Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-22 10:05:25 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #45] Refer Directly to Docs #28

New Issue
Closed
opened 2026-02-22 18:17:32 -05:00 by yindo · 4 comments
yindo commented 2026-02-22 18:17:32 -05:00
Owner
Copy Link
Copy Source

Originally created by @MilesP46 on GitHub (Jun 13, 2023).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/45

This is a SOLID project.

Would it be possible to leverage a specific prompt that would refer to a document(s) directly?

Say I need to pull A from Page X and pull B from Page Y, being able to directly point to where the information can be found would be helpful.

Originally created by @MilesP46 on GitHub (Jun 13, 2023). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/45 This is a SOLID project. Would it be possible to leverage a specific prompt that would refer to a document(s) directly? Say I need to pull A from Page X and pull B from Page Y, being able to directly point to where the information can be found would be helpful.
yindo added the question label 2026-02-22 18:17:32 -05:00
yindo closed this issue 2026-02-22 18:17:33 -05:00
yindo commented 2026-02-22 18:17:33 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jun 13, 2023):

Currently when you add documents to a workspace you get relevant document citations at the bottom of the message - so you know where that information comes from.

That being said, I really want to add in-app document citations so you can go exactly the to doc + text it used in context. Langchain does not help here so we would have to roll our own.

Not a big ask at all, but half of what you are asking for is already live 🎉

@timothycarambat commented on GitHub (Jun 13, 2023): Currently when you add documents to a workspace you get relevant document citations at the bottom of the message - so you know where that information comes from. That being said, I _really_ want to add in-app document citations so you can go exactly the to doc + text it used in context. Langchain does not help here so we would have to roll our own. Not a big ask at all, but half of what you are asking for is already live 🎉
yindo commented 2026-02-22 18:17:33 -05:00
Author
Owner
Copy Link
Copy Source

@MilesP46 commented on GitHub (Jun 19, 2023):

Currently when you add documents to a workspace you get relevant document citations at the bottom of the message - so you know where that information comes from.

That being said, I really want to add in-app document citations so you can go exactly the to doc + text it used in context. Langchain does not help here so we would have to roll our own.

Not a big ask at all, but half of what you are asking for is already live 🎉

I appreciate the response - however, I don't think I was clear in what I meant.

What I am talking about is the ability to provide a specific prompt and direct OpenAI to look at the contents prior to returning a response.

Example: "I need you to determine whether or not Document X that is inside of my Vector database can be used for..."

Essentially, it is directing OpenAI to target those documents specifically as it relates to the conversation at large.

Apologies for the confusion.

@MilesP46 commented on GitHub (Jun 19, 2023): > Currently when you add documents to a workspace you get relevant document citations at the bottom of the message - so you know where that information comes from. > > That being said, I _really_ want to add in-app document citations so you can go exactly the to doc + text it used in context. Langchain does not help here so we would have to roll our own. > > Not a big ask at all, but half of what you are asking for is already live 🎉 I appreciate the response - however, I don't think I was clear in what I meant. What I am talking about is the ability to provide a specific prompt and direct OpenAI to look at the contents prior to returning a response. Example: "I need you to determine whether or not Document X that is inside of my Vector database can be used for..." Essentially, it is directing OpenAI to target those documents specifically as it relates to the conversation at large. Apologies for the confusion.
yindo commented 2026-02-22 18:17:33 -05:00
Author
Owner
Copy Link
Copy Source

@MilesP46 commented on GitHub (Jul 7, 2023):

Do you have any idea as to whether you will incorporate a direct reference?

@MilesP46 commented on GitHub (Jul 7, 2023): Do you have any idea as to whether you will incorporate a direct reference?
yindo commented 2026-02-22 18:17:33 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Nov 14, 2023):

Going to mark this as closed since we will be implementing a slash command functionality to be able to refer to a document directly in a chat.

@timothycarambat commented on GitHub (Nov 14, 2023): Going to mark this as closed since we will be implementing a slash command functionality to be able to refer to a document directly in a chat.
yindo changed title from Refer Directly to Docs to [GH-ISSUE #45] Refer Directly to Docs 2026-06-05 14:33:05 -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 question
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#28
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?