9fe466a144db66cde5643b7b33b78a998253372b
Concept Maker
A Tauri desktop app that turns raw ideas, notes, URLs, and files into a clear project concept. The UI is React/Vite, the desktop shell is Tauri, and the Python backend is exposed through concept_api.py.
Features
- Add files, folders, and URLs as source material.
- Write freeform notes and ask a local Ollama model to rephrase, extend, or generate a concept.
- Build a JSONL knowledge base from selected files using
corpus_builder.pywhen available, with a lightweight fallback in the backend. - Search for prior art through SearXNG and Ollama embeddings.
- Preview concepts as Markdown/PDF.
- Generate an image prompt and optional image asset for a concept.
- Save and reopen local sessions.
Requirements
- Node.js and npm
- Rust toolchain
- Python 3.9+
- Ollama running locally, defaulting to
http://localhost:11434 - Optional local SearXNG instance for prior-art search, defaulting to
http://localhost:8888
Python packages are listed in requirements.txt. Some features also depend on external command-line tools:
pandocorwkhtmltopdffor higher-quality Markdown to PDF exporttesseractandocrmypdffor OCR-heavy ingestionffmpeg/ffprobefor media handling
Setup
Install JavaScript dependencies:
npm install
Install Python backend dependencies:
python3 -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip
pip install -r requirements.txt
Ensure Ollama is running before using model-backed actions:
ollama serve
Development
Run the desktop app:
npm run dev
Run the web UI in a browser:
npm run dev:web
Build the frontend:
npm run build
Build the desktop bundle:
npm run tauri build
Project Layout
src/: React frontendsrc-tauri/: Tauri desktop shell and Rust commandsconcept_api.py: JSON action backend invoked by Tauricorpus_builder.py: optional richer file ingestion pipelinewebsearch.py: prior-art search helpersrequirements.txt: Python backend dependencies
Configuration
Environment variables:
OLLAMA_HOST: override the Ollama URLIDEA_HOLE_MODEL: default model nameSEARX_URL: default SearXNG base URL
Runtime data is stored in .idea-hole/.
Description
A tool for building and managing specialized text corpora. It processes raw data into structured datasets, enabling advanced concept modeling and linguistic analysis for creative projects.
Languages
Python
68.4%
TypeScript
20.3%
CSS
5.6%
Rust
4.2%
JavaScript
1.3%
Other
0.2%