Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,3 +11,41 @@ pinned: false
|
|
| 11 |
---
|
| 12 |
|
| 13 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
| 14 |
+
# GamerRadar: Video Game Recommendation System using RAG
|
| 15 |
+
|
| 16 |
+
GamerRadar is an intelligent video game recommendation assistant built using a Retrieval-Augmented Generation (RAG) pipeline. The system allows users to input their gaming preferences or games they previously enjoyed, and it retrieves contextually relevant recommendations from a specialized dataset.
|
| 17 |
+
|
| 18 |
+
This project was developed as part of the Generative AI Bootcamp to demonstrate practical implementation of document indexing, vector databases, LLM orchestration, and interactive user interfaces.
|
| 19 |
+
|
| 20 |
+
## Features
|
| 21 |
+
|
| 22 |
+
- Custom Dataset Integration: Uses a curated dataset of video games containing titles, genres, and detailed descriptions.
|
| 23 |
+
- Open-Source Embeddings: Leverages Hugging Face sentence-transformers for local text embedding generation without API costs.
|
| 24 |
+
- Vector Storage: Implements ChromaDB as a local vector database to store and perform similarity searches on game documents.
|
| 25 |
+
- LLM Pipeline: Utilizes LangChain Expression Language (LCEL) to create a robust RAG pipeline powered by Google Gemini 2.5 Flash.
|
| 26 |
+
- Interactive UI: Features a web-based chat interface deployed via Gradio for real-time user interaction.
|
| 27 |
+
|
| 28 |
+
## Tech Stack
|
| 29 |
+
|
| 30 |
+
- Framework: LangChain / LangChain Community Core
|
| 31 |
+
- Embedding Model: Hugging Face (all-MiniLM-L6-v2)
|
| 32 |
+
- Vector Store: ChromaDB
|
| 33 |
+
- Large Language Model: Google Gemini 2.5 Flash (via Google AI Studio)
|
| 34 |
+
- User Interface: Gradio
|
| 35 |
+
- Data Management: Pandas
|
| 36 |
+
|
| 37 |
+
## Project Structure and Pipeline
|
| 38 |
+
|
| 39 |
+
1. Data Preparation: A dataset of video games is initialized and saved to a local CSV file.
|
| 40 |
+
2. Document Loading: The CSV data is extracted and parsed into structured LangChain Document objects.
|
| 41 |
+
3. Embedding and Indexing: The documents are processed through the Hugging Face embedding model and indexed inside ChromaDB.
|
| 42 |
+
4. Retrieval and Prompting: A custom system prompt is configured to instruct the assistant. A retriever fetches the top 2 most similar games based on the user's input.
|
| 43 |
+
5. Generation: The retrieved game contexts and the user query are passed through an LCEL pipeline to Gemini 2.5 Flash to generate accurate, context-aware recommendations.
|
| 44 |
+
6. Interface Deployment: The entire workflow is wrapped into a Gradio ChatInterface, launching a local widget and a shareable public URL.
|
| 45 |
+
|
| 46 |
+
## Setup and Installation
|
| 47 |
+
|
| 48 |
+
To run this notebook in Google Colab or a local Python environment, install the required dependencies:
|
| 49 |
+
|
| 50 |
+
```bash
|
| 51 |
+
pip install langchain langchain-community langchain-chroma langchain-google-genai sentence-transformers gradio pandas
|