https://github.com/joeywhelan/unstructured-es
Demonstration of unstructured data search with Elastic + Jina
https://github.com/joeywhelan/unstructured-es
elasticsearch jinaai python unstructured-data
Last synced: 22 days ago
JSON representation
Demonstration of unstructured data search with Elastic + Jina
- Host: GitHub
- URL: https://github.com/joeywhelan/unstructured-es
- Owner: joeywhelan
- License: mit
- Created: 2026-03-14T19:54:45.000Z (about 1 month ago)
- Default Branch: main
- Last Pushed: 2026-03-28T14:24:54.000Z (30 days ago)
- Last Synced: 2026-03-28T16:58:23.676Z (30 days ago)
- Topics: elasticsearch, jinaai, python, unstructured-data
- Language: Jupyter Notebook
- Homepage: https://www.linkedin.com/feed/update/urn:li:ugcPost:7438677849252999168/
- Size: 13.1 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Unstructured Data Search with Elastic + Jina
## Contents
1. [Summary](#summary)
2. [Architecture](#architecture)
3. [Features](#features)
4. [Prerequisites](#prerequisites)
5. [Installation](#installation)
6. [Usage](#usage)
## Summary
This is a demonstration of various search scenarios against technical product manuals using Elasticsearch and Jina models.
## Architecture
## Features
- Jupyter notebook
- Builds an Elastic Serverless deployment via Terraform
- Creates a data set from iFixit technical manuals.
- Utilizes the Jina Reader to parse the tech manual contents.
- Utilizes the Jina embeddings v5 model to embed the manual content.
- Performs four different search scenarios that demonstrate the enhanced search capabilities
- Deletes the entire deployment via Terraform
## Prerequisites
- terraform
- Elastic Cloud account and API key
- Jina API key
- Python
## Installation
- Edit the terraform.tfvars.sample and rename to terraform.tfvars
- Create a Python virtual environment