mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-06 11:28:38 +08:00
e20cf39735
### What problem does this PR solve? 1. Refactor model provider json file format 2. Use memory data structure to replace database 3. Add CLI command to access ``` RAGFlow(user)> list pool models from 'xai'; +-------------------------------------------------------------------------------------+------------+-------------+-----------------------+ | features | max_tokens | model_types | name | +-------------------------------------------------------------------------------------+------------+-------------+-----------------------+ | map[] | 256000 | [llm] | grok-4 | | map[] | 131072 | [llm] | grok-3 | | map[] | 131072 | [llm] | grok-3-fast | | map[] | 131072 | [llm] | grok-3-mini | | map[] | 131072 | [llm] | grok-3-mini-mini-fast | | map[multimodal:map[enabled:true input_modalities:[image] output_modalities:[text]]] | 32768 | [vlm] | grok-2-vision | +-------------------------------------------------------------------------------------+------------+-------------+-----------------------+ RAGFlow(user)> show pool model 'grok-2-vision' from 'xai'; +-------------------------------------------------------------------------------------+------------+-------------+---------------+ | features | max_tokens | model_types | name | +-------------------------------------------------------------------------------------+------------+-------------+---------------+ | map[multimodal:map[enabled:true input_modalities:[image] output_modalities:[text]]] | 32768 | [vlm] | grok-2-vision | +-------------------------------------------------------------------------------------+------------+-------------+---------------+ RAGFlow(user)> list pool providers; +--------+------------------------------------------------------------+---------------------------+ | name | tags | url | +--------+------------------------------------------------------------+---------------------------+ | OpenAI | LLM,TEXT EMBEDDING,TTS,TEXT RE-RANK,SPEECH2TEXT,MODERATION | https://api.openai.com/v1 | | xAI | LLM | https://api.x.ai/v1 | +--------+------------------------------------------------------------+---------------------------+ RAGFlow(user)> show pool provider 'openai'; +---------------------------+--------+------------------------------------------------------------+--------------+ | base_url | name | tags | total_models | +---------------------------+--------+------------------------------------------------------------+--------------+ | https://api.openai.com/v1 | OpenAI | LLM,TEXT EMBEDDING,TTS,TEXT RE-RANK,SPEECH2TEXT,MODERATION | 27 | +---------------------------+--------+------------------------------------------------------------+--------------+ ``` ### Type of change - [x] New Feature (non-breaking change which adds functionality) - [x] Refactoring --------- Signed-off-by: Jin Hai <haijin.chn@gmail.com>
239 lines
4.0 KiB
JSON
239 lines
4.0 KiB
JSON
{
|
|
"name": "OpenAI",
|
|
"tags": "LLM,TEXT EMBEDDING,TTS,TEXT RE-RANK,SPEECH2TEXT,MODERATION",
|
|
"url": "https://api.openai.com/v1",
|
|
"models": [
|
|
{
|
|
"name": "gpt-5.2-pro",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-5.2",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-5.1",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-5.1-chat-latest",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-5",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-5-mini",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-5-nano",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-5-chat-latest",
|
|
"max_tokens": 400000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-4.1",
|
|
"max_tokens": 1047576,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-4.1-mini",
|
|
"max_tokens": 1047576,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-4.1-nano",
|
|
"max_tokens": 1047576,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-4.5-preview",
|
|
"max_tokens": 128000,
|
|
"model_types": [
|
|
"llm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "o3",
|
|
"max_tokens": 200000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "o4-mini",
|
|
"max_tokens": 200000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "o4-mini-high",
|
|
"max_tokens": 200000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-4o-mini",
|
|
"max_tokens": 128000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-4o",
|
|
"max_tokens": 128000,
|
|
"model_types": [
|
|
"llm",
|
|
"vlm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-3.5-turbo",
|
|
"max_tokens": 4096,
|
|
"model_types": [
|
|
"llm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-3.5-turbo-16k-0613",
|
|
"max_tokens": 16385,
|
|
"model_types": [
|
|
"llm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "text-embedding-ada-002",
|
|
"max_tokens": 8191,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "text-embedding-3-small",
|
|
"max_tokens": 8191,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "text-embedding-3-large",
|
|
"max_tokens": 8191,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "whisper-1",
|
|
"max_tokens": 26214400,
|
|
"model_types": [
|
|
"speech2text"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-4",
|
|
"max_tokens": 8191,
|
|
"model_types": [
|
|
"llm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-4-turbo",
|
|
"max_tokens": 8191,
|
|
"model_types": [
|
|
"llm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "gpt-4-32k",
|
|
"max_tokens": 32768,
|
|
"model_types": [
|
|
"llm"
|
|
],
|
|
"features": {}
|
|
},
|
|
{
|
|
"name": "tts-1",
|
|
"max_tokens": 2048,
|
|
"model_types": [
|
|
"tts"
|
|
],
|
|
"features": {}
|
|
}
|
|
]
|
|
} |