Ecosystem/ai-gateway
5
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
987 Commits 5 Branches 367 Tags 62 MiB
04bb3ef392
Commit Graph

146 Commits

Author SHA1 Message Date
JustSong
e64e7707a0 feat: support cohere's web search 2024-04-27 00:06:43 +08:00
JustSong
ea210b6ed7 chore: update ollama models 2024-04-26 23:12:39 +08:00
JustSong
9026ec7510 feat: support cloudflare now 2024-04-26 23:05:48 +08:00
JustSong
c317872097 feat: support deepseek now 2024-04-26 00:48:53 +08:00
JustSong
da0842272c fix: add model to response (close #1362) 2024-04-24 22:19:58 +08:00
Ghostz
24f026d18e
feat: add cohere support (#1355) 
* support cohere

* chore: tiny improvements

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2024-04-24 21:50:01 +08:00
Wei Tingjiang
779b747e9e
feat: add function and tools support for Gemini (#1358) 
* Update model.go

* Support Gemini tool_calls.

* Fix gemini tool calls (also keep support functions).

* Fixed the problem of arguments not being stringified.

Fix panic: candidate.Content.Parts out of range
 2024-04-24 21:26:45 +08:00
JustSong
3d149fedf4 chore: do not hardcode context key 2024-04-21 19:43:23 +08:00
JustSong
e30ebda0fe chore: move config key to package ctxkey 2024-04-21 18:55:13 +08:00
JustSong
e5b3e37c46 feat: support bot prefix for coze 2024-04-21 18:04:56 +08:00
JustSong
8de489cf06 feat: support coze now 2024-04-21 17:59:57 +08:00
JustSong
541182102e fix: ignore empty choice response for azure (close #1324) 2024-04-21 16:22:28 +08:00
JustSong
b2679cca65 fix: fix preview completion ratio (close #1326) 2024-04-21 15:57:01 +08:00
tylinux
a2a00dfbc3
feat: groq support Llama3 now (#1333) 
* feat: groq support Llama3 now

* fix: update model ratio

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2024-04-21 14:53:03 +08:00
JustSong
2369025842 fix: use prefix to match more json response 2024-04-20 01:15:33 +08:00
Laisky.Cai
fc9a784950
feat: support aws bedrockruntime claude3 (#1328) 
* feat: support aws bedrockruntime claude3

closes #622, closes #749, closes #1300

* fix: convert to aws claude model id

* fix: Update AWS adapter to handle stream completions and calculate usage metrics

Based on the file summaries provided, here are the important bullet points for the commit message:

- Add functionality to handle stream completion events from AWS in the relay/adaptor/aws/main.go file
- Marshall AWS response to OpenAI format and calculate usage metrics in the same file
- Implement a custom render function for streaming events in the same file
- Improve error handling for JSON unmarshalling and marshalling errors in the same file

* fix: Implement AWS handler with usage tracking and error handling

- Implemented streaming response handling for AWS handler
- Set response content type to text/event-stream
- Added error handling for failed marshaling/unmarshaling
- Updated return values to include `relaymodel.ErrorWithStatusCode` and `relaymodel.Usage`
- Improved error handling and response formatting for AWS adaptor

* fix: Refactor AWS Adapter for Improved Model Mapping and Error Handling

* Refactor AWS adapter to improve model management
  - Replace hardcoded model list in `adapter.go` with a function to get models from `awsModelIDMap`
  - Update `GetModelList` function to return model list directly
  - Add `GetChannelName` function to get channel name from `Adaptor` object
* Improve error handling and code organization in main.go
  - Replace switch statement with a map to map AWS model IDs to OpenAI model IDs
  - Return an error if the model is not found in the map
  - Use a single return statement instead of wrapping multiple return statements in the `awsModelID` function
  - Add a new error message for when the model is not found in the map in the `Handler` function

* fix: bug fix

* chore: change variable name & package

* chore: change variable name

* perf: update config related code

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2024-04-20 00:40:47 +08:00
JustSong
a10232f43a feat: add gpt-4-turbo support (close #1304) 2024-04-13 11:39:31 +08:00
JustSong
e086da05b1 feat: able to change gemini version (close #1211) 2024-04-06 20:48:22 +08:00
JustSong
572fc9ffb8 fix: fix stepfun model ratio & id 2024-04-06 10:43:54 +08:00
JustSong
961b4108e6 chore: fix refactor caused typo 2024-04-06 02:12:50 +08:00
JustSong
0b8ccb94eb chore: reorganize common package 2024-04-06 02:03:59 +08:00
JustSong
f586ae0ad8 chore: remove helper & util subpackage for relay 2024-04-06 01:50:12 +08:00
JustSong
24ed170e7b chore: reorganize adaptor related package 2024-04-06 01:36:48 +08:00
JustSong
f70506eac1 chore: reorganize relay related package 2024-04-06 01:31:44 +08:00
JustSong
8f4d78e24d chore: reorganize billing related package 2024-04-06 01:26:48 +08:00
JustSong
cd2707692f chore: reorganize billing related package 2024-04-06 01:09:23 +08:00
JustSong
2ab7d25a80 chore: reorganize helper related package 2024-04-06 01:02:35 +08:00
JustSong
f9d914873f chore: reorganize constant related package 2024-04-06 00:44:33 +08:00
JustSong
880e12c855 feat: support cogview-3 2024-04-06 00:30:08 +08:00
JustSong
0cb224e62e chore: fix typo 2024-04-05 23:55:25 +08:00
JustSong
eec41849ec chore: fix ali image implementation 2024-04-05 18:25:57 +08:00
Mo
d4347e7a35
feat: support Ali stable-diffusion-xl and wanx-v1 model (#1240) 
* Fix ali ConvertRequest function to use baidu keyword

* Support Ali stable-diffusion-xl and wanx-v1 model

* Support Ali stable-diffusion-xl and wanx-v1 model

* Support Ali stable-diffusion-xl and wanx-v1 model

* chore: update ali constants and model ratio

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>
 2024-04-05 18:09:54 +08:00
manjieqi
b50b43eb65
feat: update baidu model name & ratio (#1277) 2024-04-05 17:30:48 +08:00
JustSong
5b41f57423 feat: support stepfun's models 2024-04-05 12:32:05 +08:00
JustSong
0bb7db0b44 fix: do not detect quota field in error message (close #1276) 2024-04-05 12:11:50 +08:00
JustSong
76569bb0b6 chore: disable channel when error message contain credit or balance 2024-04-05 00:31:41 +08:00
JustSong
1994256bac chore: disable channel when error message contain quota 2024-04-05 00:18:26 +08:00
JustSong
1f80b0a39f chore: add omitempty for xunfei functions 2024-04-05 00:13:37 +08:00
manjieqi
f73f2e51df
feat: update baidu model name & ratio (#1253) 
* 修正百度模型名称

* 更新百度模型名称，并保留旧版兼容以及修正单价

* chore: add more model and adjust order

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2024-04-05 00:02:15 +08:00
Yang Fei
6f036bd0c9
feat: add embedding-2 support for zhipu (#1273) 
* 增加对智谱embedding-2模型的支持

* fix: fix usage & ratio

---------

Co-authored-by: yangfei <yangfei@xuyao.info>
Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2024-04-04 23:32:59 +08:00
JustSong
065da8ef8c fix: fix ali function call (#1242) 2024-04-04 00:46:30 +08:00
JustSong
e3cfb1fa52 feat: use given usage if available in stream mode 2024-03-31 23:41:52 +08:00
JustSong
f89ae5ad58 feat: initial function call support for xunfei 2024-03-31 23:12:29 +08:00
JustSong
06a3fc5421 chore: update GeneralOpenAIRequest 2024-03-31 22:23:42 +08:00
JustSong
3f3c13c98c feat: support top_k for claude (close #1239) 2024-03-30 10:47:07 +08:00
JustSong
2ba28c72cb feat: support function call for ali (close #1242) 2024-03-30 10:43:26 +08:00
JustSong
f76c46d648 feat: add gemini-1.5-pro (#1211) 2024-03-24 22:50:09 +08:00
JustSong
56ddbb842a fix: return pre-consumed quota when error happened for audio (close #1217) 2024-03-24 22:20:41 +08:00
JustSong
99f81a267c fix: fix xunfei error handling (close #1218) 2024-03-24 22:14:45 +08:00
xietong
c243cd5535
feat: 支持 ollama 的 embedding 接口 (#1221) 
* 增加ollama的embedding接口

* chore: fix function name

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2024-03-24 21:51:31 +08:00
GuangxiaoLong
e96b173abe
feat: 移除 azure model 的 TrimSuffix (#1193) 2024-03-24 21:47:46 +08:00
Ian Li
ade19ba4a2
feat: update default API version for Azure OpenAI (#994) 
* feat: Update default API version for Azure OpenAI.

* chore: update other theme

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2024-03-17 19:34:21 +08:00
Ian Li
4d86d021c4
feat: support Azure OpenAI TTS. (#1177) 2024-03-17 19:30:50 +08:00
JustSong
1185303346 chore: update comments 2024-03-17 14:10:35 +08:00
majian
205aba694f
chore: limit the temperature and top_p parameter value range to (0.0, 1) for zhipu (#1091) 2024-03-16 13:39:30 +08:00
Jguobao
66efabd5ae
fix: fix baidu url check (#1143) 
添加百度的另外3个向量模型【"bge-large-zh",
	"bge-large-en",
	"tao-8k",
】
 2024-03-14 23:31:07 +08:00
JustSong
b169173860 fix: force set Accept header for ali stream request (close #1151) 2024-03-14 23:20:38 +08:00
JustSong
e3767cbb07 fix: fix haiku model name (close #1149) 2024-03-14 23:13:05 +08:00
JustSong
be9eb59fbb feat: support lingyiwanwu 2024-03-14 23:11:36 +08:00
JustSong
2dcef85285 feat: support ollama now (close #870) 2024-03-14 01:02:47 +08:00
JustSong
79d0cd378a fix: fix baidu system prompt (close #1079) 2024-03-13 22:56:54 +08:00
JustSong
e99150bdb9 fix: make quota int64 2024-03-13 20:00:51 +08:00
JustSong
a72e5fcc9e fix: when cached quota is too low, force refresh it 2024-03-13 19:38:44 +08:00
JustSong
49cad7d4a5 feat: update func ShouldDisableChannel for claude 2024-03-13 19:11:30 +08:00
sparanoid
a45fc7d736
fix: model name typo (#1109) 2024-03-11 00:44:49 +08:00
JustSong
1ea598c773 feat: check claude's error response 2024-03-10 20:39:55 +08:00
JustSong
8388aa537f chore: able to search channel now 2024-03-10 14:59:57 +08:00
JustSong
2346bf70af fix: check response type when expect stream response 2024-03-10 14:59:40 +08:00
JustSong
f05b403ca5 feat: use real system prompt now (close #1079) 2024-03-10 14:32:30 +08:00
JustSong
b33616df44 feat: support groq now (close #1087) 2024-03-10 14:09:44 +08:00
JustSong
bf2e26a48f feat: support claude-3 (close #1080, close #1094) 2024-03-09 01:12:47 +08:00
momomobinx
4fb22ad4ce
feat: support third part models of baidu (#1046) 
百度千帆平台上的第三方大模型调用
 2024-03-03 23:50:28 +08:00
JustSong
c6ace985c2 fix: set missing ali parameters (close #1028) 2024-03-03 22:51:01 +08:00
JustSong
9d8967f7d3 feat: support Mistral's models now (close #1051) 2024-03-03 21:46:45 +08:00
JustSong
b35f3523d3 feat: add gemini model alias (close #1064) 2024-03-03 21:03:04 +08:00
JustSong
de18d6fe16 refactor: refactor image relay (close #1068) 2024-03-03 19:30:11 +08:00
JustSong
1d0b7fb5ae feat: support chatglm-4 (close #1045, close #952, close #952, close #943) 2024-03-02 03:05:25 +08:00
JustSong
df1fd9aa81 feat: support minimax's models now (close #354) 2024-03-02 01:24:28 +08:00
JustSong
614c2e0442 feat: support baichuan's models now (close #1057) 2024-03-02 00:55:48 +08:00
JustSong
6b27d6659a fix: add role for ChatCompletionsStreamResponseChoice.Delta 2024-02-25 19:49:22 +08:00
JustSong
dc5b781191 fix: fix stream response id 2024-02-25 19:47:59 +08:00
JustSong
c880b4a9a3 fix: fix missing index in ChatCompletionsStreamResponseChoice (#1037) 2024-02-25 19:17:37 +08:00
JustSong
bd888f2eb7 fix: fix prompt token is zero (close #1023) 2024-02-21 22:19:42 +08:00
JustSong
6cf5ce9a7a fix: fix SparkDesk model name 2024-02-18 17:11:16 +08:00
JustSong
f598b9df87 feat: add new SparkDesk models 2024-02-18 17:02:36 +08:00
JustSong
2acc2f5017 feat: support moonshot now (close #804) 2024-02-18 16:17:19 +08:00
JustSong
604ac56305 fix: set seed parameter for qwen (close #1005) 2024-02-18 15:01:09 +08:00
JustSong
9383b638a6 feat: add ChatPro & ChatStd for tencent (#1010) 2024-02-18 14:40:01 +08:00
JustSong
28d512a675 refactor: delete useless code 2024-02-18 02:23:31 +08:00
JustSong
de9a58ca0b refactor: use config field to save config 2024-02-18 02:22:50 +08:00
JustSong
1aa374ccfb refactor: use adaptor to do relay & test 2024-02-18 00:15:31 +08:00
Laisky.Cai
d548a01c59
feat: Handle errors, validate model names, and calculate quota usage (#978) 
- Improved error handling in various modules for better stability and responsiveness.
- Optimized code in several files for improved efficiency and readability.
- Enhanced user experience by providing more detailed error responses in the controller.
- Strengthened security by ignoring sensitive files in `.gitignore`.
 2024-02-12 21:35:40 +08:00
JustSong
2cd1a78203 chore: update module name 2024-01-28 19:38:58 +08:00
JustSong
b9d3cb0c45 refactor: split RelayTextHelper function 2024-01-28 19:14:46 +08:00
JustSong
2d760d4a01
refactor: refactor relay part (#957) 
* refactor: refactor relay part

* refactor: refactor config part
 2024-01-21 23:21:42 +08:00
JustSong
eed9f5fdf0
refactor: refactor relay part (#935) 2024-01-14 19:21:03 +08:00