llmbedrock

Usecase- details

Here's a README file for the GitHub repository of the project you described:

AI-Powered Document Analysis

This project provides a suite of solutions for analyzing documents (PDFs and images) using AI technology. Users can upload their documents, ask questions, and receive intelligent responses enhanced by various AI capabilities.

Solutions

1. PDF Analysis

   • Upload multi-page PDF documents for analysis
   • Ask questions about the documents
   • AI enhancements:
     • Translate: Translate text to different languages
     • Comprehend: Perform entity detection and text analysis
     • Polly: Convert text to speech

2. Image Analysis

   • Upload images for analysis
   • Ask questions about the images
   • Images are analyzed using Amazon Textract for image analysis
   • AI enhancements:
     • Translate: Translate text to different languages
     • Comprehend: Perform entity detection and text analysis
     • Polly: Convert text to speech

3. RAG with Kendra and Bedrock

   • Ask questions, and responses are generated by retrieving relevant chunks from Amazon Kendra and summarized using Claude 2
   • Example: "What is ABDM?"

4. RAG with OpenSearch and Bedrock

   • Ask questions, and responses are generated by retrieving relevant chunks from OpenSearch and summarized using Claude 2
   • Example: "How did Amazon perform during COVID-19?"

5. Claude 3

   • Ask questions related to mathematics and probability
   • Provide images and text in the same query for analysis

Getting Started

Steps to use the application

Here's the rewritten version for a GitHub README file:

GenAISolutions

This repository contains code for invoking a large language model (LLM) to process and analyze large documents.

Getting Started

Follow these steps to set up the project locally:

1. Navigate to the project folder

cd GenAIsolutions

2. Create and activate a virtual environment

python3 -m venv .llmv
source .llmv/bin/activate
.llmv/bin/python

3. Install dependencies

Open a terminal and install the required packages from the requirements.txt file:

pip install -r requirements.txt

4. Run the Streamlit application

To run the Streamlit application, execute the following command:

streamlit run WelcomePage.py --server.port 8080

5. Run the main script (alternative)

Alternatively, you can run the main script directly:

python3 main.py

Usage

This project allows you to invoke a large language model to process and analyze large documents. The main functionality is provided by the main.py script, which you can run directly or through the Streamlit application.

Contributing

Contributions to this project are welcome. If you find any issues or have suggestions for improvements, please open an issue or submit a pull request.