Who it is forA user who wants to keep documents local and avoid paying for an API key.
The problemCloud LLM providers need an account and key, and some documents should not leave your computer.
The outcomeA local wiki that answers questions using a model that runs on your computer.
What you need first
- Python 3.11 or later, or uv to install it
- An API key for OpenRouter, OpenAI, Gemini or another OpenAI-compatible server, or Ollama installed for free local use
- Documents as text, Markdown, PDF, Word, PowerPoint, Excel or OpenDocument files
Steps
- Download Ollama from https://ollama.com/download and install it.
- Run
ollama pull gemma4. - Install the library with
pip install llmwiki2. - Run
llmwiki2, pick Ollama on the page, press Test connection, then Save and start. - Drop your documents on the page and ask a question to check the cited answer.
Prompt for your agent
Set up the llm-wiki-v2 repo with Ollama as the provider and gemma4 as the model, then file <document> and ask <question>. Expected output: a cited answer. Verify that the model call went to the local Ollama server, not a remote provider.
Caveat. The README says CROW's classifier is remote by default, so a fully local setup needs extra configuration or runs in classic mode without a classifier.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page