felix.ruizdearcaute/natural-language-report-service
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Cleanup

Browse Source
This commit is contained in:
felix
2026-09-27 00:15:18 +02:00
parent ad278dd680
commit 9b0b8a85c9
25 changed files with 588 additions and 1959 deletions
Download Patch File Download Diff File Expand all files Collapse all files

70
src/llm/describe.js
View File

@@ -1,59 +1,9 @@
// A profile as a plain text menu: entities, fields, code lists. Code lists up
// to INLINE_VALUES_MAX are inlined and cached for VALUES_TTL, so the LLM
// never has to search the short ones.
// to INLINE_VALUES_MAX are inlined (and cached), so the LLM never has to
// search the short ones.
import { codeList, INLINE_VALUES_MAX } from './lookup.js';
import { fieldsOf, entityForClass } from '../runner/profile.js';
const INLINE_VALUES_MAX = Number(process.env.INLINE_VALUES_MAX || 50);
const VALUES_TTL = Number(process.env.VALUES_TTL || 3600) * 1000;
// In-memory cache: profile+field → { values, at }. Refreshed lazily when stale.
const cache = new Map();
// codeListValues(profile, queryFn) → map "shapeUri|predicate|inverse"
// → [{ uri, label }]. queryFn runs under the service scope (public graph), so
// code lists read the same regardless of the caller's rights.
export async function codeListValues(profile, queryFn) {
const out = {};
for (const shape of profile.shapes) {
for (const f of shape.fields) {
if (!f.class) continue;
const key = `${shape.uri}|${f.path}|${f.inverse ? 1 : 0}`;
out[key] = await loadCodeList(f, key, queryFn);
}
}
return out;
}
async function loadCodeList(f, key, queryFn) {
if (!f.class) return [];
const hit = cache.get(key);
if (hit && Date.now() - hit.at < VALUES_TTL) return hit.values;
let values = [];
try {
values = await queryCodeList(f.class, queryFn);
} catch (e) {
// the read failed; report nothing, the LLM will use rep:anyOf with words
values = [];
}
cache.set(key, { values, at: Date.now() });
return values;
}
async function queryCodeList(type, queryFn) {
const q = `SELECT ?uri ?label WHERE {
?uri a <${type}> .
OPTIONAL { ?uri <http://www.w3.org/2004/02/skos/core#prefLabel> ?label . }
} ORDER BY ?label LIMIT ${INLINE_VALUES_MAX + 1}`;
const r = await queryFn(q);
const bindings = r.results.bindings;
return bindings.slice(0, INLINE_VALUES_MAX).map(b => ({
uri: b.uri.value,
label: b.label?.value || b.uri.value,
}));
}
export function describeProfile(profile, codeLists = {}) {
export async function describeProfile(profile) {
const lines = [];
lines.push('A spec is Turtle, in exactly this shape (copy these prefixes):');
lines.push('@prefix rep: <http://mu.semte.ch/vocabularies/reporting/> .');
@@ -80,13 +30,12 @@ export function describeProfile(profile, codeLists = {}) {
for (const shape of profile.shapes) {
lines.push(`${shape.label || shape.targetClass} — sh:targetClass <${shape.targetClass}> ; rep:entity <${shape.uri}>`);
for (const f of shape.fields) {
const key = `${shape.uri}|${f.path}|${f.inverse ? 1 : 0}`;
const kind = f.datatype ? datatypeName(f.datatype)
: f.class ? `→ ${conceptLabel(f.class, codeLists[key])}`
: f.class ? `→ ${conceptLabel(f.class, await codeList(f.class))}`
: f.node ? `→ ${linkedLabel(profile, f.node)}`
: '?';
const dir = f.inverse ? ' (inverse)' : '';
const pathShown = typeof f.path === 'string' ? f.path : '?';
const pathShown = f.path || '?';
lines.push(` ${f.name || pathShown} sh:path <${pathShown}>${dir} ${kind}`);
}
lines.push('');
@@ -95,11 +44,10 @@ export function describeProfile(profile, codeLists = {}) {
}
function conceptLabel(type, values) {
const head = values.slice(0, INLINE_VALUES_MAX);
if (!head.length) return short(type);
const names = head.map(v => v.label).join(', ');
if (!values.length) return short(type);
const names = values.map(v => v.label).join(', ');
const more = values.length >= INLINE_VALUES_MAX ? ', …' : '';
return `${short(type)} — ${head.length} waarden: ${names}${more}`;
return `${short(type)} — ${values.length} waarden: ${names}${more}`;
}
function linkedLabel(profile, nodeUri) {