What is Moorcheh Edge?
Moorcheh Edge runs locally on your machine for fast vector upload and similarity search. You provide 1024-dimensional embedding vectors; the server binarizes them and searches on-device without cloud calls.
| |
|---|
| PyPI package | moorcheh-edge |
| CLI | moorcheh-edge |
| Python import | from moorcheh_edge import MoorchehEdge |
| Server image | moorcheh/moorcheh-edge:latest (Docker Hub) |
| Default API | http://localhost:8080 |
| Data on disk | ~/.moorcheh-edge/data |
Edge has no API keys. Start the server with moorcheh-edge up, then call the API on localhost.
What you can do
- Upload or replace vectors by id
- Search with a 1024-float query vector
- Delete vectors by id
- Check store health and quota via
/health
Moorcheh Edge is vector-only. Plain text queries are rejected. Generate embeddings in your app or upstream service first.
Prerequisites
- Python 3.10+
- Docker (Desktop or Engine)
No Ollama required.
Install and run
pip install moorcheh-edge
moorcheh-edge up
moorcheh-edge status
Documentation
| Section | Use when |
|---|
| Quickstart | First run end-to-end |
| Limits | Free tier and 10k store cap |
| API reference | HTTP integration |
| Python client | Apps with MoorchehEdge |
| CLI | Local ops with moorcheh-edge |
Data persistence
Vectors are stored under:
~/.moorcheh-edge/data/
moorcheh_edge_store.json
moorcheh-edge down stops the container but does not delete this folder.
