Cross-Encoder-with-Bi-Encoder를 활용한 WebPage 데모
-
Updated
Dec 10, 2021 - Python
Cross-Encoder-with-Bi-Encoder를 활용한 WebPage 데모
PaperLens AI is a full-stack research assistant that helps you analyze papers, ask grounded questions, detect gaps, and generate experiment plans or research problem statements.
Llama RAG app to chat with Applicants' Resume and Extension for LinkedIn
SentencePiece tokenizer for cross-encoders
AI-powered Advanced Hybrid RAG for intelligent knowledge retrieval.
ViSecRAG: A comprehensive Retrieval-Augmented Generation framework featuring semantic-aware data chunking, vector-based retrieval, and fine-tuned embedding models optimized for Vietnamese language security and information extraction tasks.
RAG Framework Implementation (Retriever/Reranker Fine-Tuning & Inference)
CommitIt is an AI-powered GitHub repository assistant that enables developers to chat with any repository using natural language. It analyzes repository content, builds a searchable knowledge base, retrieves relevant code and documentation, and generates context-aware answers with source citations using hybrid retrieval and local LLMs.
2024 AI CUP Competition on E.SUN AI Open Challenge-Applications of RAG and LLM in Financial Question Answering
Hybrid RAG system (BM25 + Qdrant dense search + RRF) with cross-encoder reranking, ablation-tested retrieval, page-cited document upload, and full CI/CD.
A generative AI based smart information retrieval system featuring Hybrid Contextual Search,
Academic RAG assistant using BM25, FAISS, reciprocal-rank fusion, CrossEncoder reranking, FastAPI, and local LLM generation.
conversational rag with production features
Developing a retrieval system using semantic vector search.
Production-grade RAG platform with hybrid dense + BM25 retrieval, cross-encoder reranking, citation verification. and 3D Confidence scoring. 100% local via Ollama — zero cloud cost, zero data leakage.
A RAG system that replaces standard BM25/FAISS retrieval with a fully learned neural retrieval stack - including a fine-tuned bi-encoder, a cross-encoder reranker, ColBERT-style late interaction scoring, and a locally hosted LLM generator. Built entirely with free and open-source tools.
RAG-based AI legal assistant using hybrid retrieval and local LLM inference.
RAG + Text-to-SQL conversational analytics over Inside Airbnb data for Rome, powered by Databricks (Vector Search, SQL Warehouse, Delta Lake), FastAPI, and React.
Legal AI Assistant for Indian Law – A Hybrid RAG platform (FastAPI + React) built with Google Gemini 3.5 Flash, Dense Embeddings, and Cross-Encoder Reranking to make Indian legal statutes, contracts, and court procedures accessible in plain English.
Hybrid RAG pipeline featuring dense + sparse (BM25) search, RRF fusion, cross-encoder reranking, and automated end-to-end evaluation with Ragas metrics.
To associate your repository with the crossencoder topic, visit your repo's landing page and select "manage topics."