code example

Build FAQ Search with altor-vec

What this pattern solves: Intent-based answer lookup for help centers and support widgets.

FAQ content usually has short questions but many ways to ask the same thing. Semantic search helps one answer cover variants such as 'cancel plan', 'end subscription', or 'stop renewal' without manually tuning every synonym.

A browser-side FAQ index is especially useful in support widgets because it makes suggestions appear instantly before a user submits a ticket. That lowers support load without adding another backend dependency.

Install

npm install altor-vec

Concept explanation

In a faq search workflow, users usually describe intent in their own words. That is why vector search works well here: each record is turned into an embedding, the embeddings are indexed once, and later queries retrieve the nearest semantic neighbors instead of relying only on exact tokens. In practice this means the interface can respond to paraphrases, shorthand, and partial descriptions far better than a literal-only search box.

The browser is often the right place to do this when the corpus is moderate in size and safe to ship. The instant benefit is lower latency. The architectural benefit is that you remove a whole search service from the request path. That matters for keystroke-heavy interactions, offline-capable apps, and product surfaces where search should feel like a UI primitive rather than a network round trip.

This page uses a deterministic embedding helper so the sample is runnable with only altor-vec installed. That keeps the example honest and easy to paste into a demo project. The same retrieval pattern can power both the quick-answer layer and the context picker for a later chat or ticket workflow.

Representative browser benchmark: ~54KB gzipped library payload, sub-millisecond local query time on a moderate corpus, and no per-query API dependency. Exact numbers depend on vector dimensions, index parameters, and device class.

Runnable JavaScript example

The following snippet indexes a small in-memory dataset, performs a semantic lookup for how do I stop my subscription, and prints the nearest matches. It uses the real altor-vec API, including init(), WasmSearchEngine.from_vectors(), and search().

import init, { WasmSearchEngine } from 'altor-vec';

        const dims = 12;
        const records = [
  {
    "title": "How do I cancel my plan?",
    "text": "Open Billing, choose the current plan, and select cancel renewal.",
    "meta": "billing"
  },
  {
    "title": "Can I invite another admin?",
    "text": "Workspace owners can promote teammates from the members screen.",
    "meta": "team"
  },
  {
    "title": "Where do I download invoices?",
    "text": "Invoices are available under Billing history for every paid cycle.",
    "meta": "billing"
  },
  {
    "title": "How do I reset MFA?",
    "text": "An owner can reset multi-factor authentication for a locked-out user.",
    "meta": "security"
  },
  {
    "title": "Does the app work offline?",
    "text": "Core browsing features work offline after the first sync completes.",
    "meta": "product"
  },
  {
    "title": "How do I export data?",
    "text": "Use the exports page to create CSV or JSON downloads.",
    "meta": "data"
  }
];

        function embedText(text) {
  const vector = new Float32Array(dims);
  for (const token of text.toLowerCase().split(/[^a-z0-9]+/).filter(Boolean)) {
    let hash = 2166136261;
    for (const char of token) {
      hash = Math.imul(hash ^ char.charCodeAt(0), 16777619);
    }
    const slot = Math.abs(hash) % dims;
    vector[slot] += 1;
    vector[(slot + token.length) % dims] += token.length / 10;
  }
  const magnitude = Math.hypot(...vector) || 1;
  return Array.from(vector, (value) => value / magnitude);
}

        async function main() {
          await init();

          const flat = new Float32Array(
            records.flatMap((record) => embedText(`${record.title} ${record.text} ${record.meta}`))
          );

          const engine = WasmSearchEngine.from_vectors(flat, dims, 16, 200, 64);
          const hits = JSON.parse(engine.search(new Float32Array(embedText('how do I stop my subscription')), 4));

          const results = hits.map(([id, distance]) => ({
            ...records[id],
            similarity: Number((1 - distance).toFixed(3)),
          }));

          console.table(results);
          engine.free();
        }

        main();

React component version

The React version keeps the same index build but wires it into component state so the UI can query on input changes. That is usually how teams introduce semantic retrieval into an existing product: initialize once, keep the engine in memory, and map nearest-neighbor hits back to the original records.

import { useEffect, useState } from 'react';
        import init, { WasmSearchEngine } from 'altor-vec';

        const dims = 12;
        const records = [
  {
    "title": "How do I cancel my plan?",
    "text": "Open Billing, choose the current plan, and select cancel renewal.",
    "meta": "billing"
  },
  {
    "title": "Can I invite another admin?",
    "text": "Workspace owners can promote teammates from the members screen.",
    "meta": "team"
  },
  {
    "title": "Where do I download invoices?",
    "text": "Invoices are available under Billing history for every paid cycle.",
    "meta": "billing"
  },
  {
    "title": "How do I reset MFA?",
    "text": "An owner can reset multi-factor authentication for a locked-out user.",
    "meta": "security"
  },
  {
    "title": "Does the app work offline?",
    "text": "Core browsing features work offline after the first sync completes.",
    "meta": "product"
  },
  {
    "title": "How do I export data?",
    "text": "Use the exports page to create CSV or JSON downloads.",
    "meta": "data"
  }
];

        function embedText(text) {
  const vector = new Float32Array(dims);
  for (const token of text.toLowerCase().split(/[^a-z0-9]+/).filter(Boolean)) {
    let hash = 2166136261;
    for (const char of token) {
      hash = Math.imul(hash ^ char.charCodeAt(0), 16777619);
    }
    const slot = Math.abs(hash) % dims;
    vector[slot] += 1;
    vector[(slot + token.length) % dims] += token.length / 10;
  }
  const magnitude = Math.hypot(...vector) || 1;
  return Array.from(vector, (value) => value / magnitude);
}

        export function FaqSearchExample() {
          const [engine, setEngine] = useState(null);
          const [query, setQuery] = useState('');
          const [results, setResults] = useState([]);

          useEffect(() => {
            let cancelled = false;
            let instance;

            (async () => {
              await init();
              const flat = new Float32Array(
                records.flatMap((record) => embedText(`${record.title} ${record.text} ${record.meta}`))
              );
              instance = WasmSearchEngine.from_vectors(flat, dims, 16, 200, 64);
              if (!cancelled) setEngine(instance);
            })();

            return () => {
              cancelled = true;
              instance?.free();
            };
          }, []);

          useEffect(() => {
            if (!engine || query.trim().length < 2) {
              setResults([]);
              return;
            }

            const hits = JSON.parse(engine.search(new Float32Array(embedText(query)), 5));
            setResults(
              hits.map(([id, distance]) => ({
                ...records[id],
                similarity: Number((1 - distance).toFixed(3)),
              }))
            );
          }, [engine, query]);

          return (
            <section>
              <input
                value={query}
                onChange={(event) => setQuery(event.target.value)}
                placeholder="Ask a support question"
              />
              <ul>
                {results.map((result) => (
                  <li key={result.title}>
                    <strong>{result.title}</strong> — {result.meta} (score {result.similarity})
                  </li>
                ))}
              </ul>
            </section>
          );
        }

How this example works

The pattern has three moving parts. First, you choose what text represents each record: title, description, metadata, or a chunk of content. Second, you turn that text into vectors and flatten them into one Float32Array. Third, you build the HNSW graph and query it with a vector created from the user input. The library returns nearest-neighbor IDs and distances, and your app decides how to display or post-process them.

Because the retrieval step is approximate nearest-neighbor search, it stays fast even as the dataset grows beyond trivial linear scans. The most important quality lever is still the embedding model. Better vectors usually matter more than micro-optimizing ANN parameters, so teams should benchmark retrieval quality on real user phrasing before shipping the experience widely.

When to use this pattern

This is a practical fit when the search corpus is small to medium, shipped with the app, and searched frequently enough that backend latency would be noticeable. Common examples include docs portals, embedded support widgets, local-first assistants, and curated catalogs.

Support widgets
Help centers
In-app onboarding guidance
Customer success portals

Limitations

FAQ search still depends on content quality. If answers are outdated or too broad, semantic retrieval will faithfully find weak material. You may also need analytics to understand which unanswered intents deserve new content.

Be especially careful about corpus size, update frequency, and data sensitivity. Browser vector search is excellent when those three constraints are favorable, but it is not the right answer when the dataset is huge, private, or changing constantly for every user.

FAQ

Is vector search useful even for small FAQ sets?

Yes, because the value is not only scale. It is also about matching messy user phrasing to the right answer instantly.

Can I keep the widget offline-capable?

Yes. A local FAQ index works well in PWAs or embedded help panels that should continue responding without a network trip.

Should I replace keywords completely?

Not necessarily. Many teams combine vector retrieval with exact filters for account IDs, product names, or feature flags.

Get started: npm install altor-vec · GitHub