai embeddings (#915)
f7db219
unverified
Include last chunk in websearch context (#912)
8e839b8
unverified
Make sure preprompt is set on open ai endpoint type (#913)
bcfa394
unverified
[Assisntans filter] More UX fixes (#908)
09eb258
unverified
Mishig
commited on