Skip to content

Latest commit

 

History

History
37 lines (20 loc) · 2.02 KB

readme.md

File metadata and controls

37 lines (20 loc) · 2.02 KB
Raw

Language Model Application with Fast and Fresh Vector Search

Won Best Use of AI in Education prize in MLH's Month Long Hackathon Devpost link

Explore it live at: https://vectorizedpdf.streamlit.app/

Video walkthrough - https://www.youtube.com/watch?v=wbDxl9Dk-SA

Demo image

Overview

Welcome to the Language Model Application repository! This application leverages state-of-the-art open-source Language Model (LLM) technology, specifically incorporating models such as openAI's GPT-3.5, Langchain, and Pinecone. The primary focus is on delivering Fast and Fresh Vector Search functionality using Pinecone as a cloud-based vector database.

The application is designed to generate personalized search results for any given document, utilizing advanced language models for enhanced understanding and relevance. Additionally, it empowers users to perform vector similarity searches for questions through a user-friendly interface.

Features

  • Open-Source Language Models: Harness the power of cutting-edge language models such as openAI's GPT-3.5, Langchain, and others to enhance document understanding and search relevance.

  • Fast and Fresh Vector Search: Utilize Pinecone as a cloud-based vector database to achieve high-speed and up-to-date vector searches, ensuring the most relevant results.

  • Personalized Document Search: Generate personalized search results tailored to the content of any document, providing users with highly relevant information.

  • Vector Similarity Search: Allow users to perform vector similarity searches for questions through an intuitive user interface, enhancing the application's versatility.

Getting Started

To get started with the Language Model Application, follow these steps:

  1. Clone the Repository: 
    git clone https://github.com/rkstu/VectorizePDFQA.git
cd VectorizePDFQA