Expired85% confidenceFactTime unknown
RAGFlow recommends using DeepSeek V3 as the conversational model, Youdao Embedding as the embedding model, and DeepSeek-VL2 as the image-to-text model.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThis GraphRAG system uses DeepSeek V3 as the large language model.76% similarVerifiedDeepSeek V4 adopts a Mixture of Experts (MoE) architecture.72% similarUnverifiedDeepSeek R1 and GPT's o1/o3-mini are base large models, while the DeepSeek chat interface and ChatGPT are conversational products developed on top of base models.72% similarVerifiedDeepSeek Chat corresponds to the V3 model, and DeepSeek Reasoner corresponds to the R1 model.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/22096API
curl https://kongchang.com/api/v1/knowledge/claims/22096MCP
get_claim(id=22096)