mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-14 04:36:52 +08:00
feat: Add per-model URL overrides for NVIDIA embed and rerank models (#18154)
This commit is contained in:
@@ -107,6 +107,24 @@
|
||||
"support": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "nvidia/llama-3.2-nemoretriever-500m-rerank-v2",
|
||||
"url": "https://ai.api.nvidia.com/v1/retrieval/nvidia/llama-3_2-nemoretriever-500m-rerank-v2/reranking",
|
||||
"content_length": 131072,
|
||||
"max_output": 8192,
|
||||
"model_types": [
|
||||
"rerank"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "nvidia/llama-3.2-nv-rerankqa-1b-v1",
|
||||
"url": "https://ai.api.nvidia.com/v1/retrieval/nvidia/llama-3_2-nv-rerankqa-1b-v1/reranking",
|
||||
"content_length": 131072,
|
||||
"max_output": 8192,
|
||||
"model_types": [
|
||||
"rerank"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "meta/llama-3.3-70b-instruct",
|
||||
"content_length": 131072,
|
||||
@@ -166,6 +184,15 @@
|
||||
"support": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "nvidia/embed-qa-4",
|
||||
"url": "https://ai.api.nvidia.com/v1/retrieval/nvidia/embeddings",
|
||||
"content_length": 131072,
|
||||
"max_output": 8192,
|
||||
"model_types": [
|
||||
"embedding"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "nvidia/ising-calibration-1.5-31b",
|
||||
"content_length": 8192,
|
||||
|
||||
Reference in New Issue
Block a user