DarGlobal
Company overview ↗ Portfolio and project discovery ↗ Investor relations ↗ Selected project details ↗METHOD NOTE
Useful answers need
bounded evidence.
This assistant answers from a pre-ingested snapshot of curated public DarGlobal and Wasalt material. It does not crawl the web while you wait for an answer.
Current indexed snapshot
Thirteen curated public pages
Wasalt
Platform overview and FAQ ↗ Saudi property-search landing page ↗ Search and city/category landing pages ↗The corpus includes six DarGlobal overview, portfolio, investor, editorial, and project pages, plus seven Wasalt platform, city, and corporate pages. It is not a claim that every public URL has been indexed. Each crawl stores the source URL, title, timestamp, cleaned Markdown, and content hash before the text is chunked and indexed.
Technical architecture
Ingestion and retrieval flow
URLs
render + clean
heading chunks
source snapshot
+ Qdrant
Simple single-topic property questions take the fast route. Complex questions can be decomposed into up to five subquestions, reviewed, and rewritten once before an answer is produced. A general greeting takes the isolated conversation route and never searches the knowledge base.
Controlled expansion
What the crawler excludes
Source allowlist
Only the reviewed public DarGlobal and Wasalt hosts above are eligible for this corpus.
Refresh strategy
Re-run the ingestion job on a schedule or after a reviewed seed update; do not crawl during a chat request.
Explicit exclusions
Login and registration flows, forms, privacy pages, duplicate URL variants, personal contact details, and an unbounded crawl of live individual listings.
Dynamic inventory is a timestamped public snapshot, not a complete live catalogue. New seed URLs are reviewed before they are added to the crawler configuration.
Answer lifecycle
- Crawl offline. Crawl4AI renders approved public pages and produces cleaned Markdown.
- Preserve provenance. Postgres retains the source document and metadata; Qdrant stores retrieval vectors.
- Retrieve deliberately. Hybrid BM25 and vector search selects up to eight evidence chunks.
- Respond with proof. The answer agent can cite only the retrieved chunk IDs; the citation guard maps them to the source cards shown in chat.
Design decisions
Pre-ingested, not live-crawled
It gives predictable latency, reproducible answers, and an auditable source snapshot.
Grounded by default
Unsupported property facts, pricing, availability, and terms are declined instead of inferred.
Bounded agent workflow
Compound questions may create up to five retrieval subquestions and one focused rewrite; simple requests use the faster single-query path.