docu: add diagram and screenshot to enhance readme

Author: akshseh

README.md

@@ -2,7 +2,13 @@
 
 Bedrock Deep Research is a Streamlit-based application using Amazon Bedrock, LangGraph, and LangChain AWS libraries that automates article/report generation through AI-powered research, content writing, and image generation. It combines web research, structured content generation, and human feedback to produce comprehensive, well-researched articles with accompanying header images (generated by [Amazon Bedrock Nova Canvas](https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html)). This repo is inspired by LangChain's [Deep Researcher](https://github.com/langchain-ai/open_deep_research/tree/main).
 
-## Repository Structure
+## Features
+- **Automated Research**: Performs targeted web searches to gather relevant information
+- **Structured Content Generation**: Creates cohesive article outlines and detailed section content
+- **Interactive Feedback Loop**: Incorporates human feedback to refine article outlines
+- **AI-Generated Imagery**: Produces relevant header images for visual appeal
+
+### Repository Structure
 ```
 bedrock_deep_research/
 ├── bedrock_deep_research.py          # Main Streamlit application entry point
@@ -22,18 +28,37 @@ bedrock_deep_research/
 ```
 
 
-### Prerequisites
-- Python 3.12 (to install, visit this link: https://www.python.org/downloads/).
-   Check your python version using `python --version`.
-   If your global python isn't set as `3.12`, follow the steps here: https://python-poetry.org/docs/managing-environments/)
-- Poetry for dependency management
-- [AWS Bedrock access](https://docs.aws.amazon.com/bedrock/latest/userguide/model-access-modify.html) for LLM inference (supported models provided in `SUPPORTED_MODELS` variable in `./bedrock_deep_research/config.py`)
+## Work Flow
+The application follows a sequential workflow from topic input to final article generation, with feedback loops for refinement.
 
+![Agent Flow with Example](static/agent_walkthrough.png)
 
-## Setup
+Key Components of the graph:
+1. **Initial Researcher**: It performs initial web searches to gather context
+2. **Article Outline Generator**: creates structured outline using research data
+   - **Human Feedback Provider**: This incorporates human feedback for the outline
+3. **Section Writer**: A subgraph that generates content after web research.
+4. **Compilation**: combines all elements into a cohesive article
+5. **Final Section Generation**: Generate the overview and the last paragraph based on the other sections.
+6. **Header Image Generator**: creates relevant header image
+
+
+# Setup
 
 The setup is meant to be used locally with [AWS authentication](https://docs.aws.amazon.com/cli/v1/userguide/cli-authentication-short-term.html), as well as within Amazon Sagemaker: either in [JupyterLab](https://docs.aws.amazon.com/sagemaker/latest/dg/studio-updated-jl.html) or [Code Editor](https://docs.aws.amazon.com/sagemaker/latest/dg/code-editor.html) instance.
 
+Note: Current setup is assuming `us-east-1` region (as defined in `env.tmp` file).
+
+
+## Prerequisites
+- **Python 3.12** (to install, visit this link: https://www.python.org/downloads/).
+   Check your python version using `python --version`.
+   If your global python isn't set as `3.12`, follow the steps here: https://python-poetry.org/docs/managing-environments/)
+- **Poetry** for dependency management
+- Make sure you have **enabled model access** via [AWS Bedrock access](https://docs.aws.amazon.com/bedrock/latest/userguide/model-access-modify.html) in **`us-east-1`** region. You can find the supported models provided in `SUPPORTED_MODELS` variable in `./bedrock_deep_research/config.py`.
+- **Tavily API** key for web research capabilities.
+
+
 ### 1. Installation
 ```bash
 # Clone the repository
@@ -49,7 +74,7 @@ poetry install
 
 ### 2. Create and set your Tavily API key
 
-Go to https://app.tavily.com/home and create an API KEY for free. Copy the API Key and paste it into the `env.tmp` file.
+Go to https://app.tavily.com/home and create a free API KEY. Copy the API Key and paste it into the `env.tmp` file.
 
 ### 3. Setup the environment variables
 
@@ -65,19 +90,15 @@ cp env.tmp .env
 streamlit run bedrock_deep_research.py
 ```
 
-- In the web interface:
-   - Enter your article topic
-   - Specify writing guidelines
-   - Configure search parameters
-   - Click "Generate Outline"
+## Using the Application
+
 
-- Review and provide feedback on the outline:
-   - Submit feedback to refine the outline
-   - Accept the outline to proceed with full article generation
+| Step | Description | Visual Reference |
+|------|-------------|------------------|
+| **1. Enter Article Details** | • Enter your article topic in the main input field<br>• Add specific writing guidelines in the text area provided<br>• Adjust search parameters using the configuration panel<br>• Click the "Generate Outline" button to start the process | ![Article Creation Interface](static/article_config.png) |
+| **2. Review and Refine the Outline** | • Review the AI-generated article outline<br>• Provide specific feedback in the feedback field to improve the structure<br>• Use the editing tools to make direct modifications if needed<br>• Click "Accept Outline" when you're satisfied with the structure | ![Outline Review Interface](static/article_outline_review.png) |
+| **3. Generate the Complete Article** | • Review the fully researched and written article with its custom header image<br>• Use the formatting tools to make any final adjustments<br>• Click "Copy to Clipboard" to export your article<br>• Or select "New Article" to start the process again | ![Final Article View](static/final_article_view.png) |
 
-- Once complete:
-   - Review the generated article with header image
-   - Copy to clipboard or start a new article
 
 ### Configuration details
 
@@ -103,17 +124,6 @@ export LOG_LEVEL=DEBUG
 streamlit run bedrock_deep_research.py
 ```
 
-## Data Flow
-The application follows a sequential workflow from topic input to final article generation, with feedback loops for refinement.
-
-Key Components of the graph:
-- Initial Researcher: It performs initial web searches to gather context
-- Article Outline Generator: creates structured outline using research data
-- Human Feedback Provider: This incorporates human feedback for the outline
-- Section Writer: A subgraph that generates content after web research.
-- Header Image Generator: creates relevant header images
-- Final compilation: combines all elements into a cohesive article
-
 
 ### Contributing
 Contributions are welcome! Please open an issue or submit a pull request if you have any improvements or bug fixes. Read CONTRIBUTING.md for more details.