Commit Graph

93 Commits

Author SHA1 Message Date
韩贤涛
ff308d5292 fix: Remove the Authorization request header when using AI-proxy to proxy Gemini (#2220) 2025-05-13 09:36:04 +08:00
Xijun Dai
8b3f1aab1a feat(ai-proxy): support Amazon Bedrock Image Generation (#2212)
Signed-off-by: Xijun Dai <daixijun1990@gmail.com>
Co-authored-by: Kent Dong <ch3cho@qq.com>
2025-05-10 09:54:31 +08:00
johnlanni
0a2fb35ae2 fix gemini provider in ai-proxy 2025-05-07 16:54:40 +08:00
Kent Dong
29370b18d7 feat: Support /v1/models API in ai-proxy (#2164) 2025-05-06 15:53:13 +08:00
HaoJie Liu
a57173ce28 feat(ai-proxy): support Amazon Bedrock (#2039) 2025-04-22 22:36:14 +08:00
澄潭
8978a4e0e0 fix invalid ai-proxy cluster (#1947)
Co-authored-by: Kent Dong <ch3cho@qq.com>
2025-03-25 11:20:20 +08:00
澄潭
45fbc8b084 optimize plugin sdk (#1930) 2025-03-22 22:46:37 +08:00
rinfx
4223b2d666 Fix the error in the embedding interface under the AI proxy Qwen compatible mode. (#1928) 2025-03-21 08:32:00 +08:00
Kent Dong
9fa3a730d5 feat: Support forwarding embedding calls to Ollama in ai-proxy (#1913) 2025-03-18 10:23:34 +08:00
Kent Dong
5de7c2a5ea feat: Support files and batches APIs provided by Azure OpenAI (#1904) 2025-03-17 11:21:05 +08:00
澄潭
9a89665b22 optimize retry&failover logic (#1903) 2025-03-17 11:19:33 +08:00
澄潭
61defc13c6 fix openai embedding path (#1881) 2025-03-12 13:16:33 +08:00
Se7en
19496e5759 feat: support retry on http status code (#1817)
Co-authored-by: Kent Dong <ch3cho@qq.com>
2025-03-11 13:38:02 +08:00
Se7en
5536502c15 feat: allow failover to distinguish between different endpoint of the same provider (#1862) 2025-03-10 10:45:59 +08:00
Kent Dong
ab419efda4 fix: Fix the incorrect reasoning content concat logic in ai-proxy (#1842) 2025-03-07 10:33:45 +08:00
Kent Dong
4f1901586a doc: Update the description of timeout config of ai-proxy (#1845) 2025-03-03 15:33:16 +08:00
Se7en
d3afe345ad fix: remove last failed apiToken from retry apiToken list (#1802) 2025-02-26 21:11:51 +08:00
澄潭
1787553294 set include_usage by default for all model providers (#1818) 2025-02-26 16:49:16 +08:00
Kent Dong
49617c7a98 feat: Unify the SSE processing logic (#1800) 2025-02-25 11:00:18 +08:00
Kent Dong
2328e19c9d fix: Fix a bug in openaiCustomUrl support (#1790) 2025-02-22 12:12:49 +08:00
Kent Dong
fabc22f218 feat: Support transforming reasoning_content returned by Qwen to OpenAI contract (#1791) 2025-02-21 17:32:02 +08:00
澄潭
6fb0684c39 fix openai compatiable (#1778) 2025-02-19 15:23:15 +08:00
澄潭
49aad4152c Supports completions API & support config openai baseUrl through openaiCustomUrl (#1765) 2025-02-18 09:57:48 +08:00
澄潭
2dbde1833f ai proxy support passthrough path when api name is unknown (#1754) 2025-02-13 21:22:43 +08:00
pepesi
a84a382f1d feature: allow ai-proxy to forward standard AI capabilities that are … (#1704) 2025-02-12 15:23:44 +08:00
kai2321
fac2c3e7a3 feat:完善对接dify时返回usage相关信息 (#1715) 2025-02-03 08:35:00 +08:00
kai2321
ce94c6e62d feat:接入dify (#1664) 2025-01-21 16:04:15 +08:00
Se7en
b1f625a652 feat: support baidu api key (#1687) 2025-01-19 11:46:29 +08:00
Se7en
ba74f4bbb9 fix: baidu api issue (#1685) 2025-01-16 21:42:43 +08:00
韩贤涛
a1bf315b13 fix: resolve blocking issue with minimax responses in ai-proxy (#1663) 2025-01-14 09:43:19 +08:00
rinfx
ea0d5e7564 Improve ai plugins (#1657)
Co-authored-by: Kent Dong <ch3cho@qq.com>
2025-01-09 22:04:51 +08:00
Kent Dong
187a7b5408 fix: Enlarge the default retry timeout in ai-proxy (#1640) 2025-01-03 11:19:40 +08:00
Se7en
579c986915 feat: retry failed request (#1590) 2024-12-26 18:30:50 +08:00
VinciWu557
909cc0f088 feat: AI 代理 Wasm 插件接入 Together AI (#1617) 2024-12-23 15:39:56 +08:00
澄潭
39c007d045 optimize ai proxy (#1603) 2024-12-19 16:22:35 +08:00
rinfx
2f5709a93e qwen bailian compatible bug fix (#1597) 2024-12-17 16:57:31 +08:00
StarryNight
2a200cdd42 AI proxy return unified status in header phase (#1588) 2024-12-16 18:41:38 +08:00
韩贤涛
8544fa604d feat: support choosing chatCompletionV2 or chatCompletionPro API for minimax provider (#1593) 2024-12-15 15:12:00 +08:00
pepesi
8f660211e3 feat: ai-proxy support custom error handler by cover util.ErrorHandler (#1537) 2024-12-06 11:47:50 +08:00
pepesi
b36e5ea26b feat: allow cover api-version when use ai-proxy azure provider (#1535) 2024-12-05 13:41:02 +08:00
pepesi
d026f0fca5 feat: ai-proxy support dashscope-finance (#1554) 2024-12-05 11:48:09 +08:00
rinfx
22790aa149 fix moonshot usage compatible problem (#1568) 2024-12-05 11:35:25 +08:00
Se7en
e705a0344f fix: qwen stream issue (#1564) 2024-12-03 13:10:47 +08:00
Se7en
ee2dd76ae1 feat: migrate baidu provider to v2 api (#1527) 2024-11-27 20:12:00 +08:00
Se7en
1b1c08afb7 fix: apitoken failover for coze (#1515) 2024-11-18 15:36:26 +08:00
Se7en
d24123a55f feat: implement apiToken failover mechanism (#1256) 2024-11-16 19:03:09 +08:00
rinfx
952c9ec5dc Ai proxy support coze (#1387) 2024-10-14 12:45:53 +08:00
YeHaitao
14b11dcb05 feat: AI Proxy Wasm Plugin Integration with GitHub Models #1304 (#1362) 2024-10-06 17:12:48 +08:00
Kent Dong
708e7af79a feat: Support configuring a global provider list in ai-proxy plugin (#1334) 2024-09-26 11:27:22 +08:00
rinfx
bef9139753 Ai proxy support doubao (#1337) 2024-09-24 18:45:40 +08:00