Data / RAG
Retrieval
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 (920 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.
794vehicle pages (.md)
0store pages (.md)
920 KBbulk corpus
| Page | Source page |
|---|---|
| No store pages ingested. | |
All 794 vehicles are in the corpus as one Markdown record per VIN, addressed by the pattern https://ai.castlecdjrnaperville.com/v/{VIN}.md (and https://ai.castlecdjrnaperville.com/v/{VIN}.json). A few samples:
How to query this dataset
Bulk corpus
https://ai.castlecdjrnaperville.com/llms-full.txt (920 KB, ingestable)
Live tool
rag_search(query, limit?) over the MCP endpointPer vehicle
https://ai.castlecdjrnaperville.com/v/{VIN}.mdcurl -s -X POST https://ai.castlecdjrnaperville.com/api/ucp/mcp \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"rag_search","arguments":{}}}'