Research-Toolkit

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/
• Gemini Api: https://aistudio.google.com//

Screenshots

Flow Chart

Getting Started

1. Clone the repository:

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

2. Run the Api Server

   cd server
   pip install -r requirements.txt

   python app.py

3. Run the UI

   cd chat-with-pdf-url

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

   NEXT_PUBLIC_API_HOST="http://127.0.0.1:5000/api/v1/bp/"
   NEXT_PUBLIC_GEMINI_API_KEY="<your api key>"
   NEXT_PUBLIC_OPENAI_API_KEY="<your api key>"

   npm install
   npm run dev

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

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