merge main branch #1
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* change azure engine config to azure modelMapper config * Update go.mod * Revert "Update go.mod" This reverts commit 78d14c5. * lint fix * add test * lint fix * lint fix * lint fix * opt * opt * opt * opt
* Move form_uilder into internal pkg. * Fix import of audio.go * Reorganize. * Fix import. * Fix --------- Co-authored-by: JoyShi <[email protected]>
* chore(config.go): update Azure API version to 2023-05-15 to use the latest version available * chore(api_internal_test.go): update Azure API version to 2023-05-15 to match the latest version
Added in `unofficial` to the README to make it clear it's not official.
#339) * test: Add tests for improved coverage before refactoring This commit adds tests to improve coverage before refactoring to ensure that the changes do not break anything. * refactor: replace goto statement with loop This commit introduces a refactor to improve the clarity of the control flow within the method. The goto statement can sometimes make the code hard to understand and maintain, hence this refactor aims to resolve that. * refactor: extract for-loop from Recv to another method This commit improves code readability and maintainability by making the Recv method simpler.
Added GPT3Dot5Turbo0613, GPT3Dot5Turbo16K, GPT40613, and GPT432K0613 models from June update (https://openai.com/blog/function-calling-and-other-api-updates) Issue #360
* Improve (#356) to support registration of wildcard URLs * Add TestAzureChatCompletions & TestAzureChatCompletionsWithCustomDeploymentName * Remove TestAzureChatCompletionsWithCustomDeploymentName --------- Co-authored-by: coggsflod <[email protected]>
* add 16k_0613 model * add 16k_0613 model * add model:
* feat(chat): support function call api * rename struct & add const ChatMessageRoleFunction
* add items, which is required for array type * use JSONSchemaDefine directly
* audio: add items to AudioResponseFormat enum * audio: expand AudioResponse struct to accommodate verbose json response --------- Co-authored-by: Roman Zubov <[email protected]>
* fix: chat stream resp has 'data: ' prefix * fix: lint error * fix: lint error * fix: lint error
* feat: use json.rawMessage, test functions
* chore: lint
* fix: tests
the ChatCompletion mock server doesn't actually run otherwise. N=0
is the default request but the server will treat it as n=1
* fix: tests should default to n=1 completions
* chore: add back removed interfaces, custom marshal
* chore: lint
* chore: lint
* chore: add some tests
* chore: appease lint
* clean up JSON schema + tests
* chore: lint
* feat: remove backwards compatible functions
for illustrative purposes
* fix: revert params change
* chore: use interface{}
* chore: add test
* chore: add back FunctionDefine
* chore: /s/interface{}/any
* chore: add back jsonschemadefinition
* chore: testcov
* chore: lint
* chore: remove pointers
* chore: update comment
* chore: address CR
added test for compatibility as well
---------
Co-authored-by: James <[email protected]>
* add chatcompletion stream refusal and logprobs * fix slice to struct * add integration test * fix lint * fix lint * fix: the object should be pointer --------- Co-authored-by: genglixia <[email protected]>
* add attachments in MessageRequest * Move tools const to message * remove const, just use assistanttool const
* updated client_test to solve lint error * modified golangci yml to solve linter issues * minor change
* make user optional in embedding request * fix unit test
The ID field is not always present for streaming responses. Without omitempty, the entire ToolCall struct will be missing.
* add reasoning_effort param * add o1 model * fix lint
* Add support for O3-mini - Add support for the o3 mini set of models, including tests that match the constraints in OpenAI's API docs (https://platform.openai.com/docs/models#o3-mini). * Deprecate and refactor - Deprecate `ErrO1BetaLimitationsLogprobs` and `ErrO1BetaLimitationsOther` - Implement `validationRequestForReasoningModels`, which works on both o1 & o3, and has per-model-type restrictions on functionality (eg, o3 class are allowed function calls and system messages, o1 isn't) * Move reasoning validation to `reasoning_validator.go` - Add a `NewReasoningValidator` which exposes a `Validate()` method for a given request - Also adds a test for chat streams * Final nits
* ref: add image url support to messages * fix linter error * fix linter error
* fix: remove validateO1Specific * update golangci-lint-action version * fix actions * fix actions * fix actions * fix actions * remove some o1 test
* feat: add Anthropic API support with custom version header * refactor: use switch statement for API type header handling * refactor: add OpenAI & AzureAD types to be exhaustive * Update client.go need explicit fallthrough in empty case statements * constant for APIVersion; addtl tests
* fix lint * remove linters
* fix jsonschema tests * ensure all run during PR Github Action * add test for struct to schema * add support for enum tag * support nullable tag
* feat: add new GPT-4.1 model variants to completion.go * feat: add tests for unsupported models in completion endpoint * fix: add missing periods to test function comments in completion_test.go
* feat: Add missing TTS models and voices * feat: Add new instruction field to create speech request - From docs: Control the voice of your generated audio with additional instructions. Does not work with tts-1 or tts-1-hd. * fix: add canary-tts back to SpeechModel
…or DeepSeek R1 (#925) * support deepseek field "reasoning_content" * support deepseek field "reasoning_content" * Comment ends in a period (godot) * add comment on field reasoning_content * fix go lint error * chore: trigger CI * make field "content" in MarshalJSON function omitempty * remove reasoning_content in TestO1ModelChatCompletions func * feat: Add test and handler for deepseek-reasoner chat model completions, including support for reasoning content in responses. * feat: Add test and handler for deepseek-reasoner chat model completions, including support for reasoning content in responses. * feat: Add test and handler for deepseek-reasoner chat model completions, including support for reasoning content in responses.
The legacy completion API supports a `stream_options` object when `stream` is set to true [0]. This adds a StreamOptions property to the CompletionRequest struct to support this setting. [0] https://platform.openai.com/docs/api-reference/completions/create#completions-create-stream_options Signed-off-by: Sean McGinnis <[email protected]>
* Add Prediction field to ChatCompletionRequest * Include prediction tokens in response
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.