Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/No-Country-simulation/G9-LATAM-Team-58/llms.txt

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

Mindloom turns a pile of technical articles, documentation, and tutorials into a structured, searchable knowledge base. Paste in any technical text and Mindloom classifies it into one of eight categories, extracts its keywords, finds semantically related content already in your corpus, and makes everything discoverable by meaning — not just by matching words.

Introduction

Learn what Mindloom does, how the system works end-to-end, and which problem it solves.

Quickstart

Run Mindloom locally in minutes and ingest your first piece of technical content.

API Reference

Explore every endpoint: ingest content, search by meaning, browse the knowledge map.

Architecture

Understand the four-layer system: Web, API, Inference Service, and Oracle ADB.

What Mindloom does

Semantic Search

Find content by meaning using multilingual sentence embeddings and Oracle Vector Search.

Auto-Classification

Every ingested item is assigned to one of 8 categories — Backend, Frontend, Databases, and more.

Knowledge Map

Visualize the entire corpus as a 2D scatter plot, colored by category, powered by UMAP.

Batch Upload

Ingest hundreds of items at once by uploading a CSV file via the web UI or API.

Get up and running

1

Clone and configure

Clone the repository and copy .env.example to .env, filling in your Oracle Autonomous Database credentials.
2

Start the services

Run docker compose up to bring up the API and inference containers. The inference service downloads the model artifact from OCI Object Storage on first startup.
3

Launch the web UI

In the web/ directory run npm run dev to start the React development server at http://localhost:5173.
4

Ingest your first content

Paste a technical article title and body into the Analyze page, or call POST /content directly. Mindloom returns a category, confidence score, keywords, and related items instantly.
Mindloom requires Java 25, Python 3.12, Node 22, and Docker. Each service documents its own environment variables and configuration in its own README.md.

Build docs developers (and LLMs) love