sigoden
cf9d06f51e
refactor: update models.yaml ( #739 )
2024-07-24 12:49:47 +08:00
sigoden
17fd7b3260
refactor: update models.yaml ( #726 )
2024-07-19 06:54:48 +08:00
sigoden
0264ab80ab
refactor: update models.yaml and abandon anyscale ( #701 )
2024-07-11 07:40:24 +08:00
sigoden
3b6cf3cd1b
chore: update models.yaml
2024-07-02 10:39:11 +00:00
sigoden
9416cbd8b8
refactor: update models.yaml ( #669 )
2024-06-29 07:17:40 +08:00
sigoden
2bc9607b00
refactor: rename model type rerank to reranker ( #646 )
2024-06-25 07:50:19 +08:00
sigoden
2fbb5271af
feat: support rag-dedicated clients (jina and voyageai) ( #645 )
2024-06-25 07:39:35 +08:00
sigoden
6d148c9c53
refactor: embedding model add price and dimension ( #636 )
2024-06-23 07:17:26 +08:00
sigoden
590c525048
refactor: remove reka client ( #635 )
2024-06-23 06:08:33 +08:00
sigoden
52a847743e
refactor: improve system message handling ( #634 )
2024-06-23 06:00:58 +08:00
sigoden
250e0eb7fe
feat: ernie support function calling ( #631 )
2024-06-22 14:00:25 +08:00
sigoden
1fd5c58cff
feat: ernie support embeddings and rereank ( #630 )
2024-06-22 12:16:55 +08:00
sigoden
de16813bee
refactor: update readme and models.yaml
2024-06-22 03:01:04 +00:00
sigoden
7a089d846e
refactor: rename model.max_concurrent_chunks to model.max_batch_size ( #626 )
2024-06-21 21:56:25 +08:00
sigoden
f2378e1725
refactor: rename model.mode to model.type ( #625 )
2024-06-21 21:26:18 +08:00
sigoden
97c82e565f
feat: cloudflare support embeddings ( #623 )
2024-06-21 16:50:41 +08:00
sigoden
6d05afc81b
refactor: update models.yaml
2024-06-21 06:51:47 +00:00
sigoden
ba832016f3
refactor: update models.yaml ( #621 )
2024-06-21 06:27:37 +08:00
sigoden
abc588daac
feat: support rerank ( #620 )
2024-06-21 06:00:26 +08:00
sigoden
3b3d39cef0
refactor: rag add rag_minimum_score config ( #617 )
2024-06-19 12:15:54 +08:00
sigoden
1fb06ecdc4
feat: qianwen support function calling ( #616 )
2024-06-19 06:17:29 +08:00
sigoden
98ac7e2b57
feat: support reka client ( #614 )
2024-06-18 12:37:25 +08:00
sigoden
2f8c694626
feat: support lingyiwanwu client ( #613 )
2024-06-18 11:27:51 +08:00
sigoden
12872b3d29
refactor: update models.yaml ( #602 )
2024-06-15 06:39:55 +08:00
sigoden
746b087111
refactor: add/modify rag-related config ( #599 )
2024-06-14 19:12:18 +08:00
sigoden
1f33b3a07a
refactor: rag default_chunk_size ( #588 )
2024-06-12 08:31:22 +08:00
sigoden
a732291f33
refactor: rename pass_max_tokens to require_max_tokens ( #562 )
2024-06-05 09:10:12 +08:00
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)
2024-06-05 09:02:23 +08:00
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>
2024-05-26 05:52:24 +08:00
sigoden
2ccbb0f06a
refactor: qiawen client add qwen-long ( #537 )
2024-05-23 12:26:24 +08:00
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
2024-05-18 19:06:21 +08:00
sigoden
5378033b34
refactor: add gemini-1.5-flash to models.yaml ( #510 )
2024-05-15 09:36:31 +08:00
sigoden
369cf9a36a
refactor: minor refinement
2024-05-14 06:13:42 +00:00
sigoden
20a507375e
refactor: update models.yaml ( #501 )
2024-05-14 06:11:34 +08:00
sigoden
7762cd6bed
refactor: model pass_max_tokens ( #493 )
2024-05-08 13:46:26 +08:00
sigoden
d5fd624eb8
refactor: update models.yaml
2024-05-07 09:17:15 +00:00
sigoden
956a960390
feat: support zhipuai client ( #491 )
2024-05-07 16:40:18 +08:00
sigoden
0071d84aa5
feat: support deepseek client ( #490 )
2024-05-07 16:16:18 +08:00
sigoden
9b283024b4
feat: extract vertexai-claude client ( #485 )
2024-05-06 08:19:42 +08:00
sigoden
5eae392dbd
refactore: add models for openai-compatible platforms ( #471 )
2024-05-01 06:01:10 +08:00
sigoden
8dba46becf
feat: openai-compatible platforms share the same client ( #469 )
2024-04-30 12:52:58 +08:00
sigoden
50eac8b594
feat: support replicate client ( #466 )
2024-04-30 07:07:09 +08:00
sigoden
ffb0af8236
refactor: add some openai-compatiable platforms to config.example.yaml ( #464 )
2024-04-29 20:08:59 +08:00
sigoden
4ddccc361c
refactor: update groq models at models.yaml
2024-04-29 09:05:19 +00:00
sigoden
602494b650
refactor: merge config models, update client models ( #460 )
2024-04-29 11:57:02 +08:00
sigoden
34041a976c
feat: support cloudflare client ( #459 )
2024-04-29 09:27:11 +08:00
sigoden
865be2bf75
feat: non-streaming returns completion stats ( #456 )
2024-04-29 06:51:03 +08:00
sigoden
1f2b626703
feat: support bedrock client ( #450 )
2024-04-28 11:27:06 +08:00
sigoden
615bab215b
feat: support vertexai claude ( #439 )
2024-04-28 10:55:41 +08:00
sigoden
d6df1e84a7
refactor: extract prelude models to models.yaml ( #451 )
2024-04-28 10:14:12 +08:00
