4
[Feature Request] Parse minimal markdown syntax in LLM chat responses
Source: paperless-ngx/paperless-ngx#12762 · opened by @pReya
Description
Typically, many LLMs will answer with Markdown syntax. Currently, this is just displayed as plaintext in the Paperless chat. It would be nice if markdown would actually be parsed into HTML in the LLM chat responses. At least a minimal subset (headings, bold, italic, lists, links, quotes, inline code) would be super helpful for the LLM responses to be better looking and help with information structure and highlighting.
Other
_No response_
Typically, many LLMs will answer with Markdown syntax. Currently, this is just displayed as plaintext in the Paperless chat. It would be nice if markdown would actually be parsed into HTML in the LLM chat responses. At least a minimal subset (headings, bold, italic, lists, links, quotes, inline code) would be super helpful for the LLM responses to be better looking and help with information structure and highlighting.
Other
_No response_
No pledges yet. Be the first to back this.
Comments
Similar requests
[Feature Request] Different keys for LLM vs. LLM embeddings
6 votes · 0 comments
[Feature Request] AI chat: size the synthesis prompts by context window, not embedding chunk size
3 votes · 0 comments
[Feature Request] Add detailed debug logging for RAG/LLM requests
2 votes · 0 comments
Native Docling Integration for PDF-to-Markdown/Text conversion (Consumer & Full-Text Indexing)
3 votes · 0 comments
[Feature Request] Process markdown files like text files
2 votes · 0 comments
No comments yet.