AI Document Summarizer

Inspiration

## Project Inspiration & Journey  

My inspiration for building an **AI‑powered Document Summarizer** on Cloud Run came from the need to save time and effort in reading and processing long documents such as reports and research papers.  

I learned how to orchestrate cloud‑native services effectively, handling document ingestion, text extraction, and the use of large language models for summarization. This architecture enables seamless processing from document upload to summary storage and retrieval.  

The project was built by creating a pipeline triggered by document uploads to Cloud Storage. The upload fires Cloud Run services that:  

1. **Extract text** using Document AI OCR,  
2. **Summarize** the text with Vertex AI generative models, and  
3. **Store** the results in analytical destinations like BigQuery.  

**Challenges** faced during development included managing timeout limits on Cloud Tasks, which sometimes required migrating to longer‑running Cloud Run jobs.

What it does

How we built it

Challenges we ran into

Accomplishments that we're proud of

What we learned

What's next for AI Document Summarizer

Built With

• backend
• client
• cloud-run
• framework
• google-ai-studio
• google-cloud
• llm
• web