Commit Graph

407 Commits

Author SHA1 Message Date
Laisky.Cai
04da1b7861 fix: improve reasoning token counting in OpenAI adaptor 2025-02-19 09:13:17 +00:00
Laisky.Cai
8c77218480 feat: update billing ratios for DeepSeek models 2025-02-19 08:47:09 +00:00
Laisky.Cai
5ba60433d7 feat: enhance reasoning token handling in OpenAI adaptor 2025-02-19 08:10:19 +00:00
Laisky.Cai
a45a3d6241 feat: enhance reasoning token handling in OpenAI adaptor 2025-02-19 08:10:04 +00:00
Laisky.Cai
abe6afacca Merge branch 'fix/openrouter-reasoning' 2025-02-19 01:32:51 +00:00
Laisky.Cai
480f248a3d feat: support OpenRouter reasoning 2025-02-19 01:20:14 +00:00
Laisky.Cai
a5f5e85c44 feat: support OpenRouter reasoning 2025-02-19 01:11:46 +00:00
Laisky.Cai
2a5908586d Merge branch 'upstream/main' 2025-02-16 13:18:50 +00:00
longkeyy
7ac553541b
feat: update openrouter models and price 20250213 (#2084)
Some checks failed
CI / Unit tests (push) Has been cancelled
CI / commit_lint (push) Has been cancelled
2025-02-16 18:01:59 +08:00
longkeyy
a5c517c27a
feat: update ali models and price 20250213 (#2086) 2025-02-16 18:01:24 +08:00
JustSong
3f421c4f04 feat: support Gemini openai compatible api 2025-02-16 17:59:39 +08:00
JustSong
cafd0a0327 feat: add OpenAI compatible channel (close #2091) 2025-02-16 17:38:06 +08:00
Laisky.Cai
fef7ae048b
feat: support gemini-2.0-flash (#2055)
* feat: support gemini-2.0-flash

- Enhance model support by adding new entries and refining checks for system instruction compatibility.
- Update logging display behavior and adjust default quotas for better user experience.
- Revamp pricing structures in the billing system to reflect current model values and deprecate outdated entries.
- Streamline code by replacing hardcoded values with configurations for maintainability.

* feat: add new Gemini 2.0 flash models to adapter and billing ratio

* fix: update GetRequestURL to support gemini-1.5 model in versioning
2025-02-12 00:34:25 +08:00
JustSong
53da209134 feat: add AliBailian adaptor and update channel options 2025-02-12 00:15:43 +08:00
JustSong
eb96aa635e feat: update OpenRouter channel name and add model list for OpenRouter adaptor 2025-02-11 00:20:55 +08:00
Laisky.Cai
33f3400c12 fix: update Prompt type in GeneralOpenAIRequest and adjust related logic in ConvertCompletionsRequest 2025-02-10 02:11:53 +00:00
JustSong
c715f2bc1d feat: add new models for xai
Some checks are pending
CI / Unit tests (push) Waiting to run
CI / commit_lint (push) Waiting to run
2025-02-09 21:21:28 +08:00
JustSong
696265774e feat: add MiniMax model constants to the adaptor 2025-02-09 18:55:32 +08:00
JustSong
974729426d feat: refactor Xunfei API version handling and update model list 2025-02-09 18:50:51 +08:00
JustSong
57c1367ec8 feat: add Xunfei V2 channel support and update related configurations 2025-02-09 18:31:54 +08:00
JustSong
44233d5c04 feat: add completion tokens details and reasoning effort fields to model (close #2050) 2025-02-09 18:14:01 +08:00
JustSong
bf45a955c3 fix: update system prompt handling by renaming field and ensuring proper usage in request processing (close #2069) 2025-02-09 14:41:42 +08:00
JustSong
dd65b997dd feat: add Baidu V2 channel support and improve model handling 2025-02-09 12:37:26 +08:00
Laisky.Cai
4fb8501833 Merge branch 'upstream/main' 2025-02-09 03:49:59 +00:00
longkeyy
3e3b8230ac
fix: add read/write locks for ModelRatio and GroupRatio to prevent concurrent map read/write issues (#2067)
Some checks are pending
CI / Unit tests (push) Waiting to run
CI / commit_lint (push) Waiting to run
2025-02-09 11:02:45 +08:00
JustSong
07808122a6 fix: fix Debugf not using DebugEnabled (close #2068) 2025-02-09 10:57:22 +08:00
Laisky.Cai
032f9892c8 Merge branch 'upstream/main' 2025-02-07 02:36:12 +00:00
Laisky.Cai
2ab5f8ab47 fix: update GetRequestURL to support gemini-1.5 model in versioning 2025-02-07 02:31:22 +00:00
Laisky.Cai
6ac92a008b feat: update API version handling for Azure channel in Adaptor 2025-02-07 01:36:25 +00:00
JustSong
293ba93ad6 fix: remove outdated model from ModelList and add new deepseek models 2025-02-07 00:13:57 +08:00
JustSong
e146b14d46 fix: add default API version handling and enhance error message checks for Gemini 2025-02-07 00:01:38 +08:00
JustSong
e19045f925 chore: add deepseek-reasoner 2025-02-06 23:38:29 +08:00
Laisky.Cai
bd055dd989 Merge branch 'patch/o3-mini' 2025-02-06 13:15:05 +00:00
Laisky.Cai
0103e980fc feat: add support for audio content in Message model and update README
closes #2054
2025-02-06 13:12:35 +00:00
Laisky.Cai
b0e9573caf feat: add new Gemini 2.0 flash models to adapter and billing ratio 2025-02-06 12:57:57 +00:00
Laisky.Cai
cdacfb6787 Merge branch 'feature/gemini-2.0-flash' 2025-02-06 03:11:49 +00:00
Laisky.Cai
d70335ecea feat: support gemini-2.0-flash
- Enhance model support by adding new entries and refining checks for system instruction compatibility.
- Update logging display behavior and adjust default quotas for better user experience.
- Revamp pricing structures in the billing system to reflect current model values and deprecate outdated entries.
- Streamline code by replacing hardcoded values with configurations for maintainability.
2025-02-06 03:08:41 +00:00
Laisky.Cai
3e4708b77e feat: support gemini-2.0-flash 2025-02-06 02:34:41 +00:00
Laisky.Cai
aa30c37e3c Merge branch 'upstream/main' 2025-02-03 12:25:00 +00:00
Laisky.Cai
9dd86e8a15 fix: add warning for ENFORCE_INCLUDE_USAGE in stream mode 2025-02-03 12:08:17 +00:00
JustSong
2250f311e1 feat: add latest version of Claude model to constants 2025-02-02 22:25:52 +08:00
lyj
e43f758623
Update model.go (#1963) 2025-02-02 22:24:31 +08:00
jiz4oh
ea3331b79a
fix: remove duplicated model (#2012)
the model `llama-3.2-11b-vision-preview` was declared at 3915ce9814/relay/adaptor/groq/constants.go (L11)
2025-02-02 22:21:30 +08:00
Jeremy JIANG
7a97ddc03c
fix: fix hunyuan paramete & update price (#2019)
* fix: omit null TopP and Temperature fields in request body

* feat: update Hunyuan model ratios
2025-02-02 22:20:38 +08:00
JustSong
d7028b55fd feat: update model list in Zhipu constants for expanded options 2025-02-02 22:15:42 +08:00
Jeremy JIANG
36a03f465b
feat: update Zhipu model prices (#2020) 2025-02-02 22:06:07 +08:00
JustSong
c81ee68dd0 feat: improve error logging for token encoder initialization with offline usage guidance 2025-02-02 17:24:23 +08:00
Laisky.Cai
2ba2503874 Merge branch 'patch/o3-mini' 2025-02-01 13:26:59 +00:00
Laisky.Cai
790e1e9f5b feat: extend support for o3 models and update model ratios 2025-02-01 13:25:47 +00:00
Laisky.Cai
acd9cc0db5 Merge branch 'upstream/main' 2025-02-01 13:17:28 +00:00
Laisky.Cai
0e19d60769 feat: extend support for o3 models and update model ratios 2025-02-01 11:44:04 +00:00
JustSong
4f68f3e1b3 chore: update log content 2025-01-31 20:16:56 +08:00
JustSong
0bab887b2d chore: update log content 2025-01-31 20:15:04 +08:00
JustSong
dc470ce82e feat: show stream & elapsed time in log detail 2025-01-31 19:34:22 +08:00
Laisky.Cai
f47c70aaa2 Merge branch 'upstream/main' 2025-01-31 10:32:35 +00:00
JustSong
ea0721d525 feat: update log content format 2025-01-31 18:15:43 +08:00
Fennng
09911a301d
feat: support hunyuan-embedding (#2035)
* feat: support hunyuan-embedding

* chore: improve implementation

---------

Co-authored-by: LUO Feng <luofeng@flowpp.com>
Co-authored-by: JustSong <quanpengsong@gmail.com>
2025-01-31 16:48:02 +08:00
Laisky.Cai
d88e07fd9a
feat: add deepseek-reasoner & gemini-2.0-flash-thinking-exp-01-21 (#2045)
Some checks are pending
CI / Unit tests (push) Waiting to run
CI / commit_lint (push) Waiting to run
* feat: add MILLI_USD constant and update pricing for deepseek services

* feat: add support for new Gemini model version 'gemini-2.0-flash-thinking-exp-01-21'
2025-01-31 15:15:59 +08:00
Laisky.Cai
e49bb64ea0 fix: remove deprecated gemini model references and update pricing ratios 2025-01-28 04:01:46 +00:00
Laisky.Cai
d5fa98f2e0 fix: translate error messages and comments to English for consistency 2025-01-27 03:34:27 +00:00
Laisky.Cai
303ab407d0 fix: update repository links 2025-01-26 12:29:20 +00:00
Laisky.Cai
92a21f64eb fix: correct audio token accumulation in CountTokenMessages function 2025-01-26 12:22:50 +00:00
Laisky.Cai
2d1fcb46a7 fix: change GetAudioTokens to return float64 and update related functions 2025-01-26 12:17:31 +00:00
Laisky.Cai
a46b94d4c5 feat: only allow gpt-audio stream mode when EnforceIncludeUsage is true 2025-01-26 08:21:51 +00:00
Laisky.Cai
5e351bc02a fix: whisper model billing
- Refactor model name handling across multiple controllers to improve clarity and maintainability.
- Enhance error logging and handling for better debugging and request processing robustness.
- Update pricing models in accordance with new calculations, ensuring accuracy in the billing logic.
2025-01-26 08:02:55 +00:00
Laisky.Cai
f1db73405e fix: make ImagePrompt optional in the model definition
- Update `ImagePrompt` field to be optional in the replication model.
- Improve data handling by adding `omitempty` tag for flexibility.
2025-01-26 06:26:29 +00:00
Laisky.Cai
e265335fc5 feat: add ReasoningEffort field to GeneralOpenAIRequest and ReasoningContent to Message struct 2025-01-26 06:24:39 +00:00
Laisky.Cai
1ea322f371 fix: update OpenAI adaptor to set default temperature and clarify model limitations 2025-01-24 13:41:00 +00:00
Laisky.Cai
531f832d1e refactor: update variable names and improve code readability; add Makefile for linting and installation 2025-01-23 03:32:41 +00:00
Laisky.Cai
66d4936241 feat: add MILLI_USD constant and update pricing for deepseek services 2025-01-22 09:39:25 +00:00
Laisky.Cai
a9310deb65 feat: add support for new Gemini model version 'gemini-2.0-flash-thinking-exp-01-21' 2025-01-22 03:27:22 +00:00
Laisky.Cai
13b1b165bd refactor: update UI text and error messages to English for better accessibility 2025-01-19 12:59:58 +00:00
Laisky.Cai
21041ec7ac Merge branch 'main' into pr/Laisky/25 2025-01-17 07:45:29 +00:00
Laisky.Cai
bdb695895f fix: enhance token usage calculations and improve logging in OpenAI handler 2025-01-14 13:37:00 +00:00
Laisky.Cai
9730ac3bb5 feat: support gpt-4o-audio 2025-01-14 06:38:07 +00:00
Laisky.Cai
feacea0321 feat: support vertex imagen3 2025-01-12 04:18:57 +00:00
Laisky.Cai
e17017eb4a fix: implement audio duration retrieval and add tests 2025-01-08 03:55:02 +00:00
Laisky.Cai
c1a0471e73 feat: add audio processing helper functions and update Dockerfile
inspired by https://github.com/Laisky/one-api/pull/21
2025-01-08 02:35:38 +00:00
Laisky.Cai
ddcd1295ff
Merge pull request #20 from mxdlzg/system_instruction_feature
System instruction feature
2025-01-06 16:12:26 +08:00
Laisky.Cai
73a928f970 fix: update comments for o1 model handling 2025-01-05 02:42:37 +00:00
mxdlzg
ad56898d5a feat: use SystemInstructions and remove gemini dummy message 2024-12-23 14:44:39 +08:00
mxdlzg
ba50a137ea feat: add tool choice configuration and update steam handling in Gemini
update ToolConfig to use pointer type in ChatRequest
2024-12-23 14:44:25 +08:00
Laisky.Cai
a9604fd59c Merge branch 'upstream/main' 2024-12-22 12:13:47 +00:00
Qiying Wang
a858292b54
feat: support gpt-4o-2024-11-20 (#1941)
Some checks failed
CI / Unit tests (push) Has been cancelled
CI / commit_lint (push) Has been cancelled
2024-12-22 19:49:50 +08:00
Yuwei Ba
ff589b5e4a
chore: update model mapping implementation for audio (#1932)
* fixed model mapping

* chore: update implementation

---------

Co-authored-by: JustSong <quanpengsong@gmail.com>
2024-12-22 19:33:11 +08:00
ZhangTianrong
59eae186a3
fix: remove the duplicate claude-3-5-haiku-20241022 in Anthropic's base model list (#1957)
* Update constants.go

Remove the duplicate `claude-3-5-haiku-20241022` causing issue 1928

* fix: fix syntax error

---------

Co-authored-by: JustSong <quanpengsong@gmail.com>
2024-12-22 18:58:29 +08:00
Wei Tingjiang
49ffb1c60d
feat: enhance response handling to support gemini-2.0-thinking (#1995) 2024-12-22 18:25:44 +08:00
longkeyy
2f16649896
feat: update qwen model and price (#1966) 2024-12-22 18:22:57 +08:00
Laisky.Cai
dc181dd7fa Merge branch 'upstream/main' 2024-12-22 02:50:40 +00:00
Laisky.Cai
cf04ab9564 fix: update default version handling for Gemini models and improve billing ratio formatting 2024-12-22 02:32:46 +00:00
Jinjun Liu
c4afcc8337 feat: add support for gemini-2.0-flash-thinking-exp model 2024-12-21 19:46:35 -06:00
Laisky.Cai
e9f117ff72
feat: add gemini-2.0-flash-exp and fix race condition in processChannelRelayError (#1983)
Some checks are pending
CI / Unit tests (push) Waiting to run
CI / commit_lint (push) Waiting to run
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>
2024-12-21 20:32:30 +08:00
Laisky.Cai
6bb5247bd6
feat: add support for new OpenAI models and update billing ratios (#1990) 2024-12-21 20:28:51 +08:00
Laisky.Cai
305ce14fe3
feat: support replicate chat models (#1989)
* feat: add Replicate adaptor and integrate into channel and API types

* feat: support llm chat on replicate
2024-12-21 14:41:19 +08:00
Laisky.Cai
09bfd61f2e refactor: replace Laisky/errors with pkg/errors for improved error handling 2024-12-20 03:06:09 +00:00
Laisky.Cai
7851933cdf test: enhance image editing tests with custom FileHeader and PNG encoding 2024-12-20 02:45:27 +00:00
Laisky.Cai
40f5cd3af0 feat: add support for new OpenAI models and update billing ratios 2024-12-19 05:55:21 +00:00
Laisky.Cai
502cf3315d feat: support llm chat on replicate 2024-12-19 03:14:32 +00:00
Laisky.Cai
79bd053a0a Merge branch 'feature/replicate-remix' 2024-12-16 09:28:53 +00:00
Laisky.Cai
f72c715e4c feat: support image inpainting for flux-fill on replicate 2024-12-16 09:12:24 +00:00