Commit History
Revert "refactor: new API & universal load functions (#1743)" 91e839b
refactor: new API & universal load functions (#1743) 35a395c unverified
fix: only import node-llama-cpp if needed and skip for huggingchat image d8e426c
New `InferenceClient` endpoint type (#1813) e08e6dd unverified
feat: allow storing env variable in DB (#1802) 31daf3d unverified
feat: allow strings in `MODELS` env var (#1791) 6a449cd unverified
feat: add a local endpoint type for inference directly from chat-ui (#1778) 4e9a7a9 unverified
fix: handle no beginToken for token based reasoning models (#1713) 6647bbf unverified
chores(svelte): migration to svelte 5 (#1685) 21b8785 unverified
feat: improve tool calling & add tools to qwen 2.5 72b (#1615) f7aef71 unverified
feat: UI for advanced reasoning models (#1605) 764ecdf unverified
Fix/oai parameters 1552 (#1557) 52dfa8c unverified
evalstate commited on
fix: only show playground button for models that are available bad5446 unverified
fix: use custom tool template only for huggingchat b36dfab unverified
feat: use model id as fallback for finding a tokenizer (#1535) 2b554f9 unverified
feat(models): add `nvidia/Llama-3.1-Nemotron-70B-Instruct-HF` (#1527) d852d1b unverified
[vertex] Add PDF/plein texts support (#1520) a5e332d unverified
goupilew commited on
feat: add link to API playground for compatible models (#1488) baa5d2f unverified
feat(conv): let user switch models on conversations with deprecated models (#1462) 68972f0 unverified
feat(models): add transferTo property on old models (#1453) a1ae528 unverified
fix(continue): fix continue feature (#1459) 4f61809 unverified
Add support for Anthropic models via AWS Bedrock (#1413) b6274e8 unverified
feat(assistants): use community tools in assistants (#1421) 3bb3aef unverified
chores(deps): update Transformers to latest version and remove chat templates for all models (#1414) f3064dd unverified
Community tools (#1250) b8228c1 unverified
fix(logs): improve logging 71f3ffb unverified
feat(models): Llama 3.1 support (#1355) 79b41de unverified
Add Google Gemini API Support (#1330) 6f1638a unverified
Refactor logger error messages for consistency. (#1257) fa0afa9 unverified
Denzel Mendez commited on
Generic Multimodal Support Fixed (#1147) b4690c8 unverified
Revert "Generic Multimodal Support" (#1146) 2a40544 unverified
Mishig commited on
Generic Multimodal Support (#1021) f493225 unverified
feat: add support for anthropic on vertex (#958) 76d1477 unverified
Use pino for logs (#1086) bb6f8cb unverified
Kill app on tokenizer load fail (#1044) 4b62530 unverified
Add logs to tokenizer fetch (#1030) ac3fd05 unverified
Add langserve endpoint (#1009) a9e4746 unverified
Antonio Ramos antoniora commited on
Move default template so it doesn't override tokenizer (#987) 0598c3f unverified
Set ChatML as default chat prompt template (#985) 97f9784 unverified
Add support for cohere endpoints (#976) 1aafdd3 unverified
Use jinja template for chat formatting (#730) (#744) 3d931f5 unverified
Implement Cloudflare Workers AI endpoint (#907) (#972) ac2d8ff unverified
Google Vertex API support (#950) 48f1340 unverified
Count system prompt tokens (#850) eb2ef82 unverified
Anthropic Endpoint Support (#923) 1db019c unverified
Liam Dyer commited on