Abstract

This work presents a Retrieval-Augmented Generation (RAG) chatbot for Python learning, leveraging ChromaDB, Sentence Transformers, and Google Gemini 1.5 Flash LLM. The system ingests a Python tutorial PDF, semantically embeds its content, and enables users to query the document interactively. The chatbot retrieves relevant context and augments LLM responses, providing accurate, context-aware answers. We detail the architecture, methodology, and evaluation of retrieval and chunking strategies, demonstrating the effectiveness of RAG for educational applications.

Installation & Usage

Requirements:

Python 3.8+
Streamlit
ChromaDB
Sentence Transformers
Google Gemini API Key

Setup

git clone https://github.com/Hars99/RAG_Based_Assistant_for_python_learning.git
cd RAG_Assistant
python -m venv venv
venv\Scripts\activate  # Windows
pip install -r requirements.txt
python ingest.py
$env:GEMINI_API_KEY="your-gemini-api-key"  # Set your Gemini API key
streamlit run app.py

Introduction

Large Language Models (LLMs) have revolutionized natural language understanding, but their responses are limited by training data. Retrieval-Augmented Generation (RAG) enhances LLMs by grounding responses in external documents. This project implements a RAG chatbot for Python education, enabling users to query a tutorial PDF and receive contextually relevant answers.

Methodology

The system consists of three main modules:
1.Document Ingestion : PDF is chunked and embedded using Sentence Transformers.
2.Vector Database : ChromaDB stores embeddings for efficient semantic retrieval.
3.Chatbot Interface : Streamlit UI interacts with users, retrieves context, and queries Gemini LLM.
The workflow is illustrated in Figure 1.

Memory & Reasoning Mechanism

The chatbot maintains conversational memory and leverages prompt engineering to reformulate user queries. Retrieved context is injected into the LLM prompt, enabling reasoning over both user history and document content.

Query Processing & Retrieval

User queries are embedded and matched against stored chunks in ChromaDB. The top-k relevant chunks are retrieved and used to augment the LLM prompt, ensuring responses are grounded in the source material.

Evaluation of Retrieval

Retrieval effectiveness was measured by the semantic relevance of returned chunks and the accuracy of LLM answers. The system consistently retrieved contextually appropriate passages, improving answer quality.

Results

• Accurate Contextual Answers : The chatbot provided precise, document-grounded responses.
• Efficient Retrieval : ChromaDB enabled fast, semantic search over large documents.
• User Experience : Streamlit UI facilitated interactive learning and transparency of retrieved context.

Conclusion

This RAG-based chatbot demonstrates the power of combining semantic retrieval with LLMs for educational applications. The architecture is modular, scalable, and adaptable to other domains.

Future Work

• Integrate multi-document retrieval.
• Enhance conversational memory for multi-turn reasoning.
• Experiment with alternative LLMs and embedding models.
• Deploy as a cloud service for broader accessibility.