oadmin/new-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,381 Commits 3 Branches 0 Tags
67cbbc22669c1353dc3a92389d4bd97d00a4211d
Commit Graph

360 Commits

Author SHA1 Message Date
CaIon
a29f4d88c5 Update model-ratio.go 2025-04-04 23:41:41 +08:00
jasinliu
dc132655a6 fix dify thinking 2025-03-28 00:21:27 +08:00
Seefs
20c043f584 fix: claude function calling type 2025-03-19 22:48:49 +08:00
1808837298@qq.com
7143b0f160 feat: Add support for cross-region AWS model handling in awsStreamHandler 2025-03-17 23:41:00 +08:00
1808837298@qq.com
19935ee8ac feat: Enhance ConvertClaudeRequest method to set request model and handle vertex-specific request conversion 2025-03-17 17:13:33 +08:00
Calcium-Ion
b5aa3c129b Merge pull request #872 from neotf/main 
feat: support AWS Model CrossRegion
 2025-03-17 16:18:11 +08:00
1808837298@qq.com
8c7c39550c refactor: Update ClaudeResponse error handling to use pointer for ClaudeError and improve nil checks in response processing 2025-03-16 23:14:45 +08:00
1808837298@qq.com
d1c62a583d feat: support xinference rerank to jina format 2025-03-16 21:06:29 +08:00
1808837298@qq.com
53b3599827 refactor: Enhance Claude response handling 2025-03-16 19:11:58 +08:00
1808837298@qq.com
b3b1c803fc feat: Introduce JSON decoding utility functions and update error handling in Claude and OpenAI response structures 2025-03-16 18:34:39 +08:00
1808837298@qq.com
ee302c063c refactor: Enhance error handling in AWS and Claude response processing by updating function signatures and improving error propagation 2025-03-16 16:47:16 +08:00
1808837298@qq.com
2c81a5f0cc refactor: Streamline AWS and Claude response handling by consolidating logic and improving error management 2025-03-16 16:07:51 +08:00
Calcium-Ion
b84b6affe9 Merge pull request #874 from HynoR/feat/gemini2 
Chore: Sync Cohere Latest Model
 2025-03-15 19:44:37 +08:00
1808837298@qq.com
c183c1231c refactor: Replace direct access to ImageUrl with GetImageMedia method across multiple relay channels 2025-03-15 19:43:37 +08:00
1808837298@qq.com
dd393cd0d9 feat: support dify upload image file 2025-03-15 19:10:12 +08:00
TAKO
e98849048c Sync Cohere Latest Model 2025-03-15 12:12:46 +08:00
neotf
892d014c26 feat: support AWS Model CrossRegion 2025-03-15 01:42:24 +08:00
1808837298@qq.com
19bfa158cc refactor: Change ClaudeError field type to non-pointer and enhance response handling with reasoning content 2025-03-14 17:48:26 +08:00
CalciumIon
69e44a03b1 refactor: Simplify OpenAI handler function signature and remove unused TextResponseWithError struct; introduce common_handler for rerank functionality 2025-03-14 17:31:05 +08:00
Calcium-Ion
a381163402 Merge pull request #867 from Sh1n3zZ/wrong-think-label-fix 
fix: wrong thinking labels appear in non-thinking models (#861)
 2025-03-14 16:59:56 +08:00
CalciumIon
1644dbc864 refactor: Update token usage calculation in FormatClaudeResponseInfo #865 2025-03-14 17:00:39 +08:00
Sh1n3zZ
cc1400e939 fix: wrong thinking labels appear in non-thinking models (#861) 2025-03-14 03:13:52 +08:00
1808837298@qq.com
6187656aa9 chore: Update GitHub Actions workflows and refactor adaptor logic for Docker image builds 2025-03-13 21:10:39 +08:00
Calcium-Ion
e5b6aa6e85 Merge pull request #857 from asjfoajs/main 
Refactor: Optimize the ImageHandler under the Alibaba large model to …
 2025-03-13 19:51:08 +08:00
1808837298@qq.com
7e46d4217d feat: 初步兼容流模式下openai渠道类型转为claude格式访问 #862 2025-03-13 19:32:08 +08:00
霍雨佳
23596d22c9 Refactor: Optimize the ImageHandler under the Alibaba large model to retrieve the key from the header. 
Reason: The info parameter already includes the key, so there is no need to retrieve it again from the header.
Solution: Delete the code for obtaining the key and directly use info.ApiKey.
 2025-03-13 08:54:45 +08:00
1808837298@qq.com
2048b451bf fix panic 2025-03-12 21:35:57 +08:00
1808837298@qq.com
bd48f43410 feat: claude relay 2025-03-12 21:31:46 +08:00
1808837298@qq.com
c0b9350785 fix: claude to openai tools use 2025-03-12 19:46:08 +08:00
1808837298@qq.com
229738cda9 fix: claude to openai tools use 2025-03-12 19:29:15 +08:00
1808837298@qq.com
39d95172e8 fix: claude to openai tools use 2025-03-12 18:53:38 +08:00
1808837298@qq.com
a981e10712 feat(relay): Add Xinference channel support 2025-03-12 17:53:46 +08:00
Sh1n3zZ
e1b9f164f9 feat: gemini Embeddings support 2025-03-10 23:32:06 +08:00
霍雨佳
434e9d7695 Fix: Under Ali's large model, the task ID result for image retrieval is incorrect. 
Reason: The URL is incomplete, missing baseurl.
Solution: Add baseurl. url := fmt.Sprintf("%s/api/v1/tasks/%s", info.BaseUrl, taskID).
 2025-03-10 16:22:40 +08:00
1808837298@qq.com
a9bfcb0daf feat: Add prompt cache hit tokens support for DeepSeek channel #406 2025-03-08 16:50:53 +08:00
Sh1n3zZ
894dce7366 fix: possible incomplete return of the think field and incorrect occurrences of the reasoning field 2025-03-06 19:20:29 +08:00
Sh1n3zZ
b95142bbac fix: adapting return format for openrouter think content (#793) 2025-03-06 19:16:26 +08:00
1808837298@qq.com
558e625a01 fix: Prevent resource leaks by adding body close in stream handlers 2025-03-05 19:51:22 +08:00
1808837298@qq.com
37a83ecc33 refactor: Centralize stream handling and helper functions in relay package 2025-03-05 19:47:41 +08:00
1808837298@qq.com
8deab221f9 fix: vertex claude 2025-03-05 16:43:40 +08:00
1808837298@qq.com
cbdf26bf2c feat: Add context-aware goroutine pool for safer concurrent operations 2025-03-04 18:42:34 +08:00
1808837298@qq.com
eb46b71a71 fix: Ignore EOF errors in OpenAI stream scanner 2025-03-04 17:35:41 +08:00
1808837298@qq.com
b00dd8b405 fix: Handle scanner errors in OpenAI relay stream handler 2025-03-04 17:10:56 +08:00
1808837298@qq.com
b1be64bcf3 fix: vertex claude 2025-03-03 20:06:08 +08:00
1808837298@qq.com
18d3706ff8 feat: Add new model management features 
- Implement `/api/channel/models_enabled` endpoint to retrieve enabled models
- Add `EnabledListModels` handler in controller
- Create new `ModelRatioNotSetEditor` component for managing unset model ratios
- Update router to include new models_enabled route
- Add internationalization support for new model management UI
- Include GPT-4.5 preview model in OpenAI model list
 2025-02-28 21:13:30 +08:00
1808837298@qq.com
cfd3f6c073 feat: Enhance Claude default max tokens configuration 
- Replace ThinkingAdapterMaxTokens with a more flexible DefaultMaxTokens map
- Add support for model-specific default max tokens configuration
- Update relay and web interface to use the new configuration approach
- Implement a fallback mechanism for default max tokens
 2025-02-28 17:53:08 +08:00
1808837298@qq.com
45c56b5ded feat: Implement model-specific headers configuration for Claude 2025-02-28 16:47:31 +08:00
1808837298@qq.com
d0bc8d17d1 feat: Enhance Claude MaxTokens configuration handling 
- Update Claude relay to set default MaxTokens dynamically
- Modify web interface to clarify default MaxTokens input purpose
- Improve token configuration logic for thinking adapter models
 2025-02-27 22:10:29 +08:00
1808837298@qq.com
3a18c0ce9f fix: Correct model request configuration in Vertex Claude adaptor 2025-02-27 20:51:10 +08:00
1808837298@qq.com
929668bead feat: Refactor model configuration management with new config system 
- Introduce a new configuration management approach for model-specific settings
- Update Gemini settings to use the new config system with more flexible management
- Add support for dynamic configuration updates in option handling
- Modify Claude and Vertex adaptors to use new configuration methods
- Enhance web interface to support namespaced configuration keys
 2025-02-27 20:49:34 +08:00