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 (1,924 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 | 131 |
| models | 104 |
| site | 68 |
| departments | 30 |
| classes | 18 |
| pages | 13 |
| Measure | Value |
|---|---|
| Documents evaluated for admission | 90 |
| Admitted | 78 |
| Refused | 12 |
| Average unique words per admitted document | 525.4 |
| Repeated blocks lifted into a single document | 18 |
| Near-duplicate ratio | 0.089 |
| Reason | Documents |
|---|---|
| Near-duplicate of another document | 8 |
| Mostly repeated boilerplate | 4 |
All 314 vehicles are in the corpus as one Markdown record per VIN, addressed by the pattern https://ai.castlesubarumchenry.com/v/{VIN}.md (and https://ai.castlesubarumchenry.com/v/{VIN}.json). A few samples:
rag_search(query, limit?) over the MCP endpointhttps://ai.castlesubarumchenry.com/v/{VIN}.mdcurl -s -X POST https://ai.castlesubarumchenry.com/api/ucp/mcp \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"rag_search","arguments":{}}}'