RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Go agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
feat: Add per-model URL overrides for NVIDIA embed and rerank models (#18154)
mkaaad401f943ca383
diff --git a/conf/models/nvidia.json b/conf/models/nvidia.jsonindex 5b10ec9822..df953a33c8 100644--- a/conf/models/nvidia.json+++ b/conf/models/nvidia.json@@ -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,