https://github.com/smatiolids/astra-agent-memory

https://github.com/smatiolids/astra-agent-memory

Last synced: 7 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/smatiolids/astra-agent-memory
• Owner: smatiolids
• Created: 2023-09-26T13:28:25.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-03-05T20:23:59.000Z (8 months ago)
• Last Synced: 2024-04-14T03:41:11.226Z (7 months ago)
• Language: Jupyter Notebook
• Size: 3.86 MB
• Stars: 4
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Astra Agent Memory with PDF context

![Astra Agent Memory](astra_agent.png)

The purpose of this demo is to combine the processing of PDF files, embedding generation, multiple retrieval metrics and a user interface with streamlit that also consider agent memory.

## Installing dependencies

pip install -r requirements.txt

## DataStax Astra

Create an account and a Vector DB at (astra.datastax.com).

## Environment Variables

Define the AstraDB credentials and Open AI API Key in the .env file.

Copy .env.sample to .env

## Running

streamlit run app.py

## Loading PDF

I uploaded and converted PDF using the notebook "Explicando Retrieval Augmented Generation.ipynb".