mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-05-22 17:08:23 +08:00
078ea3bf4a
### What problem does this PR solve? 1. **Implement `Nvidia` Provider:** Fully support NVIDIA NIM APIs with robust parameter handling (including the `thinking` parameter) and safe URL merging in `NewInstance`. 2. **Fix Misleading CLI Errors:** Corrected a bug in `common_command.go` where failed chat requests inaccurately reported `failed to list instance models`. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality)
461 lines
8.8 KiB
JSON
461 lines
8.8 KiB
JSON
{
|
|
"name": "Nvidia",
|
|
"url": {
|
|
"default": "https://integrate.api.nvidia.com/v1"
|
|
},
|
|
"url_suffix": {
|
|
"chat": "chat/completions",
|
|
"models": "models"
|
|
},
|
|
"class": "nvidia",
|
|
"models": [
|
|
{
|
|
"name": "abacusai/dracarys-llama-3.1-70b-instruct",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "bytedance/seed-oss-36b-instruct",
|
|
"max_tokens": 32768,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "deepseek-ai/deepseek-v4-flash",
|
|
"max_tokens": 1048576,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "deepseek-ai/deepseek-v4-pro",
|
|
"max_tokens": 1048576,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "deepseek-ai/deepseek-v3.2",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "deepseek-ai/deepseek-v3.1",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "google/codegemma-7b",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "google/gemma-2-2b-it",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "google/gemma-4-31b-it",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "google/gemma-7b",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "ibm/granite-3.3-8b-instruct",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/llama-3.1-405b-instruct",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/llama-3.2-90b-vision-instruct",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/llama-4-maverick-17b-128e-instruct",
|
|
"max_tokens": 1048576,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "microsoft/phi-4-mini-flash-reasoning",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "minimaxai/minimax-m2.1",
|
|
"max_tokens": 204800,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "minimaxai/minimax-m2.5",
|
|
"max_tokens": 204800,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "minimaxai/minimax-m2.7",
|
|
"max_tokens": 204800,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "mistralai/devstral-2-123b-instruct-2512",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "mistralai/magistral-small-2506",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "mistralai/mistral-7b-instruct-v0.3",
|
|
"max_tokens": 32768,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "mistralai/mistral-large-3-675b-instruct-2512",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "mistralai/mistral-medium-3-5-128b",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "mistralai/mistral-nemotron",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "mistralai/mixtral-8x22b-instruct",
|
|
"max_tokens": 65536,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "moonshotai/kimi-k2.5",
|
|
"max_tokens": 262144,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "moonshotai/kimi-k2.6",
|
|
"max_tokens": 262144,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
]
|
|
},
|
|
{
|
|
"name": "moonshotai/kimi-k2-instruct",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "moonshotai/kimi-k2-instruct-0905",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "moonshotai/kimi-k2-thinking",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/gliner-pii",
|
|
"max_tokens": 4096,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.1-nemoguard-8b-content-safety",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.1-nemoguard-8b-topic-control",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.1-nemotron-nano-8b-v1",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.1-nemotron-safety-guard-8b-v3",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.1-nemotron-ultra-253b-v1",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"embedding"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.3-nemotron-super-49b-v1",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/nemoguard-jailbreak-detect",
|
|
"max_tokens": 4096,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-3-nano-30b-a3b",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat",
|
|
"vision"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-3-super-120b-a12b",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-content-safety-reasoning-4b",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/nemotron-mini-4b-instruct",
|
|
"max_tokens": 4096,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/nvidia-nemotron-nano-9b-v2",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/riva-translate-4b-instruct-v1_1",
|
|
"max_tokens": 4096,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "nvidia/usdcode",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "openai/gpt-oss-120b",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "qwen/qwen2.5-coder-7b-instruct",
|
|
"max_tokens": 32768,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "qwen/qwen3-5-122b-a10b",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "qwen/qwen3-235b-a22b",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "qwen/qwen3-coder-480b-a35b-instruct",
|
|
"max_tokens": 262144,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "z-ai/glm-5",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "z-ai/glm-5.1",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
},
|
|
{
|
|
"name": "z-ai/glm-4.7",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"thinking": {
|
|
"default_value": true,
|
|
"clear_thinking": true
|
|
}
|
|
}
|
|
]
|
|
} |