- Refactored code in relay-utils.go
- Eliminated unused imports and redundant function
- Improved code readability with added comments
- Cleaned up by removing unnecessary commented-out code
* 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>
* 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>
* fix: cloudflare test & expose detailed info about test failures
* fix: cloudflare test & expose detailed info about test failures
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com>
* 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>
- Increase the length of the commit short SHA from 8 to 7 characters
- Update relay-aiproxy.go to handle multiple content types in the last message
- Refactor and modify countVisonTokenMessages function in relay-utils.go to handle different content types and update token counts accordingly
- Update VisionMessage struct in relay.go to have Content as a slice of OpenaiVisionMessageContent
- Modify error message in `VisionMessages` function to include failed JSON blob
- Include changes to omitted files in diff summary
- High-level summary of changes
- Add function `CountVisionImageToken` to count vision image tokens
- Modify function `imageSize` to handle different image types
- Add function `countVisonTokenMessages` to count tokens in vision messages
- Add logic to count tokens for different types of vision messages in `countVisonTokenMessages`
- Add tokens for role and name in `countVisonTokenMessages`
- Update total token count calculation in `countVisonTokenMessages` to include image tokens and message tokens
- Add constant values for tokens per message and tokens per name in `countVisonTokenMessages`
- Modify the error message on line 12 to include the JSON string that failed to unmarshal
- Added required packages to go.mod: `github.com/Laisky/errors/v2 v2.0.1`, `github.com/stretchr/testify v1.8.3`, `github.com/davecgh/go-spew v1.1.1`, `github.com/pmezard/go-difflib v1.0.0`
- Increased the number of returned recordings to 100 in `relay-utils.go`
- Refactored and simplified code in `relay-aiproxy.go` for improved message retrieval and error handling
- Added new test file `relay_test.go` and various test cases for different message types
- Modified functions in `group.go` and `relay.go` for improved functionality
- Added new dependencies: `github.com/fsnotify/fsnotify v1.4.9`, `github.com/go-playground/assert/v2 v2.2.0`, `github.com/nxadm/tail v1.4.8`, `github.com/onsi/ginkgo v1.16.5`, `github.com/onsi/gomega v1.18.1`, `golang.org/x/net v0.10.0`, `gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7`
- Updated dependencies: `github.com/gin-gonic/gin` from v1.9.0 to v2.0.0, `golang.org/x/net` from v0.17.0 to v0.10.0
- Removed dependencies: `github.com/golang-jwt/jwt v3.2.2+incompatible`, `github.com/gorilla/websocket v1.5.1`
- Updated Go version from `1.18` to `1.21`
- Made various modifications and refactoring in the code:
- Added new struct `VisionMessage` with fields `Role`, `Content`, and `Name`
- Added constants for certain types
- Added methods and error handling to handle different message types
- Modified existing struct and methods to accommodate changes
- Removed unused imports
- Remove the unnecessary `AddRemainQuota` field from `updateTokenDto` struct
- Adjust `cleanToken.RemainQuota` by subtracting `tokenPatch.AddUsedQuota`
- Increase `cleanToken.UsedQuota` by adding `tokenPatch.AddUsedQuota`
- Update `model.RecordLog` call to include `tokenPatch.AddReason` and `tokenPatch.AddUsedQuota` values
- Add `gorm:"-"` tag to exclude certain fields from the database schema
- Add `AddReason` field to the `updateTokenDto` struct
- Record consumption log if `AddUsedQuota` is non-zero
- Record token quota modification log if `AddRemainQuota` is non-zero
- Update and save `cleanToken` with new values
* fix: change quota calc code (close#599)
Use float64 during calc and do math.Ceil after calc. This will result in the quota being used slightly more than the official standard, but it will be guaranteed that it will not be less.
* chore: remove blank line
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com>
- Added new API endpoints for user information retrieval, registration, login, logout, self-management, administration, options management, channel management, token management, redemption management, log management, and group retrieval
- Improved authentication flow with GitHub, WeChat, and email
- Added a function `GetSelfByToken` for getting user information using an OpenAI API token
- Updated base image in Dockerfile from `node:16` to `node:18`
- Added `tokenPatch` struct to handle updates to the `Token` model
- Updated `UpdateToken` function to use `tokenPatch` struct for binding JSON
- Improved error handling and validation for token updates
- Refined checks for token status, expiration, and quota
- Enhanced error handling and response for token updates
- Updated JSON response to include `data` field
