Social Media Performance Analysis

An basic analytics module utilizing Langflow and DataStax to analyze engagement data from mock social media accounts and Streamlit-based web application that allows users to interact with a flow generated by LangFlow for social media performance analysis.

Used Tools:

● DataStax Astra DB for database operations.

● Langflow for workflow creation and GPT integration.

● Streamlit for frontend access of Langflow.

Features

• Powered by LangFlow and DataStax for robust and accurate analysis.
• Interactive chat interface for social media performance analysis.
• Persistent query and response history using Streamlit's session_state.
• Easy-to-use interface with real-time insights from LangFlow.

---

Setup Instructions

1. Clone the Repository

https://github.com/Zaidusyy/SuperMind/
cd SuperMind

2. Create a Virtual Environment

Set up a Python virtual environment to manage dependencies:

python -m venv env

Activate the virtual environment: On Windows:

source env/Scripts/activate

On Mac/Linux:

source env/bin/activate

3. Install Dependencies

Install the required Python libraries:

pip install -r requirements.txt

4. Create a .env File

Create a .env file in the root directory of your project and add the following:

dotenv

APP_TOKEN=<your-langflow-generated-token>

Replace with the API token generated by LangFlow.

5. Run the Application

Start the Streamlit application:

streamlit run main.py

How to Use

(1) Enter your query in the text area provided.

(2) Click on the "Generate Insights" button to analyze the query.

View the analysis result and the chat history below the input area.

Project Structure

• app.py: Main application file containing the Streamlit app logic.
• requirements.txt: List of dependencies required for the project.
• .env: File for storing environment variables securely.

Demonstration

Notes

Ensure you have a valid LangFlow APP_TOKEN before running the application.

The API token is stored securely in the .env file and accessed through python-dotenv.