mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-05-28 19:53:06 +08:00
432e966414
### What problem does this PR solve? Closes #15102. OpenAI's Go provider config advertises `whisper-1` as ASR and `tts-1` as TTS, but the Go driver returned `openai, no such method` for both audio paths and did not define `url_suffix.asr` / `url_suffix.tts`. This PR: - adds OpenAI audio URL suffixes for `audio/transcriptions` and `audio/speech` - implements non-streaming `TranscribeAudio` using multipart form uploads - implements non-streaming `AudioSpeech` using the OpenAI speech JSON request shape - keeps streaming TTS explicitly unsupported instead of sending binary audio through the text SSE sender - adds focused tests for config coverage, ASR/TTS request shape, required TTS voice validation, and unsupported streaming TTS ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --------- Co-authored-by: Jin Hai <haijin.chn@gmail.com>
230 lines
3.8 KiB
JSON
230 lines
3.8 KiB
JSON
{
|
|
"name": "OpenAI",
|
|
"url": {
|
|
"default": "https://api.openai.com/v1"
|
|
},
|
|
"url_suffix": {
|
|
"chat": "chat/completions",
|
|
"models": "models",
|
|
"embedding": "embeddings",
|
|
"asr": "audio/transcriptions",
|
|
"tts": "audio/speech"
|
|
},
|
|
"class": "gpt",
|
|
"models": [
|
|
{
|
|
"name": "gpt-5.5",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-5.4",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-5.4-mini",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-5.4-nano",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-5.2-pro",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-5.2",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-5.1",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-5.1-chat-latest",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-5",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-5-mini",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-5-nano",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-5-chat-latest",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-4.1",
|
|
"max_tokens": 1047576,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-4.1-mini",
|
|
"max_tokens": 1047576,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-4.1-nano",
|
|
"max_tokens": 1047576,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-4.5-preview",
|
|
"max_tokens": 128000,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-4o-mini",
|
|
"max_tokens": 128000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-4o",
|
|
"max_tokens": 128000,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-3.5-turbo",
|
|
"max_tokens": 4096,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-3.5-turbo-16k-0613",
|
|
"max_tokens": 16385,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "text-embedding-ada-002",
|
|
"max_tokens": 8191,
|
|
"model_types": [
|
|
"embedding"
|
|
]
|
|
},
|
|
{
|
|
"name": "text-embedding-3-small",
|
|
"max_tokens": 8191,
|
|
"model_types": [
|
|
"embedding"
|
|
]
|
|
},
|
|
{
|
|
"name": "text-embedding-3-large",
|
|
"max_tokens": 8191,
|
|
"model_types": [
|
|
"embedding"
|
|
]
|
|
},
|
|
{
|
|
"name": "whisper-1",
|
|
"max_tokens": 26214400,
|
|
"model_types": [
|
|
"asr"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-4",
|
|
"max_tokens": 8191,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-4-turbo",
|
|
"max_tokens": 8191,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "gpt-4-32k",
|
|
"max_tokens": 32768,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "tts-1",
|
|
"max_tokens": 2048,
|
|
"model_types": [
|
|
"tts"
|
|
]
|
|
}
|
|
]
|
|
}
|