Commit Graph

114 Commits

Author SHA1 Message Date
Laisky.Cai
c936198ac8
feat: add Proxy channel type and relay mode (#1678)
Add the Proxy channel type and relay mode to support proxying requests to custom upstream services.
2024-07-22 22:51:19 +08:00
igophper
34cb147a74
refactor: replace hardcoded string with ctxkey constant (#1579)
Co-authored-by: 江杭辉 <jianghanghui@k.app>
2024-06-30 16:13:43 +08:00
Ghostz
fa74ba0eaa
chore: print user id when relay error happened (#1447)
* add userid when relay error

* chore: update log format

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
2024-05-28 01:30:51 +08:00
JustSong
9026ec7510 feat: support cloudflare now 2024-04-26 23:05:48 +08:00
JustSong
3d149fedf4 chore: do not hardcode context key 2024-04-21 19:43:23 +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
f586ae0ad8 chore: remove helper & util subpackage for relay 2024-04-06 01:50:12 +08:00
JustSong
f9d914873f chore: reorganize constant related package 2024-04-06 00:44:33 +08:00
JustSong
12440874b0 feat: able to disable channel by success rate 2024-03-10 17:57:47 +08:00
JustSong
10a926b8f3 feat: only use the top priority when first retry (#1048) 2024-03-03 22:16:34 +08:00
JustSong
2df877a352 feat: switch priority when retry (close #1048) 2024-03-03 22:14:07 +08:00
JustSong
614c2e0442 feat: support baichuan's models now (close #1057) 2024-03-02 00:55:48 +08:00
JustSong
b747cdbc6f fix: fix getAndValidateTextRequest failed: unexpected end of JSON input (close #1043) 2024-02-26 22:52:16 +08:00
JustSong
565ea58e68 feat: built in retry supported (close #1036, close #770) 2024-02-25 19:01:49 +08:00
JustSong
1aa374ccfb refactor: use adaptor to do relay & test 2024-02-18 00:15:31 +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
JustSong
1c8922153d feat: support gemini-vision-pro 2023-12-24 18:54:32 +08:00
Laisky.Cai
f3c07e1451
fix: openai response should contains model (#841)
* fix: openai response should contains `model`

- Update model attributes in `claudeHandler` for `relay-claude.go`
- Implement model type for fullTextResponse in `relay-gemini.go`
- Add new `Model` field to `OpenAITextResponse` struct in `relay.go`

* chore: set model name response for models

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
2023-12-24 16:58:31 +08:00
JustSong
58dee76bf7 fix: fix Gemini stream problem 2023-12-17 16:16:18 +08:00
igophper
9ba5388367
feat: refactor response parsing logic to support multiple formats (#782)
* feat: Refactor response parsing logic to support multiple formats

The parsing logic for responses in relay.go and relay-audio.go was refactored to support multiple response formats - 'json', 'text', 'srt', 'verbose_json', and 'vtt'. The existing `WhisperResponse` struct was renamed to `WhisperJsonResponse` and a new struct `WhisperVerboseJsonResponse` was added to support the 'verbose_json' format. Additional parsing functions were added to extract text from these new response types. This change was necessary to make the parsing logic more flexible and extendable for different types of responses.

* chore: update name

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
2023-12-10 18:39:14 +08:00
Zhengyi Dong
8f5b83562b
fix: fix "invalidPayload" error when request Azure dall-e-3 api without optional parameter (#764)
* fix: based on #754 add 'omitempty' in ImageRequest to fit official api reference for relay

* Revert "fix: based on #754 add 'omitempty' in ImageRequest to fit official api reference for relay"

This reverts commit b526006ce0.

* fix: add missing omitempty

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
2023-12-03 17:43:30 +08:00
JustSong
495fc628e4 feat: support gpt-4 with vision (#683, #714) 2023-11-19 18:38:54 +08:00
JustSong
76f9288c34 feat: update request struct (close #708) 2023-11-19 17:50:30 +08:00
Ian Li
969f539777
fix: skip JSON deserialization when accessing transcriptions and translations (#718)
* fix: Skip JSON deserialization when accessing transcriptions and translations.

* chore: update impl

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
2023-11-19 16:11:39 +08:00
ckt1031
ddcaf95f5f
feat: support tts model (#713)
* Added support for Text-to-Speech models and
endpoints

* chore: update impl

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
2023-11-17 21:18:51 +08:00
ckt1031
1d15157f7d
feat: keep sync with dall-e updates (#679)
* Updated ImageRequest struct and OpenAIModels,
added new Dall-E models and size ratios

* Fixed suspect `or`

* Refactored size ratio calculation in
relayImageHelper function

* Updated the format of resolution keys in
DalleSizeRatios map

* Added error handling for unsupported image size in
relayImageHelper function

* Added validation for number of generated images
and defined image generation ratios

* Refactored variable name from
DalleGenerationImageAmountRatios to
DalleGenerationImageAmounts

* Added validation for prompt length in
relayImageHelper function

* Updated model validation and removed size not
supported error in relayImageHelper function

* Refactored image size and model validation in
relayImageHelper function

* chore: discard binary file

* chore: update impl

---------

Co-authored-by: cktsun1031 <65409152+cktsun1031@users.noreply.github.com>
Co-authored-by: JustSong <songquanpeng@foxmail.com>
2023-11-17 20:03:16 +08:00
JustSong
42451d9d02 refactor: update logging related logic 2023-09-17 15:39:46 +08:00
igophper
d0a0e871e1
fix: support ali's embedding model (#481, close #469)
* feat:支持阿里的 embedding 模型

* fix: add to model list

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>
2023-09-03 22:12:35 +08:00
JustSong
d09d317459 feat: supper whisper now (close #197) 2023-08-27 15:28:23 +08:00
shao0222
4f2f911e4d
fix: fix the issue of function_call not working when using model mapping (#462) 2023-08-26 13:10:18 +08:00
JustSong
ac7c0f3a76 fix: disable channel when 401 received (close #467) 2023-08-26 12:05:18 +08:00
JustSong
1e16ef3e0d chore: resolve conflicts 2023-08-12 11:08:52 +08:00
igophper
476a46ad7e
fix: fix finish_reason fileld not fully compatible with OpenAI (close #372, #373)
* optimize:unify finish_reason field

* refactor: use a global stop finish reason

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
2023-08-12 11:04:53 +08:00
JustSong
150d068e9f chore: update prompt 2023-08-12 10:20:54 +08:00
JustSong
3b36608bbd fix: update no route handler 2023-08-11 19:53:01 +08:00
glzjin
446337c329
fix: calculate usage if not given in non-stream mode (#352) 2023-08-06 17:40:31 +08:00
JustSong
130e6bfd83 feat: support baidu's embedding model (close #324) 2023-07-29 12:15:07 +08:00
JustSong
0495b9a0d7 fix: using whitelist when disabling channels (close #292) 2023-07-22 18:15:30 +08:00
JustSong
2ff15baf66 feat: support claude now (close #150) 2023-07-22 16:18:03 +08:00
JustSong
35cfebee12 feat: retry on failed (close #112) 2023-07-15 19:06:51 +08:00
ckt
b520b54625
feat: initial support of Dall-E (#148, #266)
* feat: initial support of Dall-E

* fix: fix N not timed

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>
2023-07-15 12:30:06 +08:00
玩牛牛
81c5901123
feat: add support for /v1/engines/text-embedding-ada-002/embeddings (#224, close #222) 2023-07-15 12:03:23 +08:00
JustSong
abc53cb208 feat: disable channel when account_deactivated received (close #271) 2023-07-15 11:49:58 +08:00
JustSong
0941e294bf feat: support model remap now 2023-06-27 13:42:45 +08:00
JustSong
9b178a28a3 feat: support /v1/edits now (close #196) 2023-06-25 11:46:23 +08:00
JustSong
8a4cd403fd fix: fix http status code (close #193) 2023-06-23 22:59:44 +08:00
JustSong
00151a0124 chore: format logs 2023-06-22 10:59:01 +08:00