Company Sales Brochure Generator

---

Create a product that can generate marketing brochures about a company:

• For prospective clients
• For investors
• For recruitment

The technology:

• Use Open Al API
• Use one-shot prompting
• Stream back results and show with formatting

Project Organization

---

├── .gitignore          <- Includes files and folders that we don't want to control
|
├── images              <- Images for use in this project
│   ├── brochure.png    <- Brochure image
│   └── result.png      <- Result image
|
├── main.ipynb          <- Main jupyter file that needs to be run
|
├── requirements.txt    <- The required libraries to deploy this project. 
|                       Generated with `pip freeze > requirements.txt`
└── README.md           <- The top-level README for developers using this project.

Project Introduction

Business Problem

Creating tailored marketing brochures for companies is a complex and manual process, requiring extensive effort to gather, analyze, and organize relevant information from their websites. This project provides an automated solution to streamline the process using GPT-4o-mini and cutting-edge techniques for link evaluation and content generation.

Problem Definition

Generating professional, company-specific sales brochures involves time-consuming tasks like identifying relevant content, assembling marketing details, and designing layouts. This project automates the process by:

1. Using GPT-4o-mini to analyze company websites and extract only the most relevant links and content.
2. Automating the design and creation of sales brochures based on the extracted information.
3. Enhancing user experience with real-time streaming output for smoother content generation.

Model Output Example

system_prompt = "You are an assistant that analyzes the contents of several relevant pages from a company website and creates a short humorous, entertaining, jokey brochure about the company for prospective customers, investors and recruits. Respond in markdown.Include details of company culture, customers and careers/jobs if you have the information."

Conclusion

This is an example of Agentic AI design patterns, as we combined multiple calls to LLMs. Generating content in this way is one of the very most common Use Cases. As with summarization, this can be applied to any business vertical. Write marketing content, generate a product tutorial from a spec, create personalized email content, and so much more.

How to run the app

Follow these steps to set up and run the application:

1. Create a .env file
   Add your OpenAI API key to the .env file in the following format:

   OPENAI_API_KEY=sk-proj-blabla
   

2. Setup virtual envirenment
   Run the following command to setup virtual envirenment:

   python3 -m venv venv  # Create a virtual environment named 'venv'
   source venv/bin/activate  # Activate the virtual environment (Linux/Mac)'
   .\venv\Scripts\activate   # Activate the virtual environment (Windows)'

3. Install Dependencies
   Run the following command to install all required dependencies:

   pip install -r requirements.txt

4. Open and Run the Notebook
   Open the main.ipynb file in Jupyter Notebook and execute the cells to run the application.