Spaces:
Sleeping
Sleeping
Commit History
fix CI (#1884)
3b53c7a
unverified
Refactor token parameters to standardize naming across models and generation settings
dd2acb7
HuggingChat 2026 (#1875)
7bf1507
unverified
feat(reasoning): support end token search across multiple chunks (#1838)
6cd421f
unverified
fix: remove redundant status update in streaming
7da664f
fix: stop button working properly
260c3b7
fix: rm error in retrying when tool calls are not parsed properly
a327608
New `InferenceClient` endpoint type (#1813)
4906f37
unverified
feat: allow storing env variable in DB (#1802)
48059af
unverified
feat: add a local endpoint type for inference directly from chat-ui (#1778)
de36cdc
unverified
fix: trigger redeploy
73268d4
fix: give more buffer to reasoning
8ce2fb0
feat: improve task model tool calling (#1755)
d37f9ca
unverified
fix(endpoints): fix for tool calling on hf inference with openai endpoint type (#1754)
185c2ff
unverified
fix: improve tasks performance
28b6d44
feat(tasks): use tools for tasks if available (#1749)
6655689
unverified
fix: move FinalAnswer outside of reasoning processing blocks (#1717)
f0ab567
unverified
fix: handle no beginToken for token based reasoning models (#1713)
a68038a
unverified
chores(svelte): migration to svelte 5 (#1685)
a1a6daf
unverified
feat: add `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` to HuggingChat config (#1660)
a38e9de
unverified
Added currentDate variable to Dynamic Prompt (#1648)
81ac98c
unverified
Anthropic Tool Support (#1594)
69d5a1c
unverified
add option to send user message as part of request body in assistant … (#1322)
945e63b
unverified
fix: catch errors more gracefully in reasoning specific calls
c024800
fix: error reporting in tool calling
c75addc
unverified
feat: improve tool calling & add tools to qwen 2.5 72b (#1615)
642ce40
unverified
fix: summary prompt
66897e4
feat: UI for advanced reasoning models (#1605)
bf75aa7
unverified
[feat] Add support for endpoint web sources (#1544)
eabf2bf
unverified
feat(endpoints): Add conv ID to headers passed to TGI (#1511)
791e118
unverified
fix: multimodal on TGI endpoint type (#1491)
bd01335
unverified
fix(front): fix delay after end of streaming tokens
693d11b
unverified
fix(websearch): fix `webSearch` flag use for model with tool use (#1480)
fae04bd
unverified
fix(assistants): remove websearch from assistant tool options, add websearch in backend logic (#1465)
439b391
unverified
fix(assistants): only enable websearch on assistants with RAG (#1452)
29ea0af
unverified
feat(assistants): use community tools in assistants (#1421)
10b8070
unverified
feat(tools): use gradio ETA for tools (#1411)
15baec4
unverified
fix(tools): make show output button work
09ed06c
unverified
fix(stream): add keep alive stream event
9dea7ad
unverified
fix(tools): show error cause
d6102a1
unverified
fix(logs): better error logging
ee5c213
unverified
feat(tools): more detailed errors from tools
c31c50e
unverified
Community tools (#1250)
0c3e3b2
unverified
fix(env) enable LLM_SUMMARIZATION (#1379)
aa1ef18
unverified
zhang-yi-chi
commited on