This blog post introduces a workflow for extracting high-quality data from complex, unstructured documents by combining LlamaParse with Gemini 3.1 models. It demonstrates an event-driven architecture that uses Gemini 3.1 Pro for agentic parsing of dense financial tables and Gemini 3.1 Flash for cost-effective summarization. By following the provided tutorial, developers can build a personal finance assistant capable of transforming messy brokerage statements into structured, human-readable insights.
Build a smart financial assistant with LlamaParse and Gemini 3.1
Related Posts
Total Madness #0: Locks
This is the first post in a series about my urges to figure out the dark magics of…
ChatGPT compared the memory usage with and without PHP generators for large datasets.
Visualizing memory usage with and without using generators can help understand the efficiency benefits. Below is a comparison…
Azure WebJobs, Service Bus and Managed Identity: Lesson learned
Today I was converting some Azure webjobs to connect to Azure Service Bus using managed service identity (MSI).…
