Loading repository data…
vasu-bhai / repository
ChatBot is an AI-powered News Research Assistant that allows users to input article URLs and ask questions based on their content. It uses a Retrieval-Augmented Generation (RAG) pipeline with a local LLM (Ollama) and FAISS vector database to provide accurate, source-backed answers — completely offline.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
An AI-powered news research assistant that answers questions over any set of news article URLs — 100% offline, no API keys required. Paste up to 3 URLs, ask anything, and receive accurate answers with source citations backed by a local LLM.
Live demo: https://news-research-tool-bfx94amauo8sqcu6uxbdd7.streamlit.app/
Add a screenshot or GIF here showing a question being answered with source citations.
User pastes article URLs
↓
Web scraper fetches article text
↓
Text split into chunks (RecursiveCharacterTextSplitter)
↓
Chunks embedded and stored in FAISS vector index
↓
User asks a question
↓
FAISS retrieves the most relevant chunks (similarity search)
↓
Llama 3 (via Ollama) generates a grounded answer with citations
↓
Answer + source URLs displayed in Streamlit
This is a Retrieval-Augmented Generation (RAG) pipeline. The LLM never generates from memory alone — every answer is grounded in the retrieved article text.
llama3.2:1b model. No OpenAI or Anthropic API key needed.User-Agent headers to bypass basic blocks on news sites.faiss_store_ollama/ so you don't re-process URLs on every run.| Component | Technology |
|---|---|
| UI | Streamlit |
| LLM | Llama 3.2 1B (via Ollama) |
| Embeddings | nomic-embed-text (Ollama) |
| Vector DB | FAISS (local) |
| Orchestration |
Selected from shared topics, language and repository description—not editorial ratings.
ADITYA-KUMAR-2358 /
ASK MIRAGE is an offline AI-powered chatbot that allows users to upload PDFs and ask natural language questions. Built with LLaMA, FAISS, and LangChain, it delivers fast, accurate, and context-aware responses without needing an internet connection. Ideal for students and professionals working with large documents.
69/100 healthmudrabhedi /
MediBot is an AI-powered medical chatbot delivering context-aware health answers via an Android app with a Flask backend. It uses advanced LLMs, FAISS vector search, and LangChain to provide accurate, real-time responses based on medical documents.
41/100 health| LangChain |
| Web scraping | UnstructuredURLLoader |
News-Research-Tool/
├── main.py # Streamlit app — UI, scraping, RAG pipeline
├── requirements.txt # Python dependencies
├── .gitignore
├── .env # (not committed) environment variables if needed
└── faiss_store_ollama/ # (auto-generated) local FAISS vector index
# Install Ollama from https://ollama.com/
# Pull the LLM
ollama pull llama3.2:1b
# Pull the embedding model
ollama pull nomic-embed-text
git clone https://github.com/vasu-bhai/News-Research-Tool.git
cd News-Research-Tool
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
streamlit run main.py
App opens at http://localhost:8501.
After processing a few financial news articles:
"What did the Fed announce about interest rates?" "Which companies were mentioned as being affected by the new policy?" "What is the analyst forecast for Q4?"
main.py).MIT — free to use and modify.
fsaavedra0003 /
LangChain PDF Chatbot is an intelligent, conversational assistant built with Python, LangChain, OpenAI's GPT models, and FAISS vector search. It allows users to upload a PDF document and interact with its content through natural language questions, leveraging Retrieval-Augmented Generation (RAG) to deliver accurate, context-aware answers.
34/100 healthJeswin-arul-samuel /
This is an LLM based chatbot that converses with your pdfs and helps summarise and answer questions about your PDF. This application converts your uploaded documents into vectors using openai embeddings and the vectors are stores into a FAISS vectorstore.
38/100 healthc-kiplimo /
FinSage is an AI-powered financial Q&A chatbot that uses a smart routing layer to decide whether to search a knowledge base or answer from conversation context before every response,reducing hallucinations and unnecessary lookups.
56/100 healthHemangini21 /
The Brainlox Chatbot is an intelligent Python-based assistant that leverages embeddings and vector databases to provide context-aware answers by scraping content and interacting through a conversational UI. It uses tools like LangChain, OpenAI, and FAISS for semantic search and response generation.
27/100 health