mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-25 09:53:29 +08:00
17d71e5d79
### What problem does this PR solve? ``` RAGFlow(user)> embed text 'what is rag' 'who are you' with 'embedding-3@test@zhipu-ai' dimension 16; +-----------+-------+ | dimension | index | +-----------+-------+ | 16 | 0 | | 16 | 1 | +-----------+-------+ RAGFlow(user)> rerank query 'what is rag' document 'rag is retrieval augment generation' 'rag need llm' 'famous rag project includes ragflow' with 'rerank@test@zhipu-ai' top 2; +-------+-----------------+ | index | relevance_score | +-------+-----------------+ | 0 | 1 | | 2 | 0.99999976 | +-------+-----------------+ ``` ### Type of change - [x] New Feature (non-breaking change which adds functionality) Signed-off-by: Jin Hai <haijin.chn@gmail.com>
270 lines
4.7 KiB
JSON
270 lines
4.7 KiB
JSON
{
|
|
"name": "ZHIPU-AI",
|
|
"url": {
|
|
"default": "https://open.bigmodel.cn/api/paas/v4"
|
|
},
|
|
"url_suffix": {
|
|
"chat": "chat/completions",
|
|
"async_chat": "async/chat/completions",
|
|
"async_result": "async-result",
|
|
"embedding": "embeddings",
|
|
"rerank": "rerank",
|
|
"files": "files"
|
|
},
|
|
"class": "glm",
|
|
"models": [
|
|
{
|
|
"name": "glm-5",
|
|
"max_tokens": 204800,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-5-turbo",
|
|
"max_tokens": 204800,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-5v-turbo",
|
|
"max_tokens": 204800,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4.7",
|
|
"max_tokens": 204800,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4.7-flashx",
|
|
"max_tokens": 204800,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4.6",
|
|
"max_tokens": 204800,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4.6v-Flash",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4.5",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4.5-x",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4.5-air",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4.5-airx",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4.5-flash",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4.5v",
|
|
"max_tokens": 64000,
|
|
"model_types": [
|
|
"vision"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4-plus",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-4-0520",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-4",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-4-airx",
|
|
"max_tokens": 8000,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-4-air",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-4-flash",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-4-flashx",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-4-long",
|
|
"max_tokens": 1000000,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-4v",
|
|
"max_tokens": 2000,
|
|
"model_types": [
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-4-9b",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "embedding-2",
|
|
"max_tokens": 512,
|
|
"model_types": [
|
|
"embedding"
|
|
]
|
|
},
|
|
{
|
|
"name": "embedding-3",
|
|
"max_tokens": 512,
|
|
"model_types": [
|
|
"embedding"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-asr-2512",
|
|
"max_tokens": 4096,
|
|
"model_types": [
|
|
"asr"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-tts",
|
|
"model_types": [
|
|
"tts"
|
|
]
|
|
},
|
|
{
|
|
"name": "glm-ocr",
|
|
"model_types": [
|
|
"ocr"
|
|
]
|
|
},
|
|
{
|
|
"name": "rerank",
|
|
"model_types": [
|
|
"rerank"
|
|
]
|
|
}
|
|
]
|
|
} |