DmitryKey/bert-solr-search
Search with BERT vectors in Solr, Elasticsearch, OpenSearch and GSI APU
Leverages BERT embeddings via bert-as-service to generate dense vector representations, then indexes and queries them across multiple search engines using engine-specific optimizations—Solr's vector scoring plugin, Elasticsearch's native dense_vector type with elastiknn plugin support, and OpenSearch's nmslib-based HNSW graphs. Includes Streamlit demos and result diversity algorithms for semantic search at scale across 5+ million DBPedia abstracts.
166 stars. No commits in the last 6 months.
Stars
166
Forks
31
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Aug 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/DmitryKey/bert-solr-search"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
machinelearningZH/semantic-search-eval
A framework for evaluating semantic search across custom datasets, metrics, and embedding backends.
tkhang1999/semantic-food-search
A semantic food search web application built with Django, Solr, SBERT, and Docker
alihakimtaskiran/SemanticSearch
Meaningful Search
yberreby/ocaml-semsearch-jsoo
OCaml + js_of_ocaml + SBERT + TensorFlow.js
AxelPCG/SPLADE-PT-BR
SPLADE (Sparse Lexical AnD Expansion) model fine-tuned for Portuguese text retrieval. Based on...