{
  "path": "/projects/llm-analyser",
  "site": "at://did:plc:ofrbh253gwicbkc5nktqepol/site.standard.publication/3mfyq5mpohw25",
  "tags": [
    "ai",
    "pkgs",
    "python",
    "tooling"
  ],
  "$type": "site.standard.document",
  "title": "llm-analyser",
  "description": "Python tool for analysing .docx files and generating essays using a local Ollama model — now part of the @ewanc26/pkgs monorepo.",
  "publishedAt": "2026-02-24T00:00:00.000Z",
  "textContent": "llm-analyser is a Python CLI tool that reads all .docx files in a given directory and uses a locally-running Ollama model to generate analytical essays for each one. Output essays are saved to a new folder named <directory>_essays in the project root.\n\nThis tool is now part of the @ewanc26/pkgs monorepo.\n\nSetup\n\nRequires Python 3 and Ollama running locally.\n\nCreate the custom Ollama model from the included Modelfile:\n\nUsage\n\nFor example:\n\nThis reads all .docx files in Poetry/ and saves generated essays to Poetry_essays/ in the project root.\n\nCustomising the Model\n\nEdit the Modelfile to change the system prompt, base model, or generation parameters. If you change the FROM line, rebuild with ollama create.\n\nLicence\n\nSee repository.",
  "canonicalUrl": "https://docs.ewancroft.uk/projects/llm-analyser"
}