https://github.com/derak-isaack/eabl-rag-application

Retrieval Application for EABL 2023 financial report
https://github.com/derak-isaack/eabl-rag-application

langchain-python openai rag streamlit

Last synced: 2 months ago
JSON representation

Retrieval Application for EABL 2023 financial report

• Host: GitHub
• URL: https://github.com/derak-isaack/eabl-rag-application
• Owner: derak-isaack
• Created: 2024-05-27T19:45:48.000Z (about 2 years ago)
• Default Branch: master
• Last Pushed: 2024-05-28T00:44:58.000Z (about 2 years ago)
• Last Synced: 2025-03-14T12:22:23.548Z (over 1 year ago)
• Topics: langchain-python, openai, rag, streamlit
• Language: Python
• Homepage:
• Size: 28.1 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: Readme.md

Awesome Lists containing this project

README

          
## 


 EABL RAG(Retrival Augmented Graph) APPLICATION  
 


![Python](https://img.shields.io/badge/Python-3776AB?logo=python&logoColor=fff&style=for-the-badge)

![streamlit](https://img.shields.io/badge/Streamlit-FF4B4B?logo=streamlit&logoColor=fff&style=for-the-badge)

![OpenAI](https://img.shields.io/badge/OpenAI-412991?logo=openai&logoColor=fff&style=for-the-badge)

### 


 Project Overview 


RAG (Retrieval-Augmented Generation) applications enable querying of unstructured data, including PDF files, by converting them into word embeddings and then into vectors. This allows for efficient similarity searches when a user inputs a specific query. The use of API Keys is essential, regardless of the model being used.

### 


 Objective 


Build and deploy a RAG application to allow user interaction with the **`2023 EABL financial report.`**

The user has to use their own API KEYS which can be found [here](https://platform.openai.com/api-keys)

### 


 Deployment 


The [Streamlit](https://eabl-rag-application-lubbmb9wvwgos3jegn4xwe.streamlit.app/) application has a simple UI and only requires an `OPEN AI KEY` as the input. The data can be found in the `repo` for further understanding before running the queries. 

Below is the deploymnet screenshot 

![Deployment]()

To run the model locally, run the command `pip install requirements.txt` to install the required dependencies.