Build software better, together

denizzozupek / multi-doc-rag-assistant

Hybrid RAG pipeline (Dense + BM25 + Cross-Encoder Reranker) with conversational memory and systematic evaluation. 5 retrieval experiments, 92.3% Hit Rate, 5.0/5.0 LLM-as-a-Judge. Built with LangChain LCEL & ChromaDB.

python information-retrieval openai rag pydantic vector-search streamlit hybrid-search langchain chromadb llm-evaluation rag-evaluation lcel rag-pipeline rag-chatbot cross-encoder-reranking

Updated Sep 27, 2026
Python

Amruth011 / kannada-rag-agent

Star

A production-grade RAG system and neural voice assistant for low-resource Kannada literature ('Heli Hogu Kaarana'). It features BM25 + ChromaDB hybrid search with page-level routing, Gemini/Groq model fallbacks, and Sarvam AI TTS for streaming audio. Validated using RAGAS with 0.92 Faithfulness and 0.88 Answer Relevancy.

bm25 voice-assistant streamlit vector-database vercel-serverless fastapi-serverless gemini-flash ragas-evaluation rag-architecture bilingual-ai groq-llama rag-evals cross-encoder-reranking kannada-rag sarvam-tts

Updated Aug 22, 2026
Python

DS4AI-UPB / VANGUARD-CLEF2026-JOKER

Star

First-place official system for JOKER 2026 (CLEF) Task 1 English: a three-stage humor retrieval pipeline pairing hybrid sparse-dense retrieval and cross-encoder reranking with a rationale-distilled LLM judge ensemble. 0.6347 MAP. Team VANGUARD.

nlp information-retrieval pytorch lora gemma bm25 puns humor-detection wordplay dense-retrieval llm qlora qwen llm-judge gemma4 clef-2026 cross-encoder-reranking joker-2026 rationale-distillation

Updated Sep 22, 2026
Python

sayednowshad / CortexRAG

Star

CortexRAG: "Memory-Augmented Hybrid Retrieval"

knowledge-graph semantic-search-engine query-expansion fastapi vector-search hybrid-retrieval llm-applications retrieval-augmented-generation-rag conversational-memory cross-encoder-reranking

Updated Jun 20, 2026
Python

ICICLE-ai / icicle-ai-vector-service

Star

Store embeddings, run filtered vector search, and rerank results with MMR or a cross-encoder. Built on FastAPI + Qdrant.

restapi mmr fastapi vector-search qdrant-vector-database mmr-reranking consine-similarity cross-encoder-reranking

Updated Sep 26, 2026
Python

Murali55-09 / ClinicalAssistance

Star

Production-grade Medical RAG Assistant with Hybrid Retrieval (Dense + BM25 + RRF + CrossEncoder), Layered Guardrails, Developer Diagnostics, PDF Evidence Viewer, Langfuse Observability, Offline Evaluation, and Background Knowledge Processing using FastAPI, React, Qdrant, and Celery.

react celery bm25 rag fastapi guardrails medical-ai vector-database qdrant llm langfuse cross-encoder-reranking

Updated Aug 6, 2026
Python

spearb0lt / Context-Aware-Multimodal-Knowledge-Retrieval-System

Star

Multimodal RAG over PDFs. Three parallel pipelines (LLM summaries, raw atomic content, CLIP visual) with HyDE expansion and cross encoder reranking, answers cited inline.

ocr python3 clip pdf-parsing hyde table-extraction rag streamlit vector-database sentence-transformers document-ai llm langchain chromadb retrieval-augmented-generation multimodal-rag docling cross-encoder-reranking

Updated Jul 22, 2026
Jupyter Notebook

SayamAlt / Multi-Domain-Research-Paper-RAG-Pipeline-Evaluation

Star

Successfully developed a multi-domain RAG pipeline that retrieves and answers questions grounded in research papers on lung cancer detection, NSCLC microbiome classification, and Bhutan land cover, with a full safety evaluation suite covering toxicity, information leakage, and scope adherence using DeepEval.

nlp python3 openai ai-safety faiss rag vector-search research-papers streamlit llm langchain prompt-injection retrieval-augmented-generation llm-evaluation safety-evaluation gpt-4o-mini deepeval deepeval-metrics cross-encoder-reranking

Updated Sep 19, 2026
Python

SayamAlt / RAG-Evaluation-using-DeepEval

Star

Successfully implemented a retrieval evaluation pipeline that tests how well a RAG system finds relevant call center transcript chunks, using contextual precision and recall as metrics.

nlp evaluation openai evaluation-metrics reranking rag vector-search llm generative-ai langchain chromadb retrieval-augmented-generation deepeval cross-encoder-reranking

Updated Sep 19, 2026
Python

rahulboby / ChatVeritas

Star

Built an advanced Retrieval-Augmented Generation (RAG) system utililzing text datasets chunked dynamically. Engineered a dual-stage retrieval pipeline using all-MiniLM-L6-v2 embeddings to pull 20 FAISS candidates, refined via Cross-Encoders to feed the top 5 most relevant chunks to the LLM Synthesized context with a fine-tuned Qwen2.5-1.5B-Instruct

transformers fine-tuning vector-database low-rank-adaptation retrieval-augmented-generation cross-encoder-reranking

Updated Sep 30, 2026
Python

Navigation Menu

cross-encoder-reranking

Here are 10 public repositories matching this topic...

denizzozupek / multi-doc-rag-assistant

Amruth011 / kannada-rag-agent

DS4AI-UPB / VANGUARD-CLEF2026-JOKER

sayednowshad / CortexRAG

ICICLE-ai / icicle-ai-vector-service

Murali55-09 / ClinicalAssistance

spearb0lt / Context-Aware-Multimodal-Knowledge-Retrieval-System

SayamAlt / Multi-Domain-Research-Paper-RAG-Pipeline-Evaluation

SayamAlt / RAG-Evaluation-using-DeepEval

rahulboby / ChatVeritas

Add this topic to your repo