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

[PR #1122] [MERGED] Update all vector dbs to filter duplicate source documents that may be pinned #3591

New Issue
Closed
opened 2026-02-22 18:34:06 -05:00 by yindo · 0 comments
yindo commented 2026-02-22 18:34:06 -05:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/Mintplex-Labs/anything-llm/pull/1122
Author: @timothycarambat
Created: 4/17/2024
Status: ✅ Merged
Merged: 4/17/2024
Merged by: @timothycarambat

Base: master ← Head: dedupe-pinned-docs

📝 Commits (2)

  • b4b19d7 Update all vector dbs to filter duplicate parents
  • a555589 cleanup

📊 Changes

11 files changed (+131 additions, -21 deletions)

View changed files

📝 server/utils/chats/embed.js (+4 -1)
📝 server/utils/chats/index.js (+14 -0)
📝 server/utils/chats/stream.js (+4 -0)
📝 server/utils/vectorDbProviders/astra/index.js (+12 -2)
📝 server/utils/vectorDbProviders/chroma/index.js (+15 -2)
📝 server/utils/vectorDbProviders/lance/index.js (+13 -2)
📝 server/utils/vectorDbProviders/milvus/index.js (+13 -2)
📝 server/utils/vectorDbProviders/pinecone/index.js (+13 -2)
📝 server/utils/vectorDbProviders/qdrant/index.js (+15 -3)
📝 server/utils/vectorDbProviders/weaviate/index.js (+16 -5)
📝 server/utils/vectorDbProviders/zilliz/index.js (+12 -2)

📄 Description

Pull Request Type

  • ✨ feat
  • 🐛 fix
  • ♻️ refactor
  • 💄 style
  • 🔨 chore
  • 📝 docs

Relevant Issues

resolves #xxx

What is in this change?

Improvements with document pinning where we do not include context snippets from any pinned documents to prevent unneeded context injection as well as data duplication. This does not auto-fill the query snippet count with new snippets if they were omitted.

Additional Information

Developer Validations

  • I ran yarn lint from the root of the repo & committed changes
  • Relevant documentation has been updated
  • I have tested my code functionality (tested every db)
  • Docker build succeeds locally

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/Mintplex-Labs/anything-llm/pull/1122 **Author:** [@timothycarambat](https://github.com/timothycarambat) **Created:** 4/17/2024 **Status:** ✅ Merged **Merged:** 4/17/2024 **Merged by:** [@timothycarambat](https://github.com/timothycarambat) **Base:** `master` ← **Head:** `dedupe-pinned-docs` --- ### 📝 Commits (2) - [`b4b19d7`](https://github.com/Mintplex-Labs/anything-llm/commit/b4b19d73691cd962ef897fc69e960630c24b4831) Update all vector dbs to filter duplicate parents - [`a555589`](https://github.com/Mintplex-Labs/anything-llm/commit/a555589c5a7a3920d8ff91d0f007309d31e7a3e1) cleanup ### 📊 Changes **11 files changed** (+131 additions, -21 deletions) <details> <summary>View changed files</summary> 📝 `server/utils/chats/embed.js` (+4 -1) 📝 `server/utils/chats/index.js` (+14 -0) 📝 `server/utils/chats/stream.js` (+4 -0) 📝 `server/utils/vectorDbProviders/astra/index.js` (+12 -2) 📝 `server/utils/vectorDbProviders/chroma/index.js` (+15 -2) 📝 `server/utils/vectorDbProviders/lance/index.js` (+13 -2) 📝 `server/utils/vectorDbProviders/milvus/index.js` (+13 -2) 📝 `server/utils/vectorDbProviders/pinecone/index.js` (+13 -2) 📝 `server/utils/vectorDbProviders/qdrant/index.js` (+15 -3) 📝 `server/utils/vectorDbProviders/weaviate/index.js` (+16 -5) 📝 `server/utils/vectorDbProviders/zilliz/index.js` (+12 -2) </details> ### 📄 Description ### Pull Request Type <!-- For change type, change [ ] to [x]. --> - [ ] ✨ feat - [ ] 🐛 fix - [ ] ♻️ refactor - [ ] 💄 style - [x] 🔨 chore - [ ] 📝 docs ### Relevant Issues <!-- Use "resolves #xxx" to auto resolve on merge. Otherwise, please use "connect #xxx" --> resolves #xxx ### What is in this change? Improvements with document pinning where we do not include context snippets from any pinned documents to prevent unneeded context injection as well as data duplication. This does not auto-fill the query snippet count with new snippets if they were omitted. ### Additional Information ### Developer Validations <!-- All of the applicable items should be checked. --> - [x] I ran `yarn lint` from the root of the repo & committed changes - [x] Relevant documentation has been updated - [x] I have tested my code functionality (tested every db) - [x] Docker build succeeds locally --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-22 18:34:06 -05:00
yindo closed this issue 2026-02-22 18:34:06 -05:00
yindo changed title from [PR #1122] Update all vector dbs to filter duplicate source documents that may be pinned to [PR #1122] [MERGED] Update all vector dbs to filter duplicate source documents that may be pinned 2026-06-05 15:14:13 -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 pull-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#3591
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?