CHATBOT WITH MUITL PDF FILE

OVERVIEW

This project shows chatbot with custom data which extract from pdf files, these following libraries i use:

• Langchain
• Cohere
• PyPDF2
• Streamlit

How It Works

The application follows these steps to provide responses to your questions:

1. PDF Loading: The app reads multiple PDF documents and extracts their text content.

2. Text Chunking: The extracted text is divided into smaller chunks that can be processed effectively.

3. Language Model: The application utilizes a language model to generate vector representations (embeddings) of the text chunks.

4. Similarity Matching: When you ask a question, the app compares it with the text chunks and identifies the most semantically similar ones.

5. Response Generation: The selected chunks are passed to the language model, which generates a response based on the relevant content of the PDFs.

The reason i dont choose OpenAI, GEMINI that is COHERE has VietNamese embedding and llm becoming good than each others

Usage

i hope you installed conda, because i create virtual enviroment by anaconda

Step 1: you must get to COHERE_API_KEY and put it to .env. you can get i this link https://cohere.com/

Step 2: you only run one command below :

    Scripts.sh

Step 3: when you run command, Program will nagative to brower to dispaly GUI (Streamlit) . After that, upload PDF FILES that you want before conversation with chatbot

Reference

https://www.langchain.com/

https://github.com/alejandro-ao/ask-multiple-pdfs