go-openai
go-openai copied to clipboard
OpenAI ChatGPT, GPT-3, GPT-4, DALL·E, Whisper API wrapper for Go
such as
OpenAI has released a new model `gpt-4o-audio-preview` which is an end-to-end model for audio input/output. It can be used by chat completion api. Reference: - https://platform.openai.com/docs/guides/audio - https://platform.openai.com/docs/api-reference/chat/create
add request extra_body support like: https://github.com/openai/openai-python/blob/a8fa0def5cd999044dae39b6cdff7a54db25c627/src/openai/resources/batches.py#L48
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** Large model flow returns in the following figure, without content_filter_results information: But...
Background vLLM currently supports various model features through configuration parameters, but lacks support for passing additional model-specific parameters through extra_body, which is particularly important for features like structured output. https://github.com/vllm-project/vllm/blob/v0.6.0/vllm/engine/arg_utils.py#L276...
**Describe the change** We use Litellm and Langfuse and I realized that the `map[string]string` data type in the metadata field is insufficient to pass some trace fields (e.g. tags, trace_metadata)...
Hi - is there any plan to add support for Predicted Outputs to this library? https://platform.openai.com/docs/guides/predicted-outputs I may be missing it, but I don't see support for that parameter either...
The support for batch requests is incomplete. Specifically, the OpenAI API reference specifies that the output files containing the results of the batched operations contain request output objects in the...
Reviewing the documentation of DeepSeek, the example codes use python OpenAi library which indicates API parity with OpenAI. Is there a plan to support DeepSeek models and endpoint? Example: [DeepSeek...
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** When the data returned by SSE streaming starts with "data:" (not "data:...