VikParuchuri/researcher
Concise answers to search queries using Google and GPT-3. Includes citations.
ArchivedImplements a retrieval-augmented generation pipeline that scrapes Google results, extracts ranked text chunks via semantic matching, and feeds them to GPT-3 for summarization—eliminating hallucinations through grounded context. Supports both web scraping and Google Custom Search API modes, stores scraped HTML in SQLite for efficiency, and filters low-quality sources by ad/tracker density. Runs as a Flask web application with configurable chunk length and result counts to balance latency (10-20s per query) against summary quality.
No commits in the last 6 months.
Stars
82
Forks
6
Language
Python
License
MIT
Category
Last pushed
Dec 28, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/VikParuchuri/researcher"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
clstaudt/ragadoc
An AI document assistant that answers questions about your PDFs with citations and highlights...
Arnav000007/llmwalk
🧠Explore prompts and discover the top responses with LLMWalk, optimizing answer retrieval using...
dilzilla/LlamaSum
Simple Summarizer Tool using Llama 3 8b.
catherinewbaker/ChatbotPersonalityPreference
An academic literature review performed on the personality preferences in chatbot assistants...
gugacamara/local-rag-assistant
100% local Retrieval-Augmented Generation (RAG) chat assistant to interact with PDF files. Ask...