Commit History
feat: improve port detection on admin cli login
9af57d6
feat: admin CLI login (#1789)
06e807a
unverified
fix: lint
cacbed6
fix: docker image llama.cpp error catching
9fb713b
Add `toolId` to ToolCall and use it in tool results (#1787)
6f95791
unverified
Kelig
Kelig LEFEUVRE
commited on
fix: build llama.cpp locally in dockerfile (#1788)
f75b6cb
unverified
feat: add a local endpoint type for inference directly from chat-ui (#1778)
4e9a7a9
unverified
feat(db): use in memory db when MONGODB_URL not set (#1773)
aa54575
unverified
fix: trigger redeploy
06b1969
fix: give more buffer to reasoning
6b2e741
fix(preprocessMessages): clarify web search context in final message content
42aaa16
feat: improve task model tool calling (#1755)
28eb3b2
unverified
fix(endpoints): fix for tool calling on hf inference with openai endpoint type (#1754)
f84082b
unverified
feat(openai): added support for non-streaming o1 (e.g. Azure) models (#1687)
38dffdd
unverified
fix: improve tasks performance
49721b1
feat(model): configure Llama-3.1-8B-Instruct with OpenAI-compatible endpoint
e7fed79
feat(tasks): use tools for tasks if available (#1749)
66fd2dc
unverified
fix: move FinalAnswer outside of reasoning processing blocks (#1717)
21e1e7d
unverified
fix: handle no beginToken for token based reasoning models (#1713)
6647bbf
unverified
chores(svelte): migration to svelte 5 (#1685)
21b8785
unverified
fix: bedrock prepareMessages parameters (#1686)
8247328
unverified
feat(chart): use inference proxy (#1688)
7a23445
unverified
feat: add `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` to HuggingChat config (#1660)
3732696
unverified
Added currentDate variable to Dynamic Prompt (#1648)
b1b3d86
unverified
feat(websearch): skip pages that dont return success (#1639)
c55b3ad
unverified
Anthropic Tool Support (#1594)
1ac3a3c
unverified
add option to send user message as part of request body in assistant … (#1322)
2fb4284
unverified
Add support for Amazon Nova (#1629)
d965f78
unverified
fix: disable caching on OpenAI-compatible endpoint type
aca14a0
unverified
fix: single step in cohere endpoint type (#1632)
6d0c42a
unverified
fix: make single step forcing optional on cohere endpoint type
0d9f3a5
fix: catch errors more gracefully in reasoning specific calls
e4c9ecf
fix: set alg in auth if not set by user
b529bcf
unverified
feat(openai): added support for o1 reasoning models (#1618)
98c38e0
unverified
fix: error reporting in tool calling
f09b6ee
unverified
feat: improve tool calling & add tools to qwen 2.5 72b (#1615)
f7aef71
unverified
fix: summary prompt
d9758ad
feat: UI for advanced reasoning models (#1605)
764ecdf
unverified
Anthropic PDF Beta Support (#1571)
63c93cf
unverified
fix: default auth not properly treated if undefined
637ac6b
feat: aggregate model votes in metrics
3583080
fix: remove hf token from tool calling
6313a9e
unverified
fix(websearch): block protocols on playwright (#1579)
d020fb0
unverified
fix: remove accessToken min length for llama.cpp endpoint
ca90fbf
feat(migrations): clean up empty conversations from db (#1561)
061445d
unverified
Fix/oai parameters 1552 (#1557)
52dfa8c
unverified
evalstate
commited on