Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #4280] [FEAT]: Enhance Chat Embed History View with Markdown Rendering and Advanced Filtering #2723

New Issue
Closed
opened 2026-02-22 18:30:57 -05:00 by yindo · 0 comments
yindo commented 2026-02-22 18:30:57 -05:00
Owner
Copy Link
Copy Source

Originally created by @MateKristof on GitHub (Aug 13, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4280

What would you like to see?

I propose a series of enhancements to the "Chat Embed History" page to improve its functionality, readability, and overall user experience. The current implementation has several limitations that make it difficult to effectively review and analyze chat logs.

Here are the key features and improvements I'd like to see:

  1. Markdown Rendering in Response Column:

    • Current Behavior: The "RESPONSE" column displays raw text from the LLM, which means any markdown formatting (like lists, code blocks, or bold text) is not rendered correctly.
    • Proposed Feature: The response text should be parsed and rendered as markdown. This would significantly improve the readability of formatted responses.

  2. Toggle for LLM "Thinking" Steps:

    • Current Behavior: The LLM's internal reasoning, often enclosed in <think> tags, is either hidden or displayed as raw text.
    • Proposed Feature: A toggle switch should be added to allow users to show or hide the content within these <think> tags. This would provide a powerful tool for developers to debug the model's thought process without cluttering the default view.

  3. Advanced Session ID Filtering and Visualization:

    • Current Behavior: It is difficult to distinguish between different user sessions, and there is no way to filter the history by a specific session ID.

    • Proposed Feature:

      • Assign a unique color to each session_id to make it easy to visually track conversations.
      • Add a dropdown menu to filter the entire chat history by a selected session_id. This filter should apply across all pages of the chat log, not just the currently visible one.

  4. Enlarged Response Modal:

    • Current Behavior: The modal window for viewing the full response text is quite small, requiring excessive scrolling for longer messages.
    • Proposed Feature: The height of the response modal should be significantly increased to provide a better reading experience for detailed responses.

Why it would be useful

These enhancements would be highly beneficial for anyone who uses the chat embed feature:

  • Improved Readability: Properly rendered markdown makes chat logs much easier to read and understand.
  • Enhanced Debugging: The "thinking" toggle offers invaluable insight into the LLM's reasoning process, which is essential for development and troubleshooting.
  • Efficient Log Analysis: The ability to filter by and visually distinguish session IDs makes it much faster to analyze user interactions and track specific conversations.
  • Better User Experience: A larger, more readable modal for viewing responses improves the overall usability of the chat history page.
Originally created by @MateKristof on GitHub (Aug 13, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4280 ### __What would you like to see?__ I propose a series of enhancements to the "Chat Embed History" page to improve its functionality, readability, and overall user experience. The current implementation has several limitations that make it difficult to effectively review and analyze chat logs. Here are the key features and improvements I'd like to see: 1. __Markdown Rendering in Response Column:__ - __Current Behavior:__ The "RESPONSE" column displays raw text from the LLM, which means any markdown formatting (like lists, code blocks, or bold text) is not rendered correctly. - __Proposed Feature:__ The response text should be parsed and rendered as markdown. This would significantly improve the readability of formatted responses. 2. __Toggle for LLM "Thinking" Steps:__ - __Current Behavior:__ The LLM's internal reasoning, often enclosed in `<think>` tags, is either hidden or displayed as raw text. - __Proposed Feature:__ A toggle switch should be added to allow users to show or hide the content within these `<think>` tags. This would provide a powerful tool for developers to debug the model's thought process without cluttering the default view. 3. __Advanced Session ID Filtering and Visualization:__ - __Current Behavior:__ It is difficult to distinguish between different user sessions, and there is no way to filter the history by a specific session ID. - __Proposed Feature:__ - Assign a unique color to each `session_id` to make it easy to visually track conversations. - Add a dropdown menu to filter the entire chat history by a selected `session_id`. This filter should apply across all pages of the chat log, not just the currently visible one. 4. __Enlarged Response Modal:__ - __Current Behavior:__ The modal window for viewing the full response text is quite small, requiring excessive scrolling for longer messages. - __Proposed Feature:__ The height of the response modal should be significantly increased to provide a better reading experience for detailed responses. ### __Why it would be useful__ These enhancements would be highly beneficial for anyone who uses the chat embed feature: - __Improved Readability:__ Properly rendered markdown makes chat logs much easier to read and understand. - __Enhanced Debugging:__ The "thinking" toggle offers invaluable insight into the LLM's reasoning process, which is essential for development and troubleshooting. - __Efficient Log Analysis:__ The ability to filter by and visually distinguish session IDs makes it much faster to analyze user interactions and track specific conversations. - __Better User Experience:__ A larger, more readable modal for viewing responses improves the overall usability of the chat history page.
yindo added the enhancementfeature request labels 2026-02-22 18:30:57 -05:00
yindo closed this issue 2026-02-22 18:30:57 -05:00
yindo changed title from [FEAT]: Enhance Chat Embed History View with Markdown Rendering and Advanced Filtering to [GH-ISSUE #4280] [FEAT]: Enhance Chat Embed History View with Markdown Rendering and Advanced Filtering 2026-06-05 14:48:11 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label enhancement feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#2723
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?