Update README.md

README.md

@@ -10,7 +10,48 @@ pinned: false
 license: apache-2.0
 ---
 
-### **Implementation Steps: Validating Information with Context**  
+
+EchoTruth is an AI-powered application that helps you verify the authenticity of news articles in real-time. By using a combination of knowledge graphs, online search, and zero-shot classification models, it provides a truthfulness score, explanation, and sources for the given news input. The application is powered by advanced AI models, ensuring an accurate and up-to-date analysis.
+
+## How to Clone and Run the Application
+
+### 1. Create a Conda Environment
+First, create a new Conda environment with Python 3.10:
+```bash
+conda create --prefix ./env python==3.10
+```
+
+### 2. Install Required Libraries
+Next, install the required libraries from the `requirements.txt` file:
+```bash
+pip install -r requirements.txt
+```
+
+### 3. Use a `.env` File for Secrets
+Create a `.env` file in the project root directory and include the following keys with your respective API keys:
+```env
+SEARCH_API_KEY=""
+SEARCH_BASE_URL=""
+SEARCH_MODEL=""
+GEMINI_API_KEY=""
+```
+Make sure to replace the placeholders with your actual API keys.
+
+### 4. Run the Application
+Finally, you can run the application by executing:
+```bash
+python app.py
+```
+This will launch the application, and you can start verifying news authenticity by entering the news text or URL in the provided input box.
+
+---
+
+## How It Works
+
+### Overview
+EchoTruth uses AI models to check the authenticity of news in real-time by processing the given news or article and validating it using a combination of external search and knowledge graph retrieval. 
+
+### **Implementation Steps: Validating Information with Context**
 
 Validating the accuracy or degree of truthfulness of a given piece of information requires **context**—factual and relevant details surrounding the claim. Here’s how we approach this process step-by-step:
 
@@ -111,4 +152,14 @@ Analysis: You can reasonably trust this information, but further verification is
 3. **Scalable and Cost-Effective**: Uses pre-trained models, FAISS indexing, and simple APIs for implementation.  
 4. **Interpretability**: Outputs include confidence scores and explanations for transparency.
 
-This modular approach ensures that the **truthfulness assessment** is **scalable**, **explainable**, and **adaptable** to new domains.
+This modular approach ensures that the **truthfulness assessment** is **scalable**, **explainable**, and **adaptable** to new domains.
+
+---
+
+## Jupyter Notebook: `workflow.ipynb`
+
+The `workflow.ipynb` file provides a detailed, step-by-step demonstration of the entire EchoTruth process, from fetching online search results and knowledge graph context to calculating the truthfulness score and generating explanations. The notebook includes examples of both true and fake news, and shows how the application processes these inputs.
+
+To view the workflow:
+1. Open the Jupyter notebook.
+2. Follow the cells to see how the system fetches data and evaluates news authenticity for both true and fake news examples.