* 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

…309)

* Move form_uilder into internal pkg.

* Fix import of audio.go

* Reorganize.

* Fix import.

* Fix

---------

Co-authored-by: JoyShi <joy.shi@sap.com>

* 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.

* move request_builder into internal pkg (#304)

* add some test for internal.RequestBuilder

* add a test for openai.GetEngine

* Implement optional io.Reader in AudioRequest (#303) (#265)

* Fix err shadowing

* Add test to cover AudioRequest io.Reader usage

* Add additional test cases to cover AudioRequest io.Reader usage

* Add test to cover opening the file specified in an AudioRequest

* move error_accumulator into internal pkg (#304)

* move error_accumulator into internal pkg (#304)

* add a test for ErrTooManyEmptyStreamMessages in stream_reader (#304)

* Support Retrieve model API (#340)

* Test for GetModel error cases. (#340)

* Reduce the cognitive complexity of TestClientReturnsRequestBuilderErrors (#340)

#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.

* fix json marshaling error response of azure openai (#343)

* add a test case for handleErrorResp func (#343)

* Support Retrieve file content API (#347)

* add timeout test for GetFileContent (#347)

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 <richard.coggins@officedepot.com>

* add 16k_0613 model

* add 16k_0613 model

* add model:

* feat(chat): support function call api

* rename struct & add const ChatMessageRoleFunction

…shReason (#372)

* 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 <rzubov@aintsys.com>

…rays (#381) (#384)

* 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 <jmacwhyte@MacBooger-II.local>

* refactoring http request creation and sending

* fix lint error

* increase the test coverage of client.go

* refactor: Change the style of HTTPRequestBuilder.Build func to one-argument-per-line.

* move json schema to directory/package

* added jsonschema to README

…chema missing properties (#419)

Co-authored-by: Rick <medivhzhan@icloud.com>

* Allow raw tokens to be used as embedding input

* fix linting issues (lines too long)

* add endpoint test for embedding from tokens

* remove redundant comments

* fix comment to match new param name

* change interface to any

* Rename methods and implement convert for base req

* add comments to CreateEmbeddings

* update tests

* shorten line length

* rename parameter

* docs: added instructions for obtaining OpenAI API key to README

* docs: move 'Getting an OpenAI API key' before 'Other examples'

* Implement OpenAI July 2023 Updates

* fix: golangci-lint

* add comment

* fix: remove some model Deprecated

* fix: fix function call error due to nil properties (429)

* refactor: refactoring initializeProperties func in jsonschema pkg (429)

…ject' (#429)(#432) (#434)

* fix: invalid schema for function 'func_name': None is not of type 'object' (#429)(#432)

* test: add integration test for function call (#429)(#432)

* style: remove duplicate import (#429)(#432)

* chore: check for models before sending moderation requets to openai endpoint

* chore: table driven tests to include more model cases for moderations endpoint

* add example for fine tune

* update example for fine tune

* fix comments

* docs: add Frequently Asked Questions to README.md

* Update README.md

Co-authored-by: Alexander Baranov <677093+sashabaranov@users.noreply.github.com>

---------

Co-authored-by: Alexander Baranov <677093+sashabaranov@users.noreply.github.com>

… when content interception is triggered, the error message will contain innererror (#460)

* Compatible with Azure Openai's 2023-07-01-preview version API interface about the error information returned by the intercepted interface

* Compatible with the 2023-07-01-preview API interface of Azure Openai, when content interception is triggered, the error message will contain innererror.InnerError struct is only valid for Azure OpenAI Service.

* feat: implement new fine tuning job API

* fix: export ListFineTuningJobEventsParameter

* fix: lint errors

* fix: test errors

* fix: code test coverage

* fix: code test coverage

* fix: use any

* chore: use url.Values

* chore: add deprecation message

* chore: use new fine tuning API in README example

* completionBatchingRequestSupport

* lint fix

* fix Run test fail

* fix TestClientReturnsRequestBuilderErrors fail

* fix Codecov  check

* ignore TestClientReturnsRequestBuilderErrors lint

* fix lint again

* lint again*2

* replace checkPromptType  implementation

* remove nil check

* update file return struct

---------

Co-authored-by: W <825708370@qq.com>

* chore: support base64 embedding format

* fix: add sizeOfFloat32

* chore: refactor base64 decoding

* chore: add tests

* fix linting

* fix test

* fix return error

* fix: use smaller slice for tests

* fix [skip ci]

* chore: refactor test to consider CreateEmbeddings response

* trigger build

* chore: remove named returns

* chore: refactor code to simplify the understanding

* chore: tests have been refactored to match the encoding format passed by request

* chore: fix tests

* fix

* fix

…rch (#492)

* Add DotProduct Method and README Example for Embedding Similarity Search

- Implement a DotProduct() method for the Embedding struct to calculate the dot product between two embeddings.
- Add a custom error type for vector length mismatch.
- Update README.md with a complete example demonstrating how to perform an embedding similarity search for user queries.
- Add unit tests to validate the new DotProduct() method and error handling.

* Update README to focus on Embedding Semantic Similarity

* fix: use custom marshaler for n_epochs

* chore: use any for n_epochs

* feat: add headers to http response

* chore: add test

* fix: rename to httpHeader

* feat: add headers to http response

* feat: support rate limit headers

* fix: go lint

* fix: test coverage

* refactor streamReader

* refactor streamReader

* refactor: NewRateLimitHeaders to newRateLimitHeaders

* refactor: RateLimitHeaders Resets filed

* refactor: move RateLimitHeaders struct

Added constants for new GPT models including `gpt-4-1106-preview`,
`gpt-4-vision-preview` and `gpt-3.5-turbo-1106`.

The models were announced in the following blog post: https://openai.com/blog/new-models-and-developer-products-announced-at-devday

Copy-pasting the old sample caused compilation errors

- Fix #519

* feat: support chat completion response format

* fix linting error

* fix

* fix linting

* Revert "fix linting"

This reverts commit 015c6ad.

* Revert "fix"

This reverts commit 7b2ffe2.

* Revert "fix linting error"

This reverts commit 2996042.

* chore: add seed new parameter

* fix

* chore: implement assistants API

* fix

* fix

* chore: add tests

* fix tests

* fix linting

* feat: support tools and tools choice new fileds

* fix: use value not pointers

* add support for new image/generation api

* fix one lint

* add revised_prompt to response

* fix lints

* add CreateImageQualityStandard

* fix: refactor assistant API

* fix

* trigger build

* fix: use AssistantDeleteResponse

* feat: implement threads API

* fix

* add tests

* fix

* trigger£

* trigger

* chore: add beta header

* fix ToolChoiche typo

* add tool_call_id to ChatCompletionMessage

* add /chat system_fingerprint response field

* check empty ToolCallID JSON marshaling

and add omitempty for tool_call_id

* messages also required; don't omitempty

* add Type to ToolCall, required by the API

* fix test, omitempty for response_format ptr

* fix casing of role values in comments

* fix test server setup:
- go map access is not deterministic
- this can lead to a route: /foo/bar/1 matching /foo/bar before matching /foo/bar/1 if the map iteration go through /foo/bar first since the regex match wasn't bound to start and end anchors
- registering handlers now converts * in routes to .* for proper regex matching
- test server route handling now tries to fully match the handler route

* add missing /v1 prefix to fine-tuning job cancel test server handler

* chore: first commit

* add apis

* chore: add tests

* feat add apis

* chore: add api and tests

* chore: add tests

* fix

* trigger build

* fix

* chore: formatting code

* chore: add pagination type

Metadata is an optional field per the api spec
https://platform.openai.com/docs/api-reference/runs/createRun

requetsts -> requests

* fix test server setup:
- go map access is not deterministic
- this can lead to a route: /foo/bar/1 matching /foo/bar before matching /foo/bar/1 if the map iteration go through /foo/bar first since the regex match wasn't bound to start and end anchors
- registering handlers now converts * in routes to .* for proper regex matching
- test server route handling now tries to fully match the handler route

* add missing /v1 prefix to fine-tuning job cancel test server handler

* add create message call

* add messages list call

* add get message call

* add modify message call, fix return types for other message calls

* add message file retrieve call

* add list message files call

* code style fixes

* add test for list messages with pagination options

* add beta header to msg calls now that #545 is merged

* Update messages.go

Co-authored-by: Simone Vellei <henomis@gmail.com>

* Update messages.go

Co-authored-by: Simone Vellei <henomis@gmail.com>

* add missing object details for message, fix tests

* fix merge formatting

* minor style fixes

---------

Co-authored-by: Simone Vellei <henomis@gmail.com>

* feat: initial TTS support

* chore: lint, omitempty

* chore: dont use pointer in struct

* fix: add mocked server tests to speech_test.go

Co-authored-by: Lachlan Laycock <supagroova@gmail.com>

* chore: update imports

* chore: fix lint

* chore: add an error check

* chore: ignore lint

* chore: add error checks in package

* chore: add test

* chore: fix test

---------

Co-authored-by: Lachlan Laycock <supagroova@gmail.com>