Drupal AI on Halcyon

Halcyon Stellar Works is a made-up shipyard, but everything around it is real Drupal 11. The same ~420 pages are searched with today's keyword search and with AI search, on this site and across its two sister sites, and an AI assistant, editor tools, automation and translation run on the same content. Every AI request goes to amazee.ai: chat models, embeddings and the vector database, all through the Drupal AI module and its amazee.ai provider.

From keywords to meaning, on one site or many

Search has moved from matching words to matching meaning, and from returning links to answering questions. Each approach still has its place. Run one query through keyword and AI search at once, across all sister sites, on the compare search page.

Keyword search with Solr

Search API + Apache Solr · lexical

The traditional approach. Every page is split into words and stored in an inverted index on a Solr server. A query returns pages that contain the words you typed, ranked by how often and where they appear (title matches count more).

Advantages

  • Exact and predictable: names, part numbers and codes are found every time.
  • Fast and cheap at scale; no per-query AI cost.
  • Mature: facets, highlighting, spellcheck, synonyms, stemming.
  • Easy to explain why a result matched.

Disadvantages

  • Needs the right words: "cheap ship for one pilot" finds nothing if pages say "low-cost single-seat courier".
  • Every word must match by default, so longer natural questions return zero results.
  • Synonyms and tuning are manual work.
  • Another server to run and keep in sync.

Best for: known-item lookup, catalogues, admin search, legal or technical text where exact terms matter.

Try “Atlas Heavy Freighter”

One search across every site

AI Search · shared pgvector database or federated API

Halcyon, Ferrovane and Lumen are separate Drupal sites with their own databases. Each can search all three, two ways. Shared database (ingest time): every site embeds its pages into its own collection in one amazee.ai pgvector database, and the searching site embeds the query once and reads every collection. Federated API (query time): the searching site asks each sister's own vector endpoint in parallel and merges the answers by score.

Advantages

  • Visitors find the answer wherever it lives, without knowing which site owns it.
  • Shared database: one embedding call and one ranked list; the chatbot answers across sites too.
  • Federated API: sites stay fully independent and can even use different databases.
  • Scores from one embedding model compare fairly across sites.

Disadvantages

  • Shared database: every site must use the same AI database and embedding model.
  • Federated API: one embedding call per site, and as slow as the slowest sister.
  • Keyword search (Solr here) has no equivalent without a shared index to run and sync.

Best for: organisations with several sites, brands or departments whose visitors don't care where a page is published.

Try a question another site answers

Semantic search with a vector database

AI Search · amazee.ai embeddings · pgvector

Each page is split into chunks, and an embedding model turns each chunk into a long list of numbers that captures its meaning. These vectors live in amazee.ai's Postgres/pgvector database. A query is embedded the same way, and the closest chunks by cosine similarity are returned, whatever words they use.

Advantages

  • Matches meaning: "ore", "mining hauler" and "Belt refinery runs" all land together.
  • Robust to phrasing, typos and synonyms without manual tuning.
  • Cross-lingual by nature with multilingual embedding models.
  • The foundation for RAG: the same index feeds the chatbot below.

Disadvantages

  • Each query needs an embeddings call: slower (seconds, not milliseconds) and has a cost.
  • Indexing is slow and paid: every chunk of every page is embedded.
  • Weak on exact identifiers and rare names; scores are hard to explain.
  • Always returns "nearest" results, even when nothing is truly relevant.

Best for: research, support and knowledge bases where people describe what they need rather than name it.

Try a fuzzy question

Answers, not links: RAG chatbot

AI Assistant API · AI Chatbot · retrieval-augmented generation

Ask Halcyon (bottom right of every page) searches the vector database for the chunks most relevant to your question, then gives them to an LLM with instructions to answer only from that context and link the pages it used. It keeps the conversation, so you can ask follow-ups.

Advantages

  • One direct, conversational answer that combines several pages.
  • Grounded in your own content, with links back to the source.
  • Instructions shape tone, scope and what it refuses to answer.

Disadvantages

  • Slowest option: retrieval plus generation, several seconds per answer.
  • LLM cost per message; needs rate limits on a public site.
  • Can still misread or over-summarise; answers must be checked against the links.

Best for: guided discovery, product advice and support questions.

Open “Ask Halcyon” and try: Which ship can a single pilot fly to Europa?

Side by side

Solr keyword Vector RAG chatbot
Natural-language questionsPoorVery goodVery good
Exact names and codesExcellentFairFair
Typical response time~10–300 ms~1–7 s~5–20 s
AI cost per queryNone1 embeddings callEmbeddings + LLM
InfrastructureSolr serverVector DB + embeddings APIVector DB + embeddings + LLM
Indexing speed (this site)Seconds~40 minutesShares the vector index
Explainable rankingYesSimilarity score onlyVia cited links
Facets and filtersYesMetadata filtersNo
OutputRanked linksRanked passagesA written answer with links
Across sister sitesNo (one index per site)Yes: shared database or federated APIYes: cites pages from every site

In practice, combine them: keyword for precision, vectors for recall (AI Search can also boost a Search API database or Solr index with vector results), and RAG on top when people want an answer.

More Drupal AI on this site

Search is one use of Drupal AI. These run on this site too. Features marked Editor need a login; on a trial or a local copy, use drush uli.

Try it now

Ask Halcyon chatbot

A RAG assistant built with the AI Assistant API and AI Chatbot (Deep Chat) modules, answering from the vector index with links to sources.

Try it: open the chat bubble, bottom right, and ask “Who flies Leviathan Ore Haulers, and how many?”

Try it now

AI search across sister sites

AI Search with amazee.ai embeddings finds pages by meaning on this site and on its two sister sites, compared side by side with the site's Solr keyword search.

Try it: search in plain language and watch Solr come back empty while both AI columns find pages on other sites.

Open compare search
Editor

AI in the editor (CKEditor)

An AI button in the CKEditor toolbar: continue writing, summarise, change tone (including “Mission briefing”), translate, fix spelling, reformat HTML, or run your own prompt on selected text.

Try it: Content › Add content › Blog post, select a paragraph, click the AI button.

Add a blog post
Editor

AI Automators

Fields that fill themselves. Blog post tags are chosen by an LLM from the body when you save, reusing existing tags where they fit. Automators can also write summaries, extract data, generate images or chain steps.

Try it: save a blog post with an empty Tags field, then look at its tags.

Editor

AI Content Suggestions

On every edit form: suggested titles, a summary, a readability check, tone analysis, content moderation, and taxonomy term suggestions for the text you wrote.

Try it: edit any ship or post and open the AI suggestions panel.

Edit the Atlas Heavy Freighter
Editor

AI Translate

One-click translation of whole pages into German, French and Japanese, as real Drupal translations you can review and edit.

Try it: open a page's Translate tab and choose “AI Translate”.

Translate a ship page
Admin

AI API Explorer

A playground for site builders: try chat, embeddings and other operations against any configured provider and model, and see the code to call them from PHP.

Open the explorers
Admin

AI Logging

Every prompt this site sends is logged with its provider, model and tags, so you can see exactly what goes to the AI and what each feature costs.

View the AI log
Admin

One provider: amazee.ai

Chat, embeddings and the vector database all come from the amazee.ai provider. Features ask for model aliases like chat and embeddings, keys live in the Key module, and switching provider is one setting.

AI default providers

What else Drupal AI can do

Not installed on this demo, but part of the same ecosystem:

  • AI Agents: agents that build content types, fields and views, or edit content, from a chat prompt.
  • Image AI: alt text generation, image classification and image generation in automators.
  • ECA + AI: no-code workflows where an AI step classifies, routes or rewrites content on events.
  • Field widget actions and AI validations: AI buttons next to any field, and validation rules written in plain language.
  • External moderation: screening of user-submitted text before it reaches an LLM.
  • MCP: exposing Drupal content and actions to external AI tools.