When I get home I'd like to do some experimentation with an LLM running locally on my Mac to query all of my blog posts.
I can use something like Ollarma to spin up Gemma 3 and then send HTTP requests to it via TypeScript.
So load all the markdown files like this
import fg from "fast-glob";
import fs from "fs/promises";
import path from "path";
export async function loadMarkdownFiles(folder: string) {
const files = await fg("**/*.md", { cwd: folder, absolute: true });
const posts: { filename: string; content: string }[] = [];
for (const file of files) {
const content = await fs.readFile(file, "utf8");
posts.push({ filename: path.basename(file), content });
}
return posts;
}
and have an HTTP client
import axios from 'axios';
export async function askGemma(prompt: string): Promise<string> {
const response = await axios.post('http://localhost:11434/api/generate', {
model: 'gemma3:1b',
prompt,
stream: false,
});
return response.data.response;
}
and then prompt the LLM like this
import { loadMarkdownFiles } from "./blog-loader";
import { askGemma } from "./ollama-client";
const folder = `${process.env.HOME}/Desktop/notes`;
async function main() {
const posts = await loadMarkdownFiles(folder);
const combinedText = posts.map(p => p.content).join("\n\n");
const question = "What are the main themes across my blog posts?";
const prompt = `${combinedText}\n\nAnswer the question: ${question}`;
const answer = await askGemma(prompt);
console.log("🤖 Gemma says:\n", answer);
}
main();
It seems simple enough. Not sure how much value I get out of being able to query all of my blog posts but it's an interesting experiment.
