Skip to content

Commit

Permalink
Update README with context. (#1)
Browse files Browse the repository at this point in the history
* Update README with more context.
* Add links and resources
  • Loading branch information
whusterj authored Sep 13, 2023
1 parent e1df2e4 commit d53cec9
Showing 1 changed file with 25 additions and 7 deletions.
32 changes: 25 additions & 7 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,36 +1,54 @@
[![Built with Cookiecutter](https://img.shields.io/badge/built%20with-Cookiecutter-ff69b4.svg?logo=cookiecutter)](https://github.com/cookiecutter/cookiecutter)
[![Built with Cookiecutter](https://img.shields.io/badge/built%20with-Cookiecutter-ff69b4.svg?logo=cookiecutter)](https://github.com/thinknimble/tn-spa-bootstrapper)

# Vector Demonstration
# AI-Enabled Search Engine using LLM Embeddings, Django, and pgvector

A lot of people have asked us for ideas of how they can leverage Large Language Models (LLMs) for their business applications. A common example is to use the native language comprehension capabilities of LLMs to find matching content. This makes LLMs an excellent tool for search!

This repo demonstrates a prototype application that enables searching for job descriptions using an unstructured, English-language description of a job seeker.

## Watch the Demo on Youtube

[![Video: How We're Building AI Search Engines using LLM Embeddings](http://img.youtube.com/vi/ZCPUmC37HLU/0.jpg)](http://www.youtube.com/watch?v=ZCPUmC37HLU "How We're Building AI Search Engines using LLM Embeddings")

## Links & Resources

- https://www.sbert.net/ - Sentence Transformers package for Python
- https://github.com/pgvector/pgvector - Vector database plugin for PostgreSQL
- https://huggingface.co/spaces/mteb/leaderboard - The "Massive Text Embedding" leaderboard from HuggingFace. Look at this to find models you can use to generate embeddings.
- https://www.djangoproject.com/

## Setup

### Docker

If this is your first time...

1. [Install Docker](https://www.docker.com/)
1. Run `pipenv lock` to generate a Pipfile.lock
1. Run `cd client && npm install` so you have node_modules available outside of Docker
1. Back in the root directory, run `make build`
1. `make run` to start the app
1. If the DB is new, run `make create-test-data`
1. SuperUser `[email protected]` with credentials from your `.env`
1. User `[email protected]` with credentials from your `.env` is used by the Cypress
tests
1. SuperUser `[email protected]` with credentials from your `.env`
1. User `[email protected]` with credentials from your `.env` is used by the Cypress
tests
1. View other available scripts/commands with `make commands`
1. `localhost:8080` to view the app.
1. `localhost:8000/staff/` to log into the Django admin
1. `localhost:8000/api/docs/` to view backend API endpoints available for frontend development


### Backend

If not using Docker...
See the [backend README](server/README.md)

### Frontend

If not using Docker...
See the [frontend README](client/README.md)


## Testing & Linting Locally

1. `pipenv install --dev`
1. `pipenv run pytest server`
1. `pipenv run black server`
Expand Down

0 comments on commit d53cec9

Please sign in to comment.