Commit History
Fix Voyage re-rank model. Limit file name length. (#4171)
becc54e
Kevin Hu
commited on
Make fast embed and default embed mutually exclusive. (#4121)
541b2f3
Kevin Hu
commited on
Fix fastembed reloading issue. (#4117)
11bef16
Kevin Hu
commited on
Fix transformers dependencies for slim. (#3934)
01faf42
Kevin Hu
commited on
Fix errors detected by Ruff (#3918)
0404a52
Fix HuggingFace model error. (#3870)
0dec4cf
Kevin Hu
commited on
Fix open AI compatible rerank issue. (#3866)
4e421c5
Kevin Hu
commited on
Fix preview issue in file manager. (#3846)
ccbf14d
Kevin Hu
commited on
Change default error message to English (#3838)
d919631
Refactor embedding batch_size (#3825)
08913be
Fix voyage embedding. (#3818)
449650c
Kevin Hu
commited on
Detect invalid response from api.siliconflow.cn (#3792)
7449fd0
add jina new models in jina connector (#3770)
e5a1268
devMls
commited on
Pass top_p to ollama (#3744)
2c75739
Fix error response (#3719)
9c6d79f
Fix batch size issue. (#3675)
c9d78b3
Kevin Hu
commited on
Fix a bug in VolcEngine (#3658)
c62f284
liuhua
liuhua
commited on
Let ThreadPool exit gracefully. (#3653)
6a49fcd
Kevin Hu
commited on
Update docs for v0.14.0 (#3625)
638a84e
Kevin Hu
commited on
when qwen rerank model not return ok, raise exception to notice user (#3593)
8c3fb63
liwenju0
commited on
Make spark model robuster to model name (#3514)
258e6bf
Kevin Hu
commited on
Add api for sessions and add max_tokens for tenant_llm (#3472)
99ac12c
liuhua
liuhua
commited on
Introduced beartype (#3460)
eae0334
Added LocalAI support for rerank models (#3446)
9640d9a
shizzgar
Kevin Hu
commited on
Move settings initialization after module init phase (#3438)
6101699
Use consistent log file names, introduced initLogger (#3403)
8bc2fc9
Fix the value issue of anthropic (#3351)
9ef0b16
shijiefengjun
chenhaodong
Kevin Hu
commited on
exstract model dir from model‘s full name (#3368)
3256beb
roc king
王志鹏
Kevin Hu
commited on
Rework logging (#3358)
22fe41e
fix: Anthropic param error (#3327)
2646b91
Kevin Hu
commited on
add inputs to display to every components (#3242)
70153b9
Kevin Hu
commited on
fix: TypeError: only length-1 arrays can be converted to Python scalars (#3211)
24b9cdf
ksztone-huanggonghao
commited on
accelerate term weight calculation (#3206)
75f6aef
Kevin Hu
commited on
rm unused file (#3205)
8ce7a30
Kevin Hu
commited on
fix local variable ans (#3077)
e9cc5fb
Kevin Hu
commited on
refactor error message of qwen (#3074)
5381c23
Kevin Hu
commited on
make gemini robust (#3012)
1a43942
Kevin Hu
commited on
fix SILICONFLOW rerank error (#2980)
9cbbedc
Kevin Hu
commited on
[Bug]: unnecessary auto-increment calculations in the tokens statistics of the chat model (#2969)
c31ab66
Yinquan WANG
Kevin Hu
commited on
[Bug]: When use OpenAI chat model , raise ERROR: 'CompletionUsage' object has no attribute 'get' #2948 (#2949)
8efa7c5
Yinquan WANG
Kevin Hu
commited on
fix sequence2txt error and usage total token issue (#2961)
0dbe613
Kevin Hu
commited on
Feature/feat1017 (#2872)
8de8827
Resolves #2905 openai compatible model provider add llama.cpp rerank support (#2906)
27aa4e5
Fix keys of Xinference deployed models, especially has the same model name with public hosted models. (#2832)
13b2570
support chat model in huggingface (#2802)
19806c7
JobSmithManipulation
commited on
reduce rerank batch size (#2801)
4a4d1d6
Kevin Hu
commited on
support api-version and change default-model in adding azure-openai and openai (#2799)
fa680e0
JobSmithManipulation
Kevin Hu
commited on
fix bedrock issue (#2776)
40df4d9
Kevin Hu
commited on
fix xinference add rerank model bug (#2758)
f2ca0b5
Sky Blue
commited on