amosblomqvist
f5edc7f0a5
Louvain only ever found the reasoning chains (the graph is disconnected by nature — every connected component became its own cluster) and edge-orphans could never join anything. Clusters are now RELATED TOPICS: propositions grouped by meaning. - Embedder (src/server/embeddings.ts): in-process transformers.js v4 running EmbeddingGemma-300M q8 (MTEB 68.4, ~300MB one-time download), MRL-truncated to 512d, "title: none | text:" prefix on 100% of inputs, L2-normalized so cosine = dot. Model/dim mismatch voids the ledger (full re-embed). Injected at the composition root — the agent layer never imports the server layer (architecture law). - Ledger (data/graph/embeddings.json): model + dim + vectors + the persisted cluster partition. Reclustering runs at the END of every embedding batch (post-merge hook, both front doors) — never per read (the agglomerative pass is ~1.5s at 338 nodes). - Clustering (src/core/semantic-clusters.ts): hand-rolled average-linkage agglomerative over cosine (npm HDBSCAN is an abandoned alpha). Stragglers stay singletons by default; attachStragglers is the all-in toggle. Threshold 0.60 swept on the real graph: 26 topics, 74/90 edge-orphans land in real topics, 10 stragglers. - Consumers (snapshot, settle, namer, replay) read the persisted partition — one cluster concept everywhere; core-survival label matching unchanged (20/26 topics kept labels). - Louvain retired: detectCommunities + graphology* deps deleted (graphology-louvain had leaked into the client bundle since the clusters wave); scripts/bench-graph.ts (dead FA2 bench) removed. - scripts/embed-graph.ts: backfill/cold-start (338 nodes in 150s including the one-time model download).
70 lines
2.9 KiB
TypeScript
70 lines
2.9 KiB
TypeScript
/**
|
|
* Import raw notes files through the format-agnostic front door (vision §1,
|
|
* 2026-09-13) — every *.md / *.txt file in a directory becomes one
|
|
* extraction run (extractor → auditor → merger) over its raw text. Run
|
|
* from this worktree only — data never crosses trees:
|
|
*
|
|
* npx tsx --env-file=.env.local scripts/import-notes.ts <dir> [concurrency]
|
|
*
|
|
* Default dir: real-data-extraction/learn-sessions (the prototype
|
|
* learning-session exports — deliberately NOT imported as chats: they run
|
|
* through the notes path, raw). Runs in this process: the dev server's
|
|
* status chips do NOT see them (registry is per-process) — the dev server
|
|
* sees runs triggered through /api/graph/import.
|
|
*/
|
|
import * as fs from "node:fs";
|
|
import * as path from "node:path";
|
|
import { createExtractionPipeline } from "../src/agent/subagents/extraction.ts";
|
|
import { embedNewNodes } from "../src/server/embeddings.ts";
|
|
import { clusterNamingSettled } from "../src/agent/subagents/cluster-namer.ts";
|
|
import { getGraph } from "../src/core/graph.ts";
|
|
import { stores } from "../src/server/stores.ts";
|
|
|
|
async function main() {
|
|
const dir = process.argv[2] ?? "real-data-extraction/learn-sessions";
|
|
const limit = Number(process.argv[3] ?? 4);
|
|
const files = fs
|
|
.readdirSync(dir)
|
|
.filter((f) => f.endsWith(".md") || f.endsWith(".markdown") || f.endsWith(".txt"))
|
|
.sort();
|
|
console.log(`[import-notes] ${files.length} note files from ${dir} (concurrency ${limit})`);
|
|
|
|
const pipeline = createExtractionPipeline({ ...stores, embedder: embedNewNodes });
|
|
const queue = [...files];
|
|
const totals = { nodes: 0, edges: 0, events: 0, failed: 0 };
|
|
const workers = Array.from({ length: Math.min(limit, files.length) }, async () => {
|
|
for (;;) {
|
|
const file = queue.shift();
|
|
if (!file) return;
|
|
const filePath = path.join(dir, file);
|
|
const t0 = Date.now();
|
|
try {
|
|
const stats = await pipeline.importNotes({ filePath, text: fs.readFileSync(filePath, "utf-8") });
|
|
totals.nodes += stats.nodes;
|
|
totals.edges += stats.edges;
|
|
totals.events += stats.events;
|
|
console.log(
|
|
`[import-notes] ${file}: ${stats.nodes} nodes, ${stats.edges} edges, ${stats.events} events in ${((Date.now() - t0) / 1000).toFixed(1)}s`,
|
|
);
|
|
} catch (err) {
|
|
totals.failed++;
|
|
console.error(`[import-notes] ${file} FAILED:`, err);
|
|
}
|
|
}
|
|
});
|
|
await Promise.all(workers);
|
|
|
|
// The post-merge cluster naming is fire-and-forget inside the pipeline;
|
|
// settle it before the process exits so labels actually land.
|
|
await clusterNamingSettled();
|
|
|
|
const graph = getGraph(stores.graphStore);
|
|
const labels = stores.graphStore.readClusterLabels().length;
|
|
console.log(
|
|
`[import-notes] done: +${totals.nodes} nodes, +${totals.edges} edges, +${totals.events} events, ${totals.failed} failed — ` +
|
|
`graph now ${graph.nodes.length} nodes, ${graph.edges.length} edges, ${graph.events.length} events, ` +
|
|
`${labels} named clusters`,
|
|
);
|
|
}
|
|
|
|
main(); |