adityamparikh commented on PR #88:
URL: https://github.com/apache/solr-mcp/pull/88#issuecomment-4681615450

   Closing in favor of the server-side Markdown approach discussed in #69.
   
   Rather than indexing a flat extracted-text blob, we'll add an 
`index-markdown-documents` tool (CommonMark-based) that maps structure — 
frontmatter, headings, title — onto Solr fields. Markdown subsumes the 
plain-text path this PR added (plain text is just Markdown with no structure), 
and for arbitrary formats the client/LLM can convert extracted text to Markdown 
before indexing. See #69 for the agreed direction and design notes.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to