Contextual Retrieval solves this problem by prepending chunk-specific explanatory context to each chunk before embedding (“Contextual Embeddings”) and creating the BM25 index (“Contextual BM25”).
-
Updated
Sep 29, 2024 - Python
#
contextual-retrieval
Here are 25 public repositories matching this topic...
Contextual RAG over webinar videos using Pinecone, Claude and AWS.
-
Updated
Jul 13, 2026 - Python
RAG-Ingest: A tool for converting PDFs to markdown and indexing them for enhanced Retrieval Augmented Generation (RAG) capabilities.
information-retrieval aws-s3 document-ingestion hybrid-search qdrant llamaindex retrieval-augmented-generation ollama pdf-to-markdown contextual-retrieval qdrant-rag
-
Updated
Nov 22, 2024 - Python
It is a case study of an intelligent agent for Ocean.
-
Updated
Jan 22, 2026 - Python
Enhance your RAG with Contextual Retrieval
-
Updated
Sep 30, 2024 - Python
Production-grade agentic RAG system with LangGraph, hybrid search, async ingestion, multi-user auth, and rich PDF understanding. Built with Gemini 2.5 Flash, FastAPI, Next.js 16, Postgres, pgvector, Redis, and Celery.
redis postgres celery rag fastapi huggingface gemeni hybrid-search llm langchain pgvector langgraph agentic-rag agentic-ai contextual-retrieval nextjs16
-
Updated
Jul 17, 2026 - Python
Shared knowledge layer for human-agent teams. Agents search, classify, and manage knowledge alongside your team.
knowledge-base obsidian ai-agents rag vector-search golden-path hybrid-search azure-openai human-ai-collaboration contextual-retrieval sqlite-vec
-
Updated
Aug 2, 2026 - Python
ContextualRetriever enhances document retrieval accuracy by leveraging Voyage AI models for embedding & reranking models, and the GEMINI model for context and retrieval generation.
-
Updated
Dec 4, 2024 - Python
PDF → Mistral OCR → deterministic AST chunker with Anthropic contextual retrieval for RAG pipelines
-
Updated
Mar 16, 2026 - TypeScript
Chatbot based on Contextual RAG with Hybrid Search and Reranking with short conversation history awareness, fully OpenSource.
-
Updated
Jan 27, 2025 - Python
Anthropic's Contextual Retrieval (2024) implemented and measured: LLM-situated chunks vs plain chunks, contextual embeddings + contextual BM25, reproducible recall@5 benchmark on an ambiguity-engineered corpus. Free local Ollama.
-
Updated
Jul 17, 2026 - Python
Production-grade RAG over Chip Huyen's "AI Engineering" book and blog. Every answer cites its exact source passage and is re-checked by a local NLI model — when evidence is missing, the system declines to answer. Hybrid retrieval (BM25 + embeddings + RRF), reranking, contextual retrieval, and a CI gate that re-checks quality on every push.
python gemini bm25 nli rag weaviate sentence-transformers hybrid-search retrieval-augmented-generation llm-evaluation contextual-retrieval
-
Updated
Jul 17, 2026 - Python
Reproducible benchmark: per-chunk vs per-document contextual retrieval for RAG — cost, speed, and recall/nDCG accuracy on a self-labeled corpus.
benchmark embeddings rag milvus vector-database llm retrieval-augmented-generation contextual-retrieval
-
Updated
Jun 8, 2026 - Python
A LangChain-powered application that parses PDF resumes, converts them into semantic chunks using FAISS, and enables intelligent querying via RAG and Anthropic models. Designed to assist in resume screening through contextual and multi-query retrieval.
resume-parser semantic-search rag llm generative-ai anthropic langchain-python faiss-vector-database contextual-retrieval
-
Updated
Aug 13, 2025 - Python
Rigorous evaluation of contextual retrieval techniques on FinanceBench: comparing 5 embedders × 4 chunking strategies with bootstrapped confidence intervals on FinMTEB and FinanceBench.
python benchmarking natural-language-processing information-retrieval pytorch embeddings semantic-search rag vector-search huggingface sentence-transformers retrieval-augmented-generation llm-evaluation contextual-retrieval late-chunking finance-nlp financebench finmteb
-
Updated
May 12, 2026 - Jupyter Notebook
Self-correcting RAG pipeline built with LangGraph and contextual retrieval. Query rewriting, hybrid retrieval, Cohere reranking, and grounded self-check with retry loops.
python re-ranking claude cohere rag ai-engineering llm langchain anthropic chromadb langgraph contextual-retrieval
-
Updated
May 12, 2026 - Python
Slack Q&A bot template — ingests Slack threads + markdown docs into Pinecone, then an n8n workflow retrieves, re-ranks on metadata, and posts answers back in-thread. Includes contextual retrieval and an eval harness.
starter-template openai slack-bot knowledge-base pinecone rag n8n vector-database llm retrieval-augmented-generation llamaparse contextual-retrieval chatbot-template eval-harness
-
Updated
Jun 9, 2026 - Python
Production-grade RAG service: async document ingestion, hybrid retrieval + reranking, multi-tenant ACL isolation via JWT, guardrails, a two-tier Redis semantic cache, and a Langfuse-native eval harness with a bootstrap-CI regression gate. Framework-free core behind swappable Protocol interfaces.
python redis multi-tenant bm25 reranking rag fastapi vector-search hybrid-search qdrant llm semantic-cache retrieval-augmented-generation langfuse rag-evaluation llm-guardrails nvidia-nim contextual-retrieval
-
Updated
Jul 27, 2026 - Python
Self-hosted contextual RAG on local GPUs: hybrid retrieval with reranking, cited answers, a Next.js chat UI with per-chunk retrieval traces, and full pipeline observability.
-
Updated
Aug 7, 2026 - Python
Improve this page
Add a description, image, and links to the contextual-retrieval topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the contextual-retrieval topic, visit your repo's landing page and select "manage topics."