Spaces:
Build error
Build error
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,3 +10,55 @@ pinned: false
|
|
| 10 |
---
|
| 11 |
|
| 12 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
| 13 |
+
# PDF Query Chatbot
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Overview
|
| 18 |
+
|
| 19 |
+
The **PDF Query Chatbot** is a Streamlit-based application hosted on Hugging Face Spaces. It allows users to upload a PDF document and ask questions about its content. The chatbot utilizes a transformer model to generate responses based on the text extracted from the PDF.
|
| 20 |
+
|
| 21 |
+
## Live Demo
|
| 22 |
+
|
| 23 |
+
You can try the PDF Query Chatbot live here: [PDF Query Chatbot on Hugging Face Spaces](https://huggingface.co/spaces/datascientist22/rag-pdfQA-chatbot)
|
| 24 |
+
|
| 25 |
+
## Features
|
| 26 |
+
|
| 27 |
+
- **Upload PDF Files**: Upload PDF files directly from your local machine.
|
| 28 |
+
- **Query Input**: Enter questions related to the uploaded PDF content.
|
| 29 |
+
- **Text Extraction**: Extracts text from the PDF for querying.
|
| 30 |
+
- **Response Generation**: Uses a transformer model to generate answers based on your query and the PDF content.
|
| 31 |
+
|
| 32 |
+
## How to Use
|
| 33 |
+
|
| 34 |
+
1. **Upload PDF File**: Use the sidebar to upload a PDF file.
|
| 35 |
+
2. **Enter Query**: Type your question related to the PDF content in the query input field.
|
| 36 |
+
3. **Submit**: Click the "Submit" button to process the file and get a response.
|
| 37 |
+
4. **View Response**: The generated response will be displayed below the input fields.
|
| 38 |
+
|
| 39 |
+
## Requirements
|
| 40 |
+
|
| 41 |
+
To run this app locally, ensure you have the following Python packages installed:
|
| 42 |
+
|
| 43 |
+
- `transformers`: For using pre-trained transformer models.
|
| 44 |
+
- `PyPDF2`: For extracting text from PDF files.
|
| 45 |
+
- `torch`: PyTorch library for running the model.
|
| 46 |
+
- `streamlit`: For the web app interface.
|
| 47 |
+
|
| 48 |
+
## Installation
|
| 49 |
+
|
| 50 |
+
1. Clone the repository:
|
| 51 |
+
```bash
|
| 52 |
+
git clone https://github.com/mldatascientist23/Generative_AI_Projects.git
|
| 53 |
+
cd your-repository
|
| 54 |
+
```
|
| 55 |
+
|
| 56 |
+
2. Install the required packages:
|
| 57 |
+
```bash
|
| 58 |
+
pip install transformers PyPDF2 torch streamlit
|
| 59 |
+
```
|
| 60 |
+
|
| 61 |
+
3. Run the Streamlit app:
|
| 62 |
+
```bash
|
| 63 |
+
streamlit run app.py
|
| 64 |
+
``
|