https://github.com/sagor0078/building-rag-using-dspy-and-gemini-api
This codebase implements a Retrieval-Augmented Generation (RAG) chatbot using the Gemini API and DSPy framework, designed to answer questions based on the HotPotQA dataset. It includes components for loading data, generating responses, and evaluating model performance through various QA strategies, including basic QA and multi-hop retrieval.
https://github.com/sagor0078/building-rag-using-dspy-and-gemini-api
dspy-ai gemini hotpotqa rag
Last synced: 3 months ago
JSON representation
This codebase implements a Retrieval-Augmented Generation (RAG) chatbot using the Gemini API and DSPy framework, designed to answer questions based on the HotPotQA dataset. It includes components for loading data, generating responses, and evaluating model performance through various QA strategies, including basic QA and multi-hop retrieval.
- Host: GitHub
- URL: https://github.com/sagor0078/building-rag-using-dspy-and-gemini-api
- Owner: Sagor0078
- Created: 2024-11-02T16:33:18.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2024-11-03T06:52:32.000Z (7 months ago)
- Last Synced: 2025-01-11T11:23:13.938Z (4 months ago)
- Topics: dspy-ai, gemini, hotpotqa, rag
- Language: Python
- Homepage:
- Size: 10.7 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# RAG-based Chatbot using Gemini API and DSPy
This project implements a Retrieval-Augmented Generation (RAG) chatbot that utilizes the Gemini API for natural language processing tasks. The chatbot is designed to answer questions based on the HotPotQA dataset, leveraging both retrieval and generative capabilities.
## Features
- **Retrieval-Augmented Generation**: Combines retrieval of relevant context with generative responses.
- **Custom Gemini Model Integration**: Utilizes the Gemini API for generating answers.
- **Local Dataset Handling**: Downloads and caches the HotPotQA dataset locally for efficient access.
- **Multi-hop Querying**: Supports complex queries through a multi-hop retrieval mechanism.
## Requirements
- Python 3.11 or higher
- `dspy` library
- `google-generativeai` library
- `datasets` library
- Other dependencies are managed via `requirements.txt`.
## Installation
1. Clone this repository:
```bash
https://github.com/Sagor0078/building-RAG-using-DSPy-and-Gemini-API.git
```
## Continue..