Master

.gitignore

@@ -1 +1,6 @@
-env
+env
+pycache/.env
+.env
+/pycache/
+/models/
+.gitattributes

.vs/100x_enginners_hackathon_genai/v17/DocumentLayout.json

@@ -0,0 +1,12 @@
+{
+  "Version": 1,
+  "WorkspaceRootPath": "F:\\100x_enginners_hackathon_genai\\",
+  "Documents": [],
+  "DocumentGroupContainers": [
+    {
+      "Orientation": 0,
+      "VerticalTabListWidth": 256,
+      "DocumentGroups": []
+    }
+  ]
+}

.vs/ProjectSettings.json

@@ -0,0 +1,3 @@
+{
+  "CurrentProjectSetting": null
+}

.vs/VSWorkspaceState.json

@@ -0,0 +1,6 @@
+{
+  "ExpandedNodes": [
+    ""
+  ],
+  "PreviewInSolutionExplorer": false
+}

README.md

@@ -1,53 +1,97 @@
-# Project Overview
+# Our Hackathon MVP:
 
-This project is a Flask-based web application that allows users to generate animated infographic videos based on input text. The application leverages the Pexels API for video content and incorporates natural language processing (NLP) techniques to analyze and transform the input text into a suitable format for video generation.
+## DataVizAI
 
-# Features
+**![images](https://github.com/user-attachments/assets/e26aee53-96a6-4271-a28d-646419758071)**
 
-1. **Text-to-Video Conversion**: Users can input text, and the application will generate a video based on the content of the text.
-2. **NLP Analysis**: The application performs sentiment analysis and semantic segmentation on the input text to better understand its context and meaning.
-3. **Video Generation**: The application uses the Pexels API to search for videos that match the processed text and returns a selection of video URLs.
-4. **Logging**: The application logs responses from the Pexels API and OpenAI (if integrated) for debugging and analytics purposes.
 
-# Technical Details
+# MVP Videos:
 
-1. **Backend**: The application is built using Flask, a Python web framework.
-2. **NLP Libraries**: The application utilizes the following NLP libraries:
-	* TextBlob for sentiment analysis
-	* Spacy for semantic segmentation
-	* NLTK for text preprocessing
-    *transformers
-    *huggingface
-    *langchain
-3. **API Integration**: The application integrates with the Pexels API for video content.
-4. **Frontend**: The application uses HTML, CSS, and JavaScript for the user interface.
+**coming soon ....**
 
-# Installation and Setup
+## Project Overview:
 
-1. Clone the repository: `git clone https://github.com/Blacksujit/100X-Enginnerres-Hackathon-Submission`
+Dataviz AI is an AI powered web application that enables users to generate animated infographic videos based on input  Data , text,files. This MVP leverages the Pexels API for video content and incorporates advanced natural language processing (NLP) techniques, including LangChain and stable diffusion techniques, to analyze and create visual impact
+
+## Key Features:
+
+1. **Text-to-Video Conversion**: Users can input text, and the application will generate a video based on the content of the text, making information more engaging and accessible.
+
+2. **NLP Analysis**: The application performs sentiment analysis and semantic segmentation on the input text to better understand its context and meaning, ensuring that the generated video aligns with the user's intent.
+
+3. **Video Generation**: The application uses the Pexels API to search for videos that match the processed text and returns a selection of video URLs, providing users with high-quality visual content.
+
+4. **Logging**: The application logs responses from the Pexels API and OpenAI (if integrated) for debugging and analytics purposes, allowing for continuous improvement and monitoring of the application’s performance.
+
+
+## Impact of the Product:
+
+The Dataviz AI is an AI powered web application  has the potential to significantly impact various sectors, including education, marketing, and content creation. By transforming textual information into engaging video content, it enhances the way information is consumed and understood. Here are some key impacts:
+
+- **Enhanced Learning**: In educational settings, the ability to convert complex text into visual formats can aid in comprehension and retention, making learning more effective.
+
+- **Marketing and Communication**: Businesses can leverage this tool to create promotional videos quickly, allowing for more dynamic and engaging marketing strategies that capture audience attention.
+
+- **Accessibility**: By providing visual representations of textual information, the application can help make content more accessible to individuals with different learning styles or those who may struggle with reading.
+
+- **Content Creation**: Content creators can streamline their workflow by generating videos from scripts or articles, saving time and resources while maintaining high-quality output.
+
+
+## Technical Overview
+
+1. **Frontend**: The application uses HTML, CSS, and JavaScript for the user interface, providing a seamless user experience.
+
+2. **Backend**: The application is built using Flask, a Python web framework that allows for easy routing and handling of HTTP requests.
+
+3. **NLP Libraries**: The application utilizes the following NLP libraries:
+   - **TextBlob** for sentiment analysis, enabling the application to gauge the emotional tone of the input text.
+   - **SpaCy** for semantic segmentation, which helps in understanding the structure and meaning of the text.
+   - **NLTK** for text preprocessing, ensuring that the input text is clean and ready for analysis.
+   - **Transformers** and **Hugging Face** for advanced NLP tasks.
+   - **LangChain** for managing and chaining together different language models and tasks.
+
+4. **API Integration**: The application integrates with the Pexels API for video content, allowing users to access a vast library of stock videos.
+
+
+## Installation and Setup
+
+1. Clone the repository: 
+   ```bash
+    https://github.com/Blacksujit/100X-Engineers-GenAI-Hackathon-Submission.git
+   ```
+
+2. Install the required packages: 
+   ```bash
+   pip install -r requirements.txt
+   ```
 
-2. Install the required packages: `pip install -r requirements.txt`
 3. Set up the environment variables:
-	* `OPENAI_API_KEY`: Your OpenAI API key (if using OpenAI integration)
-	* `PEXELS_API_KEY`: Your Pexels API key
-4. Run the application: `python app.py`
+   - `OPENAI_API_KEY`: Your OpenAI API key (if using OpenAI integration).
+   - `PEXELS_API_KEY`: Your Pexels API key.
+   - `GROQ_API_KEY`: Your Groq API key. 
 
-# Usage
+4. Run the application: 
+   ```bash
+   python app.py
+   ```
 
-1. Open a web browser and navigate to `http://localhost:2000`
+## Usage
+
+1. Open a web browser and navigate to `http://localhost:2000`.
 2. Input text in the text box on the homepage and click the "Generate Video" button.
 3. The application will redirect you to a page displaying the generated video URLs.
 
-# Contributing
+
+## Contributing
 
 Contributions are welcome! If you'd like to contribute to this project, please follow these steps:
 
-1. Fork the repository
-2. Create a new branch for your feature or fix
-3. Make your changes and commit them
-4. Push your branch to your forked repository
-5. Submit a pull request to the original repository
+1. Fork the repository.
+2. Create a new branch for your feature or fix.
+3. Make your changes and commit them.
+4. Push your branch to your forked repository.
+5. Submit a pull request to the original repository.
 
-# License
+## License
 
 This project is licensed under the MIT License.

app.py

@@ -1,6 +1,29 @@
+"""
+This is the entry point for the application.
+The script performs the following tasks:
+1. Imports necessary modules and functions.
+2. Creates an instance of the application using the `create_app` function.
+3. Ensures that the directories 'uploads' and 'models' exist, creating them if necessary.
+4. Runs the application in debug mode on port 200.
+If an exception occurs during the execution, it is logged as an error.
+Modules:
+    os: Provides a way of using operating system dependent functionality.
+    logging: Provides a way to configure and use loggers.
+Functions:
+    create_app: A function imported from the app module to create an instance of the application.
+Exceptions:
+    Any exception that occurs during the execution is caught and logged.
+"""
 from app import create_app
+import os
+import logging
 
 app = create_app()
 
 if __name__ == "__main__":
-    app.run(debug=True, port=200)
+    try:
+        os.makedirs("uploads", exist_ok=True)
+        os.makedirs("models", exist_ok=True)
+        app.run(debug=True, port=200)
+    except Exception as e:
+        logging.error(f"An error occurred: {e}")

app/Preprocess_text_NLP.py

@@ -0,0 +1,53 @@
+# import pandas as pd
+# import matplotlib.pyplot as plt
+# import matplotlib.animation as animation
+# import numpy as np
+# import os
+# import torch
+# from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, AutoModelForTokenClassification
+# import gtts  # For text-to-speech audio generation
+# # from langchain_community import LangChain  # For implementing langchain and other NLP tasks
+
+
+
+# def nlp_pipeline(text, data):
+#     # Use T5 for summarization
+#     summary_model = AutoModelForSeq2SeqLM.from_pretrained('t5-base')
+#     summary_tokenizer = AutoTokenizer.from_pretrained('t5-base')
+
+#     # Prepare input
+#     input_text = f"summarize: {text} {data}"
+#     inputs = summary_tokenizer.encode(input_text, return_tensors='pt', max_length=512, truncation=True)
+
+#     # Generate summary
+#     outputs = summary_model.generate(inputs, max_length=100)
+#     summary_text = summary_tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+#     # Extract percentages and categories using simpler regex patterns
+#     import re
+#     percentages = [int(x.strip('%')) for x in re.findall(r'\d+%', text)]
+#     words = text.split()
+#     categories = []
+
+#     # Find words after "use" or "uses"
+#     for i, word in enumerate(words):
+#         if word.lower() in ['use', 'uses'] and i + 1 < len(words):
+#             categories.append(words[i + 1])
+
+#     if not percentages or not categories:
+#         percentages = [100]
+#         categories = ['Summary']
+
+#     # Generate audio
+#     tts = gtts.gTTS(summary_text, lang='en')
+#     tts.save('summary_audio.mp3')
+
+#     return {
+#         'categories': categories,
+#         'values': percentages,
+#         'text': summary_text
+#     }
+
+
+
+# Old NLP pipeline code not in  use having some import issues 

app/__init__.py

@@ -1,10 +1,24 @@
 from flask import Flask
+from flask_caching import Cache
+from flask import url_for
+from flask_cors import CORS
+# done with the conflicts 
 
+import os
 def create_app():
-    app = Flask(__name__, template_folder='../templates')  # Specify the path to the templates folder
-
+    app = Flask(__name__, template_folder='../templates', static_folder='../static')  # Specify the path to the templates and static folders
+    # Set cache directory and other caching parameters
+    # models_dir = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'models')
+    CORS(app)
+    app.config['CACHE_TYPE'] = 'filesystem'
+    app.config['CACHE_DIR'] = 'D:\\cahc_models_folder'  # Change this to your desired cache path
+    app.config['CACHE_DEFAULT_TIMEOUT'] = 300
+    # Initialize the cache
+    cache = Cache(app)
+    # Set the path for the models directory (outside the app directory)
+
     with app.app_context():
         from .routes import main
         app.register_blueprint(main)
-
+    
     return app