Unverified50% confidenceFactExact time
Facebook AI于2017年开源FAISS，引入了IVF-PQ等算法，将十亿级向量检索时间压缩至毫秒级
1
Sources
50%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
Ternlight: A 7MB Browser-Side Embedding Model for Server-Free Semantic Search
hackernewshackernews7/6/2026
Related Claims
Unverified2016年Facebook AI Research发布PyTorch，引入动态计算图（Define-by-Run）机制72% similarUnverifiedFacebook AI Research 于 2017 年提出 DrQA 系统，将 TF-IDF 检索与阅读理解模型结合用于维基百科问答67% similarUnverifiedFacebook AI Research于2019年发布的fairseq S2T系统率先证明了直接从音频到目标语文本的可行性65% similarUnverifiedFAISS (Facebook AI Similarity Search) is a high-performance vector retrieval library open-sourced by Meta, supporting multiple index types such as Flat exact retrieval, IVF inverted index, and HNSW graph index.63% similarPartially VerifiedONNX由微软和Facebook于2017年联合发起，目前已成为AI模型互操作的事实标准63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/262531API
curl https://kongchang.com/api/v1/knowledge/claims/262531MCP
get_claim(id=262531)