sigoden
df13045b2c
feat: add siliconflow client ( #831 )
1 month 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
dc78636129
feat: add huggingface client ( #822 )
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
ef0810434c
refactor: minor improvement ( #818 )
2 months ago
rolfwilms
a204a4b189
refactor: update models.yaml to fix Bedrock Sonnet 3.5 max_output_tokens (4096) ( #813 )
2 months ago
sigoden
34ef752359
feat: support ai21 client ( #800 )
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
4384010e5b
refactor: update models.yaml ( #772 )
3 months ago
sigoden
81cc3400d6
refactor: update models.yaml and make minor improvement ( #771 )
3 months ago
sigoden
77df849234
refactor: udpate models.yaml and Argcfile.sh ( #761 )
3 months ago
sigoden
adf6716c84
feat: bedrock client switch to converse api and support cohere models ( #747 )
3 months ago
sigoden
a6f0196017
feat: vertexai support mistral models ( #746 )
3 months ago
sigoden
96ad64352d
feat: merge vertexai-cluade with vertexai ( #745 )
3 months ago
sigoden
5dc84a84c3
chore: update models.yaml ( #743 )
3 months ago
sigoden
cf9d06f51e
refactor: update models.yaml ( #739 )
3 months ago
sigoden
17fd7b3260
refactor: update models.yaml ( #726 )
3 months ago
sigoden
0264ab80ab
refactor: update models.yaml and abandon anyscale ( #701 )
3 months ago
sigoden
3b6cf3cd1b
chore: update models.yaml
4 months ago
sigoden
9416cbd8b8
refactor: update models.yaml ( #669 )
4 months ago
sigoden
2bc9607b00
refactor: rename model type `rerank` to `reranker` ( #646 )
4 months ago
sigoden
2fbb5271af
feat: support rag-dedicated clients (jina and voyageai) ( #645 )
4 months ago
sigoden
6d148c9c53
refactor: embedding model add price and dimension ( #636 )
4 months ago
sigoden
590c525048
refactor: remove reka client ( #635 )
4 months ago
sigoden
52a847743e
refactor: improve system message handling ( #634 )
4 months ago
sigoden
250e0eb7fe
feat: ernie support function calling ( #631 )
4 months ago
sigoden
1fd5c58cff
feat: ernie support embeddings and rereank ( #630 )
4 months ago
sigoden
de16813bee
refactor: update readme and models.yaml
4 months ago
sigoden
7a089d846e
refactor: rename model.max_concurrent_chunks to model.max_batch_size ( #626 )
4 months ago
sigoden
f2378e1725
refactor: rename model.mode to model.type ( #625 )
4 months ago
sigoden
97c82e565f
feat: cloudflare support embeddings ( #623 )
4 months ago
sigoden
6d05afc81b
refactor: update models.yaml
4 months ago
sigoden
ba832016f3
refactor: update models.yaml ( #621 )
4 months ago
sigoden
abc588daac
feat: support rerank ( #620 )
4 months ago
sigoden
3b3d39cef0
refactor: rag add rag_minimum_score config ( #617 )
4 months ago
sigoden
1fb06ecdc4
feat: qianwen support function calling ( #616 )
4 months ago
sigoden
98ac7e2b57
feat: support reka client ( #614 )
4 months ago
sigoden
2f8c694626
feat: support lingyiwanwu client ( #613 )
4 months ago
sigoden
12872b3d29
refactor: update models.yaml ( #602 )
4 months ago
sigoden
746b087111
refactor: add/modify rag-related config ( #599 )
4 months ago
sigoden
1f33b3a07a
refactor: rag default_chunk_size ( #588 )
4 months ago
sigoden
a732291f33
refactor: rename `pass_max_tokens` to `require_max_tokens` ( #562 )
5 months ago
sigoden
1ec6abfaee
feat: support RAG ( #560 )
...
* feat: support RAG
* support more embeddings models and implement concurrent embedding api
* show the progress of addings paths
* ignore embedding context when saving message
* embedding model max_chunk_size => default_chunk_size
* support pdf and pandoc formats (docx, epub, ipynb)
5 months ago
rolfwilms
569317728c
fix: bedrock issues ( #544 )
...
* Removed extraneous key [stream] for AWS Bedrock Claude models.
* Reduceddefault AWS Bedrock llama-3 max_output_tokens to 2048 to align with API requirements.
---------
Co-authored-by: Rolf Wilms <rwilms@csc.com>
5 months ago
sigoden
2ccbb0f06a
refactor: qiawen client add qwen-long ( #537 )
5 months ago
sigoden
b4a40e3fed
feat: support function calling ( #514 )
...
* feat: support function calling
* fix on Windows OS
* implement multi-steps function calling
* fix on Windows OS
* add error for client not support function calling
* refactor message data structure and make claude client supporting function calling
* support reuse previous call results
* improve error handling for function calling
* use prefix `may_` as indicator for `execute` type fucntions
5 months ago