go-openai

go-openai copied to clipboard

Refactor/internal testing

1

See issue: https://github.com/sashabaranov/go-openai/issues/186 Add helpers in order to reduce boilerplate code in the tests. To test this PR run the tests: `go test ./...`.

rexposadas

Incomplete about the stream

3

The content of each request and response is incomplete. How to solve this problem

yzchen27

I m looking to way to reset current dialog context with ChatGPT I've found a way to do it using openAI Python library ``` response = openai.Completion.create( engine="davinci", prompt="Hello, how...

JackBekket

Reading the Open AI docs on [Chat completion](https://platform.openai.com/docs/guides/chat/managing-tokens) they specifically call out counting tokens on input (as you are billed on these as well as the amount of tokens on...

AndrewMohawk

Addded Word-Level Timestamp Granularity Support

1

Added word-level timestamp granularity support as outlined in the OpenAI API documentation for the transcription endpoint. ref: https://platform.openai.com/docs/api-reference/audio/createTranscription#audio-createtranscription-timestamp_granularities 

LinuxSploit

feat(whisper): add request parameter TimeStampGranularities and respo…

1

**Describe the change** Add new struct field `timestamp_granularities[]` and `words` for whisper transcatiption API **Provide OpenAI documentation link** * [timestamp_granularities[]](https://platform.openai.com/docs/api-reference/audio/createTranscription#audio-createtranscription-timestamp_granularities) * [words](https://platform.openai.com/docs/api-reference/audio/verbose-json-object#audio/verbose-json-object-words) **Describe your solution** Add OpenAI new added parameter...

chenhhA

Your issue may already be reported! Please search on the [issue tracker](https://github.com/sashabaranov/go-openai/issues) before creating one. **Describe the bug** A clear and concise description of what the bug is. If it's...

miaojinsing

0 is a valid value for temperature, top-p in the openAI API, but is not forwarded by go-openai

2

In chat.go and completion.go and edits.go temperature and top P are defined with json modifier omitempty: ``` chat.go: Temperature float32 `json:"temperature,omitempty"` chat.go: TopP float32 `json:"top_p,omitempty"` completion.go: Temperature float32 `json:"temperature,omitempty"` completion.go:...

chrbsg

When using go sdk requests /completions, finish_reason is "" instead of null request vllm directly ``` ... data: {"id":"cmpl-096176162ed84f0e85e6b5aece29f27b","object":"chat.completion.chunk","created":8209815,"model":"public/qwen1-5-72b-chat-int4@main","choices":[{"index":0,"delta":{"content":""},"finish_reason":null}]} data: {"id":"cmpl-096176162ed84f0e85e6b5aece29f27b","object":"chat.completion.chunk","created":8209815,"model":"public/qwen1-5-72b-chat-int4@main","choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}]} data: {"id":"cmpl-096176162ed84f0e85e6b5aece29f27b","object":"chat.completion.chunk","created":8209815,"model":"public/qwen1-5-72b-chat-int4@main","choices":[{"index":0,"delta":{"content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":12,"total_tokens":55,"completion_tokens":43}} ``` Request vllm through go SDK ```...

allenhaozi

How to get JSON mode working for Open AI Vision

2

is there any support for JSON mode in vision preview? i've tried to get it working with `GPT4Turbo1106` as well but it does not work. below is my example ```...

mingsterism