https://github.com/tharuneshwar-s/research-toolkit-llm

This project introduces an innovative AI-powered chatbot designed to revolutionize how users interact with and extract information from both PDF documents and online content. By leveraging cutting-edge natural language processing, the chatbot offers a seamless, intuitive experience for information access and exploration.
https://github.com/tharuneshwar-s/research-toolkit-llm

flask-api gemini-ai gemini-api gemini-pro langchain nextjs openai-api python python-3

Last synced: 3 months ago
JSON representation

This project introduces an innovative AI-powered chatbot designed to revolutionize how users interact with and extract information from both PDF documents and online content. By leveraging cutting-edge natural language processing, the chatbot offers a seamless, intuitive experience for information access and exploration.

• Host: GitHub
• URL: https://github.com/tharuneshwar-s/research-toolkit-llm
• Owner: tharuneshwar-s
• Created: 2023-11-13T06:01:03.000Z (over 1 year ago)
• Default Branch: v2
• Last Pushed: 2024-05-13T14:20:52.000Z (about 1 year ago)
• Last Synced: 2025-04-09T21:55:23.227Z (3 months ago)
• Topics: flask-api, gemini-ai, gemini-api, gemini-pro, langchain, nextjs, openai-api, python, python-3
• Language: TypeScript
• Homepage:
• Size: 1.81 MB
• Stars: 2
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Research-Toolkit

[![forthebadge made-with-python](http://ForTheBadge.com/images/badges/made-with-python.svg)](https://www.python.org/)

[![made-with-NextJs](https://img.shields.io/badge/Made%20with-NextJs-1f425f.svg)](https://nextjs.org/)

[![OpenAi Api](https://img.shields.io/badge/OpenAI-Api-white.svg)]([https://shields.io/](https://platform.openai.com/))

[![Faiss](https://img.shields.io/badge/Faiss-Package-blue.svg)]([https://shields.io/](https://platform.openai.com/))

[![Python Flask](https://img.shields.io/badge/Python-Flask-yellow.svg)]([https://shields.io/](https://platform.openai.com/))

[![koyeb Hosting](https://img.shields.io/badge/koyeb-Hosting-green.svg)]([https://shields.io/](https://platform.openai.com/))

[![Vercel Hosting](https://img.shields.io/badge/Vercel-Hosting-black.svg)]([https://shields.io/](https://platform.openai.com/))

[![Gemini API](https://img.shields.io/badge/Gemini-API-darkbllue.svg)]([https://shields.io/](https://platform.openai.com/))

## Overview 

The objective of this project is to develop an AI-powered chatbot that revolutionizes user interaction with PDF and online content. Leveraging cutting-edge natural language processing, the chatbot offers a seamless, intuitive experience for information access and exploration. This unified platform simplifies information retrieval, empowering users to engage in insightful conversations with their documents. Additionally, by adopting a semantic search approach, the chatbot can uncover hidden relationships and connections within the data, leading to a deeper understanding of the content.

## Key Features

- **Conversational Interface:** Engage in natural language conversations with your documents, asking questions and receiving accurate answers.

- **Unified Platform:** Seamlessly interact with both PDF documents and website content through a single interface.

- **AI-Powered Question Answering:** Get precise answers to your questions based on the content of the uploaded documents or websites.

- **Semantic Search:** Uncover hidden relationships and connections within the data using advanced semantic search capabilities.

- **Key Information Extraction:** Quickly extract important takeaways, summaries, and insights from complex documents.

- **Time-Saving Efficiency:** Streamline research and analysis tasks by quickly accessing the information you need.

## Technologies Used

**Frontend:**

- **Next.js:** A React framework for building modern, fast, and user-friendly web applications.

**Backend:**

- **Python Flask:** A lightweight and flexible web framework for creating APIs and handling server-side logic.

- **AI and Natural Language Processing:**

Gemini AI (or similar large language model): Advanced AI for natural language understanding, question answering, and text generation.

- **OpenAI Embeddings:** Used to create semantic representations of text, enabling accurate semantic search.

**Data Storage and Search:**

- **Faiss:** An efficient similarity search library for indexing and searching high-dimensional vectors (like embeddings).

## Links

- **OpenAi Api**: [https://platform.openai.com/](https://platform.openai.com/)

- **Gemini Api**: [https://aistudio.google.com//](https://aistudio.google.com/)

## Screenshots

![1](https://github.com/THARUNESHWAR-369/Research-Toolkit-LLM/assets/84437531/e479954e-14c9-4dde-a1ef-2fcc27d064dc)

![2](https://github.com/THARUNESHWAR-369/Research-Toolkit-LLM/assets/84437531/8c57a9a1-406a-4aed-8adb-563fcf03b1d2)

## Flow Chart

![flotchat](https://github.com/THARUNESHWAR-369/Research-Toolkit-LLM/assets/84437531/905afe5f-46ae-45c0-b2ac-f81fc364c339)

## Getting Started

1. Clone the repository: 

    ```bash

    git clone https://github.com/THARUNESHWAR-369/Research-Toolkit-LLM

    cd Research-Toolkit-LLM

    ```

2. Run the Api Server

    ```bash

    cd server

    pip install -r requirements.txt

    ```

    ```bash

    python app.py

    ```

3. Run the UI

    ```bash

    cd chat-with-pdf-url

    ```

    Create a .env.local file and add (for ui):

    ```env

    NEXT_PUBLIC_API_HOST="http://127.0.0.1:5000/api/v1/bp/"

    NEXT_PUBLIC_GEMINI_API_KEY=""

    NEXT_PUBLIC_OPENAI_API_KEY=""

    ```

    ```bash

    npm install

    npm run dev

    ```

4. Access the Api at `http://127.0.0.1:5000`

5. Access the Application at `http://localhost:5173`