GenAI-Chatbot

Chat with the Document

GenAI-Chatbot is a Streamlit-based application that allows users to upload PDF and PNG files, process the text content, and interact with a generative AI model to ask questions about the uploaded documents.

Features

• Upload PDF and PNG files: Users can upload multiple PDF and PNG files.
• Text Extraction: Extracts text from PDF files and images using PyPDF2 and pytesseract.
• Text Chunking: Splits extracted text into manageable chunks using RecursiveCharacterTextSplitter.
• Vector Store: Stores text chunks as vectors using FAISS and GoogleGenerativeAIEmbeddings.
• Conversational AI: Uses ChatGoogleGenerativeAI to answer questions based on the uploaded documents.
• Clear Chat: Allows users to clear the chat history and reset the context.

Tech Stack Used

Dependencies

• Streamlit
• PyPDF2
• pytesseract
• FAISS
• Google Generative AI
• langchain_google_genai
• langchain
• Pillow
• python-dotenv

Preview

Local Development

Creae Virtual Environment

pip install virtualenv
python -m venv env

Activate the Virtual Environment

In CMD

.\env\Scripts\activate.bat

1. Install Dependencies:

   pip install -r requirements.txt

Using pytesseract

• Ubuntu sudo-apt install tesseract-ocr

 pytesseract.pytesseract.tesseract_cmd = r'/usr/bin/tesseract'

• Windows
  • Download
  • Set Environment Variable → System Variable → Path → C:\Program Files\Tesseract-OCR

2. Set up Google API Key:

   • You can get Google Api key from Here
     Get API key -> Generative Language Client -> Create API key in existing project.
   • Obtain a Google API key and set it in the .env file.

   GOOGLE_API_KEY=your_api_key_here

3. Run the Application:

   streamlit run app.py