Learn how to extract high-quality data from complex, unstructured PDFs using LlamaParse powered by Gemini 3.1 Pro. This guide demonstrates an event-driven workflow to automate the parsing of dense financial tables and generate intelligent summaries with Gemini 3.1 Flash. Perfect for developers building scalable document-parsing pipelines and AI personal finance assistants.

GoogleDevs' platform is a central hub for developers interested in Google technologies, APIs, and developer tools. Through articles, tutorials, and documentation, GoogleDevs offers insights into building applications using Google Cloud Platform, Android, Chrome, and other Google services. Developers can learn about cloud computing, machine learning, and mobile app development with Google's developer tools and platforms.

Google Developers

A step-by-step guide to building an event-driven financial document assistant using LlamaParse powered by Gemini 3.1 Pro for parsing and Gemini 3 Flash for summarization. The workflow parses complex brokerage statement PDFs, extracts text and tables in parallel using LlamaIndex Workflows, and generates plain-language financial summaries. The two-model architecture balances layout comprehension accuracy with cost efficiency, and the full code is available on GitHub.

Build a smart financial assistant with LlamaParse and Gemini 3.1

The use case: parsing brokerage statements