https://github.com/mikeralphson/vectorvictor

Process documents and store chunks and embeddings for textual search
https://github.com/mikeralphson/vectorvictor

ai documentation embeddings machine-learning search vectors

Last synced: 2 months ago
JSON representation

Process documents and store chunks and embeddings for textual search

• Host: GitHub
• URL: https://github.com/mikeralphson/vectorvictor
• Owner: MikeRalphson
• Created: 2023-04-04T13:37:34.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-09-30T06:48:27.000Z (9 months ago)
• Last Synced: 2024-10-05T19:21:49.689Z (8 months ago)
• Topics: ai, documentation, embeddings, machine-learning, search, vectors
• Language: JavaScript
• Homepage:
• Size: 1.92 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Vector-Victor

![logo](./logo.webp)

![screenshot](./screenshot.webp)

## SQL tables needed

* See `tables-*.sql`

## Included scripts

* create embeddings using OpenAI API (`importFile.js` and `importBlog.js`)

* cache queries and search by cosine affinity (`query.js`)

* link queries to prompts to correct errors (`link.js`)

## TODO

* Allow to run with `sqlite-vss` as well as Postgres and `pgvector` extension