Commit Graph

714 Commits (e5cc194598b86c20e6870ae3d68fe256f3a6ce4e)
 

Author SHA1 Message Date
sigoden e5cc194598
feat: proxy rerank api (#851) 1 month ago
sigoden 69965466e6
feat: proxy chat-completions api with tools support (#850) 1 month ago
sigoden a56d5f2ddf
feat: save rag in YAML instead of bin (#848) 1 month ago
sigoden 89554e0d4e
feat: support RAG-scoped rag_top_k and rag_reranker_model (#847) 1 month ago
sigoden 5adaa869bf chore: update config.example.yaml and models.yaml 1 month ago
sigoden d96950c23b
feat: tolerate failure to load some rag files (#846) 1 month ago
sigoden f4a48e646b
refactor: render error with prefix `Error: ` (#844) 1 month ago
sigoden 9347bb866e
feat: add role %create-prompt% (#843) 1 month ago
sigoden 555f4f5d12
feat: better html to markdown converter (#840) 1 month ago
sigoden 791b6150af
feat: add config `serve_addr` & env $SERVE_ADDR for specifying serve addr (#839) 1 month ago
sigoden b16913fec3
fix: render stream failed due to read cursor position timeout (#835) 1 month ago
sigoden d92f102a85 chore: release v0.21.1 1 month ago
sigoden df13045b2c
feat: add siliconflow client (#831) 1 month ago
sigoden 9654445c32
fix: `:` can be used as seperator for role arguments (#830) 1 month ago
sigoden d57f11445d
chore: release v0.21.0 (#819) 2 months ago
sigoden b2fef25a52
refactor: gemini use batch embedding api (#827) 2 months ago
sigoden 476d29c40a
feat: use dynamic batch size for embedding (#826) 2 months ago
sigoden 3695c12646 chore: update config.example.com 2 months ago
sigoden 3c45ced2d9
refactor: improve bash completion (#824) 2 months ago
sigoden b34b542d31
refactor: keep the role arguments (#823) 2 months ago
sigoden dc78636129
feat: add huggingface client (#822) 2 months ago
sigoden e39498e340 chore: update config.example.yaml 2 months ago
sigoden 2cba09c064
feat: migrate `cloudflare` client to `openai-compatible` (#821) 2 months ago
sigoden 6462a58742 chore: update models.yaml 2 months ago
sigoden 2c6aafb0d7
refactor: openai_compatible client config (#820) 2 months ago
sigoden ef0810434c
refactor: minor improvement (#818) 2 months ago
sigoden 573e0d58b4
feat: migrate `ollama`/`qianwen` clients to `openai-compatible` (#816) 2 months ago
sigoden 55e36c7e9d
feat: webui support RAG (#815) 2 months ago
sigoden ed242c65f0
feat: webui use querystring as settings (#814) 2 months ago
rolfwilms a204a4b189
refactor: update models.yaml to fix Bedrock Sonnet 3.5 max_output_tokens (4096) (#813) 2 months ago
sigoden 00376b98e0
refactor: no function_calling=false if functions.json is empty (#812) 2 months ago
sigoden d8d52b60d6
feat: save temp session with `temp-<timestamp>` if `save_session: true` (#811) 2 months ago
sigoden 4bbf479616
feat: replace roles.yaml with roles/<name>.md (#810) 2 months ago
sigoden 298a45232b
refactor: template for including files (#807) 2 months ago
sigoden 11022f88de
refactor: webui update error style (#803) 2 months ago
sigoden 34ef752359
feat: support ai21 client (#800) 2 months ago
sigoden 8e4b9a383d chore: update config.example.yaml 2 months ago
sigoden 9383d00bcd chore: update models.yaml 2 months ago
sigoden 96eee23d62
refactor: update models.yaml (#799) 2 months ago
sigoden f1cbb3c006
feat: support github client (#798) 2 months ago
sigoden c0eae1c55c
refactor: webui render error (#797) 2 months ago
sigoden 7eefb96b0c
fix: incomplete stream response in proxy LLM api (#796) 2 months ago
sigoden 669f2c602c
feat: enable custom `api_base` for most clients (#793) 2 months ago
sigoden 580ed6bea3
feat: no check model's support for function calls (#791) 2 months ago
sigoden 7a95bd5de0
fix: invalid model error while switching roles if the model_id is same to current (#788) 2 months ago
sigoden 3b8bb7389e
refactor: improve crawl website (#787) 2 months ago
sigoden d79ad49106
feat: support builtin website crawling (recursive_url) (#786) 2 months ago
sigoden 92ce440b0b
fix: claude fails to run tools with zero arguments (#780) 2 months ago
LifetimeMistake 5c559f616a
fix: incorrect function call handling with session in non-REPL (#777) 2 months ago
sigoden 514a3689e8
chore: release v0.20.0 (#774) 3 months ago