Commit Graph

86 Commits

Author SHA1 Message Date
56c25bfb78 fix: bad xinference error (#2384) 2024-02-05 10:52:14 +08:00
04fb610fe7 add gpt-3.5-turbo-0125 to trail llm list (#2354) 2024-02-02 15:29:27 +08:00
ecf947258a fix [baichuan] Error: argument of type 'NoneType' is not iterable (#2351)
Co-authored-by: baiyansong <baiyansong@hotmail.com>
2024-02-02 12:56:48 +08:00
cd078a6264 feat:add gpt-3.5-turbo-0125 (#2347) 2024-02-02 12:33:11 +08:00
9f637ead38 bump version to 0.5.3 (#2306) 2024-02-01 18:11:57 +08:00
a84e15b8cc fix: ignore spark provider credential validate (#2344) 2024-02-01 18:04:05 +08:00
0c330fc020 feat: add xinference llm context size (#2336) 2024-02-01 17:10:45 +08:00
f0c9bb7c91 fix: typo (#2318) 2024-02-01 13:08:31 +08:00
07279558a5 Change ZHIPU_MAX_LIMITS to 5. Fix issue 2323 (#2324) 2024-02-01 09:06:32 +08:00
2166473852 Feat/add spark3.5 llm (#2314)
Co-authored-by: lux@njuelectronics.com <lux@njuelectronics.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-01-31 17:57:17 +08:00
2660fbaa20 Fix/typos (#2308) 2024-01-31 11:58:07 +08:00
6d5b386394 Feat/blocking function call (#2247) 2024-01-30 15:25:37 +08:00
9d072920da fix: remove finish_reason condition logic when deltaContent is empty (#2270)
Co-authored-by: wanggang <wanggy01@servyou.com.cn>
2024-01-29 23:24:13 +08:00
11a75ee78a fix: remove invalid parameter return_type (#2253) 2024-01-27 14:29:25 +08:00
bb5d5fc683 Feat/billing enhancement (#2239)
Co-authored-by: takatost <takatost@gmail.com>
2024-01-26 18:26:15 +08:00
99e80a8ed0 fix:Bedrock llm issue #2214 (#2215)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Chenhe Gu <guchenhe@gmail.com>
2024-01-26 15:34:29 +08:00
c9e65f4221 Fix/update broken doc links (#2187)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-01-26 15:20:03 +08:00
42227f93c0 add openai gpt-4-0125-preview (#2226) 2024-01-26 13:36:24 +08:00
8be7d8a635 Add new OpenAI embedding models (#2217) 2024-01-26 04:48:20 +08:00
21450b8a51 feat: openai_api_compatible support config stream_mode_delimiter (#2190)
Co-authored-by: wanggang <wanggy01@servyou.com.cn>
Co-authored-by: Chenhe Gu <guchenhe@gmail.com>
2024-01-26 00:31:59 +08:00
b921c55677 Feat/zhipuai function calling (#2199)
Co-authored-by: Joel <iamjoel007@gmail.com>
2024-01-25 16:29:35 +08:00
6cf93379b3 fix: split chunks return empty strings (#2197) 2024-01-25 13:59:18 +08:00
fd5c45ae10 Add tts document&fix bug (#2156)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Yeuoly <45712896+Yeuoly@users.noreply.github.com>
2024-01-24 23:04:14 +08:00
043517717e fix: minimax request timeout (#2185) 2024-01-24 21:53:29 +08:00
76c52300a2 feat: abab6-chat supported (#2184) 2024-01-24 21:07:37 +08:00
dda32c6880 fix: credentials validation of ababa (#2183) 2024-01-24 21:07:26 +08:00
ac4bb5c35f Add tongyi tts&tts function optimization (#2177)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-01-24 20:32:04 +08:00
3c13c4f3ee fix: filename cause windows import error (#2176) 2024-01-24 18:24:17 +08:00
00f4e6ec44 feat: add ffmpeg faq link in missing ffmpeg error (#2146) 2024-01-24 01:45:35 +08:00
6355e61eb8 tts models support (#2033)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Yeuoly <45712896+Yeuoly@users.noreply.github.com>
2024-01-24 01:05:37 +08:00
86286e1ac8 Feat/assistant app (#2086)
Co-authored-by: chenhe <guchenhe@gmail.com>
Co-authored-by: Pascal M <11357019+perzeuss@users.noreply.github.com>
2024-01-23 19:58:23 +08:00
7434d44412 feat: bedrock reorder in provider list (#2121) 2024-01-22 12:06:10 +08:00
8394bbd47f feat: support GLM-4V (#2124) 2024-01-22 11:56:37 +08:00
14a2eeba0c Add bedrock (#2119)
Co-authored-by: takatost <takatost@users.noreply.github.com>
Co-authored-by: Garfield Dai <dai.hai@foxmail.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Charlie.Wei <luowei@cvte.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: Benjamin <benjaminx@gmail.com>
2024-01-22 11:00:19 +08:00
a18dde9b0d feat: add cohere llm and embedding (#2115) 2024-01-21 20:52:56 +08:00
8438d820ad Feat/2070 glm 4 and glm 3 turbo (#2114) 2024-01-21 16:58:06 +08:00
09a8db10d4 Add jina-embeddings-v2-base-de model configuration (#2094) 2024-01-19 18:11:55 +08:00
1a6ad05a23 feat: service api add llm usage (#2051) 2024-01-17 22:39:47 +08:00
1d91535ba6 fix: azure customize model name duplicate (#2073) 2024-01-17 21:17:59 +08:00
d7209d9057 feat: add abab5.5s-chat (#2063) 2024-01-16 19:45:21 +08:00
1a2eacc5a6 Add jina-embeddings-v2-base-zh model configuration (#2049) 2024-01-16 12:25:42 +08:00
b582fc13c3 fix: qwen top_p min/max wrong (#2044) 2024-01-16 01:12:55 +08:00
149102927b fix: openai tool tokens (#2026) 2024-01-14 15:51:05 +08:00
cb7be3767c feat: huggingface llm add new params. (#2014) 2024-01-12 21:15:07 +08:00
34bf2877c8 fix: tongyi stream generate not incremental and add qwen max models (#2013) 2024-01-12 19:19:12 +08:00
1779cea6e3 fix: model provider credentials null value validate failed (#2009) 2024-01-12 16:48:38 +08:00
cc9e74123c improve: introduce isort for linting Python imports (#1983) 2024-01-12 12:34:01 +08:00
cca9edc97a feat: ollama support (#2003) 2024-01-12 12:29:13 +08:00
5e97eb1840 fix: azure openai stream response usage missing (#1998) 2024-01-11 17:34:58 +08:00
c9e4147b11 optimize baichuan invalid key error (#1996) 2024-01-11 13:35:24 +08:00