RAG: the pages it generated
Retrieval-augmented generation over this dealer's data. Every vehicle and store page is expanded into plain-text Markdown you can browse below, pull as one bulk corpus, or query live with the rag_search tool.
How the RAG corpus works
Each vehicle and store page is written out as clean Markdown and concatenated into a single bulk corpus, llms-full.txt (3,315 KB). An agent can ingest the whole corpus, or call rag_search(query) over the MCP endpoint to retrieve just the matching chunks with source links. Everything below is a real generated page you can open.
Every document is checked against an admission policy before it joins the corpus. Search-results and filter pages are refused, interface furniture and text that repeats across the corpus is removed, thin and near-identical documents are refused, and each refusal is recorded with its reason.
| Document type | Documents |
|---|---|
| faq | 338 |
| site | 116 |
| models | 109 |
| pages | 68 |
| guides | 55 |
| offers | 7 |
| Measure | Value |
|---|---|
| Documents evaluated for admission | 122 |
| Admitted | 116 |
| Refused | 6 |
| Average unique words per admitted document | 1093.2 |
| Repeated blocks lifted into a single document | 4 |
| Near-duplicate ratio | 0.025 |
| Model summaries built from inventory records | 109 |
| Dealer knowledge documents | 3 |
| Average words per model summary | 42.4 |
| Reason | Documents |
|---|---|
| Navigation or utility page | 3 |
| near duplicate of new-inventory-chevrolet-htm.md jaccard | 1 |
| near duplicate of new-inventory-chevrolet-suv-htm.md jaccard | 1 |
| near duplicate of research-gmc-sierra-1500-trim-htm.md jaccard | 1 |
These questions have no source content, so no document claims to answer them: Delivery and out-of-area purchase.
All 979 vehicles are in the corpus as one Markdown record per VIN, addressed by the pattern https://markquartmotors.ai/v/{VIN}.md (and https://markquartmotors.ai/v/{VIN}.json). A few samples:
rag_search(query, limit?) over the MCP endpointhttps://markquartmotors.ai/v/{VIN}.mdcurl -s -X POST https://markquartmotors.ai/api/ucp/mcp \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"rag_search","arguments":{}}}'