An open API service indexing awesome lists of open source software.

https://github.com/spidy20/indian-document-extraction-aws

This solution is a proof of concept for an Indian Legal Document Extractor utilizing AWS Lambda, Bedrock, SQS, and S3.
https://github.com/spidy20/indian-document-extraction-aws

bedrock document-scanner lambda s3 sqs

Last synced: 20 days ago
JSON representation

This solution is a proof of concept for an Indian Legal Document Extractor utilizing AWS Lambda, Bedrock, SQS, and S3.

Awesome Lists containing this project

README

          

# IndianšŸ‡®šŸ‡³ Legal Document Extractor using AWS Bedrock, Lambda, and SQS

### [Watch this tutorialā–ŗ](https://youtu.be/YWmnD_QcZQU)

- In this tutorial, we'll be creating a GPT-4 AWS Helper ChatBot utilizing Langchain, Lambda, API Gateway, and PostgreSQL PGVector hosted on an EC2 instance as our Vector database.

### Implementation Architecture

### Used Services
- **AWS Lambda**: Responsible for managing the backend of the Document Extractor using the Boto3 SDK.
- **AWS SQS**: Manages the scalability of solutions by maintaining a queue, enabling multiple documents to be processed.
- **Bedrock Claude Sonnet Model**: Used to extract JSON data from legal documents.
- **S3**: Stores images of legal documents and triggers SQS with a Lambda function upon upload.

### Implementation Setup
- Creating an S3 Bucket.
- Creating a Lambda function and lambda handler.
- Setting up the SQS Queue and Policy.
- Configuring S3 event to trigger SQS with AWS Lambda
- Testing the automation workflow.
- Testing with Indian legal documents.

### Give Star⭐ to this repository, and fork it to support me.

### [Buy me a Coffeeā˜•](https://www.buymeacoffee.com/spidy20)
### [Donate me on PayPal(It will inspire me to do more projects)](https://www.paypal.me/spidy1820)