Skip to content

Latest commit

 

History

History
33 lines (24 loc) · 1.56 KB

README.md

File metadata and controls

33 lines (24 loc) · 1.56 KB

Q-A-Chatbot-System-for-E-learning-Company

image

Purpose

Developed a chatbot Q&A system for e-learning company, to provide instant and accurate answers to learners' questions, enhancing their learning experience

Description:

Designed and developed a chatbot Q&A system leveraging Google PaLM and Langchain, with a userfriendly Streamlit interface. Utilized Hugging Face Instructor Embeddings for text embeddings and FAISS for vector database management. This chatbot system enables learners to ask questions and receive answers in real-time, improving learner engagement and reducing support queries (Streamlit, Langchain, Google Palm LLM, FAISS, RAG (Retrieval-Augmented-Generation), PyCharm)

Project Highlights

  • Use a real CSV file of FAQs that Ed - company is using right now.

  • Their human staff will use this file to assist their course learners.

  • We will build an LLM based question and answer system that can reduce the workload of their human staff.

  • Students should be able to use this system to ask questions directly and get answers within seconds

    Tools

  • Langchain + Google Palm: LLM based Q&A

  • Streamlit: UI

  • Huggingface instructor embeddings: Text embeddings

  • FAISS: Vector databse

Project Structure

  • main.py: The main Streamlit application script.
  • langchain_helper.py: This has all the langchain code
  • requirements.txt: A list of required Python packages for the project.
  • .env: Configuration file for storing your Google API key.