Metadata-Version: 2.4
Name: webiks-hebrew-ragbot
Version: 1.4.0
Summary: A search engine using machine learning models and Elasticsearch for advanced document retrieval.
Home-page: https://github.com/shmuelrob/ragbot
Author: Shmuel Robinov
Author-email: shmuel_robinov@webiks.com
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: elasticsearch==8.17.1
Requires-Dist: sentence-transformers==3.4.1
Requires-Dist: torch==2.6.0
Requires-Dist: transformers==4.48.3
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# **Webiks-Hebrew-RAGbot**

## **Overview**

This project is a search engine that uses machine learning models and Elasticsearch to provide advanced document retrieval.
You can use [Webiks-Hebrew-RAGbot-Demo](https://github.com/NNLP-IL/Webiks-Hebrew-RAGbot-Demo) to demonstrate the engine's document retrieval abilities

## **Features**

Document representation and validation
Document embedding and indexing in Elasticsearch
Advanced search using machine learning model
Integration with LLM (Large Language Model) client for query answering

## **Installation**

1.  Clone the repository:
   
`git clone https://github.com/NNLP-IL/Webiks-Hebrew-RAGbot.git`

`cd Webiks-Hebrew-RAGbot`

2.  Create a virtual environment and activate it:Â Â 

`python -m venv venv`

`source venv/bin/activate`

On Windows use `\venv\\Scripts\\activate\`

3.  Install the required dependencies:Â Â 

`pip install -r requirements.txt`

## **Configuration**

Set the following environment variables:Â Â 

MODEL_LOCATION: Path to the model directory 
ES_EMBEDDING_INDEX_LENGTH: Size of any index in elasticsearch
EMBEDDING_INDEX: The name of the index we will embed docs into
