[PR #1059] [MERGED] Enable customization of chunk length and overlap #3569

Closed
opened 2026-02-22 18:34:03 -05:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/Mintplex-Labs/anything-llm/pull/1059
Author: @timothycarambat
Created: 4/6/2024
Status: Merged
Merged: 4/6/2024
Merged by: @timothycarambat

Base: masterHead: 490-text-chunking-config-v1


📝 Commits (2)

  • 3bec1c3 Enable customization of chunk length and overlap
  • fa45881 fix onboarding link

📊 Changes

19 files changed (+455 additions, -47 deletions)

View changed files

📝 frontend/src/App.jsx (+9 -0)
📝 frontend/src/components/LLMSelection/LMStudioOptions/index.jsx (+1 -1)
📝 frontend/src/components/LLMSelection/LocalAiOptions/index.jsx (+1 -1)
📝 frontend/src/components/SettingsSidebar/index.jsx (+16 -2)
frontend/src/pages/GeneralSettings/EmbeddingTextSplitterPreference/index.jsx (+180 -0)
📝 frontend/src/utils/paths.js (+4 -0)
📝 server/endpoints/admin.js (+15 -1)
📝 server/models/systemSettings.js (+42 -0)
📝 server/utils/EmbeddingEngines/azureOpenAi/index.js (+3 -1)
📝 server/utils/EmbeddingEngines/openAi/index.js (+3 -1)
server/utils/TextSplitter/index.js (+84 -0)
📝 server/utils/vectorDbProviders/astra/index.js (+12 -5)
📝 server/utils/vectorDbProviders/chroma/index.js (+12 -5)
📝 server/utils/vectorDbProviders/lance/index.js (+13 -5)
📝 server/utils/vectorDbProviders/milvus/index.js (+12 -5)
📝 server/utils/vectorDbProviders/pinecone/index.js (+12 -5)
📝 server/utils/vectorDbProviders/qdrant/index.js (+12 -5)
📝 server/utils/vectorDbProviders/weaviate/index.js (+12 -5)
📝 server/utils/vectorDbProviders/zilliz/index.js (+12 -5)

📄 Description

Pull Request Type

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

Relevant Issues

resolves #490

What is in this change?

Enable the modification of the Chunk length and overlap as performance can change depending on documents and use-case.

This is the set up for more configurations in the future. This is the first iterations of the process.

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
  • 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/1059 **Author:** [@timothycarambat](https://github.com/timothycarambat) **Created:** 4/6/2024 **Status:** ✅ Merged **Merged:** 4/6/2024 **Merged by:** [@timothycarambat](https://github.com/timothycarambat) **Base:** `master` ← **Head:** `490-text-chunking-config-v1` --- ### 📝 Commits (2) - [`3bec1c3`](https://github.com/Mintplex-Labs/anything-llm/commit/3bec1c3bb6757a596c725c5d5deb2a149dd9e96e) Enable customization of chunk length and overlap - [`fa45881`](https://github.com/Mintplex-Labs/anything-llm/commit/fa458818bca74a568365bee6a7e88db7e2c9b55e) fix onboarding link ### 📊 Changes **19 files changed** (+455 additions, -47 deletions) <details> <summary>View changed files</summary> 📝 `frontend/src/App.jsx` (+9 -0) 📝 `frontend/src/components/LLMSelection/LMStudioOptions/index.jsx` (+1 -1) 📝 `frontend/src/components/LLMSelection/LocalAiOptions/index.jsx` (+1 -1) 📝 `frontend/src/components/SettingsSidebar/index.jsx` (+16 -2) ➕ `frontend/src/pages/GeneralSettings/EmbeddingTextSplitterPreference/index.jsx` (+180 -0) 📝 `frontend/src/utils/paths.js` (+4 -0) 📝 `server/endpoints/admin.js` (+15 -1) 📝 `server/models/systemSettings.js` (+42 -0) 📝 `server/utils/EmbeddingEngines/azureOpenAi/index.js` (+3 -1) 📝 `server/utils/EmbeddingEngines/openAi/index.js` (+3 -1) ➕ `server/utils/TextSplitter/index.js` (+84 -0) 📝 `server/utils/vectorDbProviders/astra/index.js` (+12 -5) 📝 `server/utils/vectorDbProviders/chroma/index.js` (+12 -5) 📝 `server/utils/vectorDbProviders/lance/index.js` (+13 -5) 📝 `server/utils/vectorDbProviders/milvus/index.js` (+12 -5) 📝 `server/utils/vectorDbProviders/pinecone/index.js` (+12 -5) 📝 `server/utils/vectorDbProviders/qdrant/index.js` (+12 -5) 📝 `server/utils/vectorDbProviders/weaviate/index.js` (+12 -5) 📝 `server/utils/vectorDbProviders/zilliz/index.js` (+12 -5) </details> ### 📄 Description ### Pull Request Type <!-- For change type, change [ ] to [x]. --> - [x] ✨ feat - [ ] 🐛 fix - [ ] ♻️ refactor - [ ] 💄 style - [x] 🔨 chore - [ ] 📝 docs ### Relevant Issues <!-- Use "resolves #xxx" to auto resolve on merge. Otherwise, please use "connect #xxx" --> resolves #490 ### What is in this change? Enable the modification of the Chunk length and overlap as performance can change depending on documents and use-case. This is the set up for more configurations in the future. This is the first iterations of the process. ### 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 - [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 18:34:03 -05:00
yindo closed this issue 2026-02-22 18:34:03 -05:00
yindo changed title from [PR #1059] Enable customization of chunk length and overlap to [PR #1059] [MERGED] Enable customization of chunk length and overlap 2026-06-05 15:14:05 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#3569