Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

https://github.com/AKMessi/AI-IPO-Analyst

Custom research AI agent that analyzes IPOs, you just have to upload the DRHP and give the company name to the AI agent
https://github.com/AKMessi/AI-IPO-Analyst

Last synced: about 1 month ago
JSON representation

Custom research AI agent that analyzes IPOs, you just have to upload the DRHP and give the company name to the AI agent

Awesome Lists containing this project

README 

          
📈 AI-Powered IPO Analysis Agent



A sophisticated, AI-powered agent that automates the in-depth analysis of Indian IPOs. This tool ingests a company's Draft Red Herring Prospectus (DRHP), performs a detailed financial analysis, enriches it with live market data, and presents a structured, actionable report through a simple web interface.



App Screenshot



✨ Features:



📄 PDF Data Ingestion: Automatically parses complex DRHP PDFs to extract key financial statements (Balance Sheet, P&L, Cash Flow).



🧠 Custom Analysis Engine: Leverages Google's Gemini 2.5 Pro via LangChain to conduct a nuanced analysis of the company's financial health based on a predefined methodology.



🌐 Web-Enabled Enrichment: Autonomously searches the web using the Tavily API to fetch critical, up-to-the-minute data points like Industry P/E ratios, peer company P/Es, and the latest Grey Market Premium (GMP).



📊 Interactive UI: Built with Streamlit for a user-friendly experience, allowing easy PDF uploads and a clear, well-structured display of the final analysis report.



☁️ Deployable: Designed as a self-contained application, ready for deployment on cloud platforms like Streamlit Community Cloud or Hugging Face Spaces.



🛠️ Tech Stack:



Backend: Python



AI/LLM Framework: LangChain



LLM: Google Gemini 2.5 Pro



Web UI: Streamlit



PDF Parsing: pdfplumber



Data Handling: pandas



Web Search: Tavily Search API



Vector Store: FAISS (for in-memory vector search)



🚀 Getting Started



Follow these instructions to set up and run the project on your local machine.



Prerequisites



Python 3.8+



A Google API Key with the Gemini 2.5 Pro model enabled. You can get one from Google AI Studio.



A Tavily API Key for the web search functionality. You can get one from the Tavily AI website.



1. Clone the Repository



git clone https://github.com/AKMessi/AI-IPO-Analyst.git



cd AI-IPO-Analysis-Agent



2. Create and Activate a Virtual Environment

   

A virtual environment is recommended to keep dependencies isolated.



On macOS/Linux:



python3 -m venv venv



source venv/bin/activate



On Windows:



python -m venv venv



.\venv\Scripts\activate



3. Install Dependencies



Install all the required packages using the requirements.txt file.



pip install -r requirements.txt



⚙️ Configuration



The application requires API keys to function. Create a file named .env in the root directory of the project.



Create the .env file:



touch .env



Add your API keys to the .env file:



GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY_HERE"



TAVILY_API_KEY="YOUR_TAVILY_API_KEY_HERE"



Replace the placeholder text with your actual keys. The application uses python-dotenv to load these keys automatically.



▶️ How to Run



Once the setup and configuration are complete, you can launch the Streamlit application with a single command.



streamlit run app.py



This will start the web server and open the application in your default web browser. You can now upload a DRHP PDF, enter the company name, and start the analysis.



⚠️ Disclaimer:



This tool is for informational and educational purposes only. The analysis provided is generated by an AI agent and should not be considered financial advice. Always conduct your own thorough research or consult with a qualified financial advisor before making any investment decisions.