Persistent memory search server — hybrid BM25 + vector search, neural reranking, file watching
-
Updated
May 19, 2026 - TypeScript
#
neural-reranking
Here are 5 public repositories matching this topic...
TREC ROBUST04 ad-hoc retrieval system achieving MAP 0.4044 via a Seeded LLM Tournament (GPT-4o-mini listwise judge) and a Hybrid BM25+RM3+MonoT5+RRF pipeline. MSc final project, Reichman University.
python nlp information-retrieval bm25 query-expansion trec pyserini reciprocal-rank-fusion gpt-4o neural-reranking robust04 llm-reranking monot5
-
Updated
Jun 13, 2026 - Jupyter Notebook
Flowise chatflow implementing a tool-using LLM agent with OpenAI embeddings (3072-dim), Pinecone similarity search, Jina reranking, Tavily API search, document loaders, text splitting, and conversational memory.
large-language-models rag-pipeline conversational-memory neural-reranking agent-tool-routing web-search-integration
-
Updated
Dec 16, 2025
⚡ Enterprise RAG system — BM25 hybrid retrieval, neural re-ranking & sub-second LLM answers via Groq LPU. Built for the OSC AI/ML Hackathon 2026.
react python nlp machine-learning ai hackathon llama bm25 rag fastapi groq llm retrieval-augmented-generation enterprise-ai neural-reranking
-
Updated
Jun 15, 2026 - TypeScript
Project repository for university course in information retrieval
-
Updated
Jan 30, 2026 - Jupyter Notebook
Improve this page
Add a description, image, and links to the neural-reranking topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the neural-reranking topic, visit your repo's landing page and select "manage topics."