Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
@@ -1,12 +1,96 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
# Website RAG Chatbot
|
3 |
+
This project implements a Retrieval-Augmented Generation (RAG) system using Langchain, Google's Generative AI, and Gradio. It creates a chatbot interface that answers questions based on information retrieved from a pre-processed set of web pages.
|
4 |
+
|
5 |
+
## Features
|
6 |
+
|
7 |
+
- Web-based chatbot interface using Gradio
|
8 |
+
- RAG system powered by Langchain and Google's Generative AI
|
9 |
+
- Local FAISS vector store for efficient information retrieval
|
10 |
+
- Customizable UI with CSS styling
|
11 |
+
|
12 |
+
## Prerequisites
|
13 |
+
|
14 |
+
- Python 3.9 or higher
|
15 |
+
- Google API key for access to Generative AI models
|
16 |
+
- Langchain API key
|
17 |
+
- Pre-processed FAISS index (stored in `./Vector_DB/faiss_index`)
|
18 |
+
|
19 |
+
## Installation
|
20 |
+
|
21 |
+
1. Clone this repository:
|
22 |
+
```
|
23 |
+
git clone
|
24 |
+
cd website-rag-chatbot
|
25 |
+
```
|
26 |
+
|
27 |
+
2. Install the required packages:
|
28 |
+
```
|
29 |
+
pip install -r requirements.txt
|
30 |
+
```
|
31 |
+
|
32 |
+
3. Set up your environment variables:
|
33 |
+
Create a `.env` file in the project root and add the following:
|
34 |
+
```
|
35 |
+
GOOGLE_API_KEY=your_google_api_key
|
36 |
+
LANGCHAIN_API_KEY=your_langchain_api_key
|
37 |
+
```
|
38 |
+
|
39 |
+
## Usage
|
40 |
+
|
41 |
+
To run the chatbot locally:
|
42 |
+
|
43 |
+
```
|
44 |
+
python app.py
|
45 |
+
```
|
46 |
+
|
47 |
+
This will start the Gradio interface, typically accessible at `http://localhost:7860`.
|
48 |
+
|
49 |
+
## Deployment
|
50 |
+
|
51 |
+
This project is configured for deployment to Google Cloud Run.
|
52 |
+
|
53 |
+
1. Build the Docker image:
|
54 |
+
```
|
55 |
+
docker build -t website-rag-chatbot .
|
56 |
+
```
|
57 |
+
|
58 |
+
2. Tag and push the image to Google Container Registry:
|
59 |
+
```
|
60 |
+
docker tag website-rag-chatbot gcr.io/your-project-id/website-rag-chatbot
|
61 |
+
docker push gcr.io/your-project-id/website-rag-chatbot
|
62 |
+
```
|
63 |
+
|
64 |
+
3. Deploy to Cloud Run:
|
65 |
+
```
|
66 |
+
gcloud run deploy website-rag-chatbot --image gcr.io/your-project-id/website-rag-chatbot --platform managed
|
67 |
+
```
|
68 |
+
|
69 |
+
Remember to set the necessary environment variables in the Cloud Run configuration.
|
70 |
+
|
71 |
+
## Project Structure
|
72 |
+
|
73 |
+
- `app.py`: Main application file containing the Gradio interface and RAG logic
|
74 |
+
- `Dockerfile`: Configuration for containerizing the application
|
75 |
+
- `requirements.txt`: List of Python package dependencies
|
76 |
+
- `Vector_DB/faiss_index`: Pre-processed FAISS index (not included in repository)
|
77 |
+
|
78 |
+
## Contributing
|
79 |
+
|
80 |
+
Contributions are welcome! Please feel free to submit a Pull Request.
|
81 |
+
|
82 |
+
## License
|
83 |
+
|
84 |
+
This project is licensed under the MIT License - see the LICENSE file for details.
|
85 |
+
|
86 |
+
## Acknowledgments
|
87 |
+
|
88 |
+
- Langchain for the RAG framework
|
89 |
+
- Google for the Generative AI models
|
90 |
+
- Gradio for the easy-to-use interface building
|
91 |
+
|
92 |
+
## Contact
|
93 |
+
|
94 |
+
Created by Yash Kavaiya - feel free to contact me!
|
95 |
+
- GitHub: [https://github.com/Yash-Kavaiya](https://github.com/Yash-Kavaiya)
|
96 |
+
- LinkedIn: [https://linkedin.com/in/Yash-Kavaiya](https://linkedin.com/in/Yash-Kavaiya)
|