https://github.com/kevinknights29/pyconnect2023_genai_digital_transformation
This repo contains the content related to the talk: "Construyendo soluciones con Generative AI para la transformación digital" for PyConnect 2023
https://github.com/kevinknights29/pyconnect2023_genai_digital_transformation
genai langchain llms openai python streamlit weaviate
Last synced: 4 months ago
JSON representation
This repo contains the content related to the talk: "Construyendo soluciones con Generative AI para la transformación digital" for PyConnect 2023
- Host: GitHub
- URL: https://github.com/kevinknights29/pyconnect2023_genai_digital_transformation
- Owner: kevinknights29
- Created: 2023-10-11T03:23:55.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-03-08T04:59:28.000Z (over 1 year ago)
- Last Synced: 2025-01-27T23:46:50.855Z (9 months ago)
- Topics: genai, langchain, llms, openai, python, streamlit, weaviate
- Language: Python
- Homepage:
- Size: 7.07 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# PyConnect2023_GenAI_Digital_Transformation
This repo contains the content related to the talk:
`Construyendo soluciones con Generative AI para la transformación digital`
**Content**
1. [Overview](#overview)
2. [Getting Started](#getting-started)
3. [Contributing](#contributing)
---
**New Features**
- Added model arguments control
## Overview
I wanted to showcase the true value of GenAI applications,
and the best way was to create a chatbot application for the entire conference.
### Idea
Build an application to support event's participants/attendees.
### Business Objective
Increase participants/attendees satisfaction (CSAT = customer satisfaction).
### Requirements
- GUI (graphical interface).
- Conference Knowledge Base.
- Personalization (unique experience for each user).
### GenAI (ML) Objective
Maximize participants/attendees experience.
### Technologies
- Langchain
- Streamlit
- Weaviate
- OpenAI
### Data gathering
Collected all text information for each session in the calendar.
#### Schedule Content
#### Session Content Example
#### Data Storage
In regard to vector stores, I selected weaviate since they are open source and provide a great free tier.
To create an account visit: [Weaviate - Homepage](https://weaviate.io/)
### Model Selection
I selected OpenAI as the LLM service provider, since they offer a very good price/quality ratio.
- gpt-3.5-turbo
- text-embedding-ada-002
For reference, around 750 words predicted by `gpt-3.5-turbo` costs 0.002 USD.
## Getting Started
### Setup
Create the virtual environment with:
```bash
python -m venv .venv
```
Then, activate it with:
```bash
source .venv/bin/activate
```
Finally, install dependencies with:
```bash
pip install -r requirements.txt
```
### Local Usage
To run the streamlit application locally, use:
```bash
streamlit run app.py
```
This will automatically open a window in your default web browser.
#### Have fun!
## Contributing
### Installing pre-commit
Pre-commit is already part of this project dependencies.
If you would like to installed it as standalone run:
```bash
pip install pre-commit
```
To activate pre-commit run the following commands:
- Install Git hooks:
```bash
pre-commit install
```
- Update current hooks:
```bash
pre-commit autoupdate
```
To test your installation of pre-commit run:
```bash
pre-commit run --all-files
```