Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.moorcheh.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
What is Moorcheh On-Prem?

Moorcheh On-Prem runs on your machine: semantic search over text documents and precomputed vectors, with embeddings powered by Ollama. You install the moorcheh-client package from PyPI, start the stack with one command, and call the API from your app or the CLI.
PyPI packagemoorcheh-client
CLImoorcheh
Python importfrom moorcheh import MoorchehApiClient
Server imagemoorcheh/server:latest (Docker Hub)
Default APIhttp://localhost:8080
Data on disk~/.moorcheh/data
On-prem has no API keys. Start the server with moorcheh up, then call the API on localhost or your trusted network.

​
What you can do

  • Create text namespaces (documents embedded via Ollama) or vector namespaces (you supply vectors)
  • Upload, get, and delete items by id
  • Semantic search across one or more namespaces
  • Check global storage quota via /health
AI Answer (LLM-generated responses from search context) is available on Moorcheh Cloud, not in on-prem today. On-prem provides search/retrieval; you can pass results to your own LLM if needed.

​
Prerequisites

  • Python 3.10+
  • Docker (Desktop or Engine)
  • Ollama for embeddings — either already running on the host (127.0.0.1:11434) or started via moorcheh up --bundled-ollama

​
Install and run

pip install moorcheh-client
moorcheh up
moorcheh status
See Quickstart for a full upload-and-search walkthrough.

​
Limits

  • Unlimited namespaces - no cloud-tier namespace count limit; create as many text or vector namespaces as you need
  • 100,000 items total across all namespaces (text + vectors)
  • Item ids are unique per namespace (the same id string may exist in different namespaces)
  • Get/delete by id: at most 100 ids per request

​
Documentation

SectionUse when
PrerequisitesInstall Python, Docker, and Ollama
QuickstartFirst run end-to-end
API referenceIntegrating via HTTP / curl
Python clientBuilding apps with MoorchehApiClient
CLILocal ops and testing with moorcheh

​
Data persistence

Vectors and documents are stored under: 
~/.moorcheh/data/
 moorcheh_data_store.json
 namespace_registry.json
moorcheh down stops containers but does not delete this folder. Back up ~/.moorcheh to save everything.