Shadowgraph
TrendingAbout
Sign in

TiannuoYang/hnsw_index

Dataset

This is the vector index file of our paper SearchAgent-X. It contains a HNSW-based index file of approxiamte nearest neighbor search built for Wikipedia English corpus.

1

3 commits

2 linked in READMEs

updated Jul 2, 2025

See the code

README

This is the vector index file of our paper SearchAgent-X. It contains a HNSW-based index file of approxiamte nearest neighbor search built for Wikipedia English corpus.

Details of this dataset:

  • Chunked Text: wiki-18-corpus
  • Embedding Model: all-MiniLM-L6-v2
  • HNSW Implementation Base: HNSWLib
  • Indexing Params:
    • 32 neighbors per node (i.e., M)
    • candidate list of 500 (i.e., efConstruction)

DIY: How to Encode and Index Your Own Corpus?
😄 Follow our github instructions and code here

arxiv.org/abs/2505.12065

Contributors

TiannuoYang

3 commits

Similar repos

Intelligent-Internet/wikipedia_en

Dataset

`wikipedia_en`

2

matchyc/vector-search-papers

📚 Awesome papers and technical blogs on vector DB (database), semantic-based vector search or…

117

Agrover112/awesome-semantic-search

A curated list of awesome resources related to Semantic Search🔎 and Semantic Similarity tasks.

366

vector-index-bench/vibe

Vector Index Benchmark for Embeddings (VIBE) is an extensible benchmark for approximate nearest…

73

SimoneZeng/awesome-vector-ANN-search-papers

A list of papers in the field of approximate nearest neighbor search on high-dimensional vectors.

141

yyu/wiki_corpus

Dataset

0

i2plus/WikiSeeker-Data

Dataset

1

vector-index-bench/vibe

Dataset

This repository contains the datasets presented in [VIBE: Vector Index Benchmark for…

2

Linked in READMEs

nmslib/hnswlib

Header-only C++/python library for fast approximate nearest neighbors

5,332

README badge

tiannuo-yang/SearchAgent-X

A High-Efficiency System of Large Language Model Based Search Agents

80

README badge

TiannuoYang/hnsw_index

Dataset

This is the vector index file of our paper SearchAgent-X. It contains a HNSW-based index file of approxiamte nearest neighbor search built for Wikipedia English corpus.

1

3 commits

2 linked in READMEs

updated Jul 2, 2025

See the code

README

This is the vector index file of our paper SearchAgent-X. It contains a HNSW-based index file of approxiamte nearest neighbor search built for Wikipedia English corpus.

Details of this dataset:

  • Chunked Text: wiki-18-corpus
  • Embedding Model: all-MiniLM-L6-v2
  • HNSW Implementation Base: HNSWLib
  • Indexing Params:
    • 32 neighbors per node (i.e., M)
    • candidate list of 500 (i.e., efConstruction)

DIY: How to Encode and Index Your Own Corpus?
😄 Follow our github instructions and code here

arxiv.org/abs/2505.12065

Similar repos

Intelligent-Internet/wikipedia_en

Dataset

`wikipedia_en`

2

matchyc/vector-search-papers

📚 Awesome papers and technical blogs on vector DB (database), semantic-based vector search or…

117

Agrover112/awesome-semantic-search

A curated list of awesome resources related to Semantic Search🔎 and Semantic Similarity tasks.

366

vector-index-bench/vibe

Vector Index Benchmark for Embeddings (VIBE) is an extensible benchmark for approximate nearest…

73

SimoneZeng/awesome-vector-ANN-search-papers

A list of papers in the field of approximate nearest neighbor search on high-dimensional vectors.

141

yyu/wiki_corpus

Dataset

0

i2plus/WikiSeeker-Data

Dataset

1

vector-index-bench/vibe

Dataset

This repository contains the datasets presented in [VIBE: Vector Index Benchmark for…

2

Linked in READMEs

nmslib/hnswlib

Header-only C++/python library for fast approximate nearest neighbors

5,332

README badge

tiannuo-yang/SearchAgent-X

A High-Efficiency System of Large Language Model Based Search Agents

80

README badge

Contributors

TiannuoYang

3 commits