Media and community Case study
AI parsing of uploaded documents on AWS Lambda
An AWS Lambda pipeline: a file uploaded to S3 is unzipped or its text extracted from PDF or Word, sent to the ChatGPT API, stored as JSON and announced to the website by webhook.

- Client
- Website client
- Service
- AI, Integrations
- Years
- 2023
- Stack
- AWS Lambda, OpenAI API, Amazon S3
Client details are private, so this study describes the client by type.
Overview
A website needed the documents it receives turned into structured data without anyone retyping them. We built an event-driven pipeline on AWS: uploading a file to an S3 bucket starts a Lambda function that opens ZIP archives, extracts the text from PDF and Word files, sends it to the ChatGPT API, stores the JSON it returns in a database and tells the website by webhook where the result is.
What we built
- An S3 trigger that runs a Lambda function whenever a new file is uploaded
- ZIP handling: archives are unzipped into a sub-folder of the bucket, so each file inside is processed in turn
- Text extraction from PDF, DOCX and DOC files
- ChatGPT API integration that turns the extracted text into JSON
- Storage of the JSON results in a database
- A step that waits for processing to finish before handling the results
- A webhook that sends the website the address of each finished JSON result
Technology used
| Layer | Choice | Purpose |
|---|---|---|
| Processing | AWS Lambda | unzipping, text extraction and the model call |
| AI | OpenAI API (ChatGPT) | turns document text into structured JSON |
| Trigger | Amazon S3 | new uploads start the pipeline |
| Hand-off | Webhook | tells the website where each result is |
What happened next
- Delivered
The work described above was delivered to the client.
- Operational facts
- Our work on this project took place in 2023.
Could this be your project?
- You have a defined job in a real process that automation or AI could take on. AI services
- Your product has to connect to payment, accounting, messaging or other third-party systems.
- You work in media and community and want a team that has built for it before. Media and community work
Questions about this project
How long did this project take?
Our work on it took place in 2023.
What technology was used?
AWS Lambda, OpenAI API, Amazon S3.
Similar work

Also AWS, same industry
TheHopeLine: crisis-support community platform
A long-running ASP.NET website, agent CRM and mobile app for a youth crisis-support organisation: topic pages, live chat, prayer requests, reports and reminders.

Also OpenAI, also an integrations project
Reactor: AI assistant and Web3 data back end
A Node.js back end for Reactor, an AI chat assistant with Web3 tools: streaming chat and voice, a keyed language-model API for businesses, and a crypto service for token audits, swaps and rewards.
Also OpenAI, also an integrations project
Beliri: designer marketplace iOS payments and Shopify sync
Native Stripe and PayPal checkout in the iOS app of Beliri, a marketplace for new and pre-owned designer goods, and a Shopify connector that brings merchant catalogues into the marketplace.

