{"repo":"redis-developer/ArXivChatGuru","free":true,"listed":false,"github":"https://github.com/redis-developer/ArXivChatGuru","clone":"git clone https://github.com/redis-developer/ArXivChatGuru.git","description":"Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache.","language":"Python","stars":562,"topics":["ai","machine-learning","openai","python","question-answering","redis","vector-search","langchain","arxiv","rag"],"license":"MIT","category":"ai-agents","readme_excerpt":"ArXiv ChatGuru ArXiv ChatGuru is a Streamlit app that turns a topic from arXiv into a topic-scoped Redis vector index. It fetches papers, chunks them, stores embeddings in Redis, and lets you ask grounded questions against the papers you loaded. This app is a learning project for academic RAG. It is intentionally simple and is meant to show how Redis fits into a paper Q&A workflow, not to act as a production-ready research assistant. What Redis does in this app - Stores topic-specific paper chunks and embeddings - Powers vector search for retrieval - Lets you inspect the active index from the built-in stats page How it works 1. Enter a topic and choose how many papers to load. 2. The app pulls papers from arXiv and splits them into chunks. 3. OpenAI generates embeddings for those chunks. 4. Redis stores the chunks and embeddings in a topic-scoped index. 5. LangChain retrieves the closest chunks for each user question and sends that context to the chat model. Prerequisites - Python 3.13 for local development - Docker Desktop if you want the Docker-first flow - An OpenAI API key Environment setup Create a .env file from the template: Then set at least: The default template uses: - OPENAI CHAT MODEL=gpt-4.1-mini - OPENAI EMBEDDING MODEL=text-embedding-3-small - REDIS INDEX BASENAME=arxiv - REDIS URL=redis://arxivchatguru-redis:6379 Run with Docker Docker is the primary local path. Then open: To stop the stack: Run locally Install Poetry if you do not already have it: Use Python ","default_branch":null,"files":null,"tree":[],"storefront":"/r/redis-developer","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/redis-developer/ArXivChatGuru/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}