async-openai
async-openai copied to clipboard
64bit
Rust library for OpenAI
Error: JSONDeserialize(Error("missing field `illicit`", line: 19, column: 7)) ```rust use async_openai::{types::CreateModerationRequestArgs, Client}; use std::error::Error; #[tokio::main] async fn main() -> Result { let client = Client::new(); let model = "text-moderation-latest"; //...
fixed the error that some openai compatible api's response don't have "object" field
https://ai.google.dev/gemini-api/docs/openai Create a self contained `examples/gemini` which demonstrate usage of this library for all samples listed on https://ai.google.dev/gemini-api/docs/openai. This library should work as is if Gemini "OpenAI compatibility" is fully...
[Spec](https://platform.openai.com/docs/api-reference/realtime-server-events/conversation/item/input_audio_transcription) input_audio_transcription object language string Optional The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. en) format will improve accuracy and latency. model string Optional The...
https://github.com/64bit/async-openai/issues/349#issue-2916029810
OpenAI session error: Invalid value: 'g711-ulaw'. Supported values are: 'pcm16', 'g711_ulaw', and 'g711_alaw'. [Spec](https://platform.openai.com/docs/api-reference/realtime-sessions/create) input_audio_format string Optional The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16,...
Potentially a bug in macro where doc comment is generated twice For example: > Retrieves an assistant. Retrieves an assistant. https://docs.rs/async-openai/0.28.0/async_openai/struct.Assistants.html#method.retrieve
when marshal the detail field to '"detail": null', it will break vllm openai api server ``` 3月 07 16:43:07 mymachine llama-swap[2425068]: ERROR 03-07 16:43:07 serving_chat.py:197] Error in preprocessing prompt inputs...
This Fixes Crash when a run is using an assistant with file search enabled
Fixes issue mentioned in #340
