# Extracting structured data from PDFs using Gemini 2.0 and Genkit

DevFeed: [Extracting structured data from PDFs using Gemini 2.0 and Genkit](<https://devfeed.tech/articles/extracting-structured-data-from-pdfs-using-gemini-2-0-and-genkit-16580.md>)

Original publisher: [Read original article](<https://firebase.blog/posts/2025/02/gemini-genkit-pdf-structured-data>)

Author: Peter Friese

Published: 2025-02-20T09:41:00Z

Content type: tutorial

Language: en

Sources: [Firebase Blog](<https://devfeed.tech/sources/firebase-blog.md>)

Topics: [Genkit](<https://devfeed.tech/topics/genkit.md>), [Structured-data](<https://devfeed.tech/topics/structured-data.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Node.js](<https://devfeed.tech/topics/node-js.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [SDKs](<https://devfeed.tech/topics/sdks.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [firebase](<https://devfeed.tech/tags/firebase.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [genkit](<https://devfeed.tech/tags/genkit.md>), [guide](<https://devfeed.tech/tags/guide.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [node-js](<https://devfeed.tech/tags/node-js.md>), [snippet](<https://devfeed.tech/tags/snippet.md>), [structured-output](<https://devfeed.tech/tags/structured-output.md>), [typescript](<https://devfeed.tech/tags/typescript.md>)

## AI overview

A step-by-step tutorial showing Node.js developers how to use Gemini 2.0 and Genkit to extract structured invoice data from PDF files. It covers multimodal PDF analysis, OCR, and schema-constrained output with Zod.

## Source excerpt

Extract structured data from PDFs using Gemini 2.0's vision and Genkit. Step-by-step guide with code examples for Node.js developers.