mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-13 20:26:51 +08:00
1b02abd487
Some NVIDIA hosted models (e.g. meta/llama-3.2-11b-vision-instruct )
expose a full
endpoint URL per model that does not follow the normal base_url +
url_suffix
assembly. Previously the Go driver always called {base}/chat/completions
, so chat
requests for these vision models hit the wrong endpoint and failed.
This PR adds an optional per-model url field in conf/models/nvidia.json
. When
present, every NVIDIA driver request (chat, streaming chat, embedding,
rerank, model
listing) uses it directly; otherwise the standard assembly is unchanged.
404 lines
8.0 KiB
JSON
404 lines
8.0 KiB
JSON
{
|
|
"name": "NVIDIA",
|
|
"url": {
|
|
"default": "https://integrate.api.nvidia.com/v1"
|
|
},
|
|
"url_suffix": {
|
|
"chat": "chat/completions",
|
|
"models": "models",
|
|
"embedding": "embeddings",
|
|
"rerank": "ranking"
|
|
},
|
|
"class": "nvidia",
|
|
"models": [
|
|
{
|
|
"name": "deepseek-ai/deepseek-v4-flash",
|
|
"content_length": 1048576,
|
|
"max_output": 393216,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "deepseek-ai/deepseek-v4-pro",
|
|
"content_length": 1048576,
|
|
"max_output": 393216,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "google/diffusiongemma-26b-a4b-it",
|
|
"content_length": 262144,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "google/gemma-4-31b-it",
|
|
"content_length": 262144,
|
|
"max_output": 262144,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "meta/llama-3.1-70b-instruct",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/llama-3.1-8b-instruct",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/llama-3.2-11b-vision-instruct",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"url":"https://integrate.api.nvidia.com/v1/meta/llama-3.2-11b-vision-instruct",
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/llama-3.2-1b-instruct",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/llama-3.2-3b-instruct",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/llama-3.2-90b-vision-instruct",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"url":"https://integrate.api.nvidia.com/v1/meta/llama-3.2-90b-vision-instruct",
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "meta/llama-3.3-70b-instruct",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/llama-guard-4-12b",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "minimaxai/minimax-m3",
|
|
"content_length": 1048576,
|
|
"max_output": 16384,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "mistralai/mistral-medium-3.5-128b",
|
|
"content_length": 262144,
|
|
"max_output": 262144,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "mistralai/mistral-nemotron",
|
|
"content_length": 131072,
|
|
"max_output": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "moonshotai/kimi-k2.6",
|
|
"content_length": 262144,
|
|
"max_output": 131072,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/ising-calibration-1.5-31b",
|
|
"content_length": 8192,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.1-nemotron-nano-8b-v1",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.1-nemotron-nano-vl-8b-v1",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.1-nemotron-safety-guard-8b-v3",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.3-nemotron-super-49b-v1",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
},
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-3-embed-1b",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"max_batch_size": 32
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-3-nano-30b-a3b",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
},
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-3-super-120b-a12b",
|
|
"content_length": 262144,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-3-ultra-550b-a55b",
|
|
"content_length": 262144,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-3.5-content-safety",
|
|
"content_length": 8192,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-mini-4b-instruct",
|
|
"content_length": 8192,
|
|
"max_output": 4096,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-nano-12b-v2-vl",
|
|
"content_length": 8192,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/nv-embed-v1",
|
|
"max_tokens": 32768,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"max_batch_size": 32
|
|
},
|
|
{
|
|
"name": "nvidia/nv-embedcode-7b-v1",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"max_batch_size": 32
|
|
},
|
|
{
|
|
"name": "nvidia/nvidia-nemotron-nano-9b-v2",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/riva-translate-4b-instruct-v2",
|
|
"content_length": 8192,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "openai/gpt-oss-120b",
|
|
"content_length": 131072,
|
|
"max_output": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "openai/gpt-oss-20b",
|
|
"content_length": 131072,
|
|
"max_output": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "poolside/laguna-xs-2.1",
|
|
"content_length": 262144,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "stepfun-ai/step-3.7-flash",
|
|
"content_length": 32768,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "thinkingmachines/inkling",
|
|
"content_length": 8192,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "z-ai/glm-5.2",
|
|
"content_length": 1000000,
|
|
"max_output": 128000,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
}
|
|
]
|
|
}
|