### What problem does this PR solve?
1. expose batch_chunk_token_size for configuration
2. retrieve chunks when build subgraph for the doc, not retreive all
docs chunks at the begining
3. get all chunks for a document, used to be hard coded 10000
4. delete not used method run_graphrag
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
Follow on: #14617
### What problem does this PR solve?
Closes#14674.
This PR improves RAPTOR configuration and tree construction while
preserving the existing RAPTOR behavior as the default.
RAPTOR currently builds summary layers with the original UMAP + GMM
clustering path. This PR keeps that default path, and adds:
- A hidden backend tree-builder option:
- `tree_builder="raptor"`: default, existing RAPTOR behavior.
- `tree_builder="psi"`: rank-aware Psi-style tree builder using original
embedding-space cosine ranking.
- A user-facing clustering method option for the default RAPTOR builder:
- `clustering_method="gmm"`: existing default.
- `clustering_method="ahc"`: agglomerative hierarchical clustering path.
- A RAPTOR UI setting for `Clustering method` and `Max cluster`.
### What changed
#### Backend
- Added `tree_builder` support for RAPTOR/Psi.
- Added `clustering_method` support for GMM/AHC.
- Kept existing RAPTOR + GMM as the default.
- Added Psi tree building from original-space cosine similarity.
- Added bucketed Psi building controls for large inputs:
- `raptor.ext.psi_exact_max_leaves`
- `raptor.ext.psi_bucket_size`
- Added method-aware RAPTOR summary metadata using existing
`extra.raptor_method`.
- Avoided adding a dedicated DB schema field for experimental method
tracking.
- Added cleanup/migration logic to avoid mixing stale RAPTOR summary
trees.
- Added defensive checks for Psi tree construction and summary failures.
#### Frontend/UI
- Added `Clustering method` in RAPTOR settings with `GMM` and `AHC`.
- Added/kept `Max cluster` in RAPTOR settings.
- Enlarged max cluster UI limit to `1024`, matching backend validation.
- Kept AHC editable even when a RAPTOR task has already finished.
- Fixed the UI save payload so `clustering_method` and `tree_builder`
are serialized through `parser_config.raptor.ext`, avoiding backend
validation errors for extra top-level RAPTOR fields.
Example saved RAPTOR config:
```json
{
"raptor": {
"max_cluster": 317,
"ext": {
"clustering_method": "ahc",
"tree_builder": "raptor"
}
}
}
Co-authored-by: CaptainTimon <CaptainTimon@users.noreply.github.com>
### What problem does this PR solve?
GraphRAG feature - Part 1 - add spacy to extract entity and relation
<img width="1621" height="1288" alt="image"
src="https://github.com/user-attachments/assets/aadeddad-94da-46c6-adad-9c3784181f61"
/>
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: UI Placeholder and Hint Optimization
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Fix:Bugs fix
- Configure memory and metadata (in Chinese)
- Add indexing modal
- Reduce metadata saving steps
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Feat: Replace antd with shadcn and delete the template node. #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: UI adjustments, replacing private components with public components
- UI adjustments for public components (input, multiselect,
SliderInputFormField)
- Replacing the private LlmSettingFieldItems component in search with
the public LlmSettingFieldItems component
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Bug Fixes#10703
- Fixed the menu order in the user center
- Added a disabled RAPTOR scope
- Fixed some style issues
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fixes: Fixed model provider issues and improved some features
- Removed the old login page
- Updated model provider icons
- Added RAPTOR modification range parameter
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Optimize code and fix ts type errors #9869
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
fix: Optimize internationalization configuration
- Update multi-language options, adding general translations for
functions like Select All and Clear
- Add internationalization support for modules like Chat, Search, and
Datasets
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Optimized Input and MultiSelect component functionality and
dataSet-chunk page styling
- Updated @js-preview/excel to version 1.7.14 #9779
- Optimized the EditTag component
- Updated the Input component to optimize numeric input processing
- Adjusted the MultiSelect component to use lodash's isEmpty method
- Optimized the CheckboxSets component to display action buttons based
on the selected state
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Optimize dataset page layout and internationalization and Fix
setting default values for multi selection drop-down boxes #3221
-Adjust the style and layout of each component on the dataset page
-Add and update multilingual translation content
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix (search): Search application list supports renaming function #3221
-Update the search application list page and add a renaming operation
entry
-Modify the search application details interface to support obtaining
detailed information
-Optimize search settings page layout and style
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Replace Avatar with RAGFlowAvatar component for knowledge base and
agent, optimize Agent template page, and modify bugs in knowledge base
#3221
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
fix dataset-page's bugs,Input component supports icon, added Radio
component, and removed antd from chunk-result-bar page [#3221
](https://github.com/infiniflow/ragflow/issues/3221)
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Fixed the issue of retrieval operator text overlapping #3221
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Fixed the issue where the dataset configuration page kept
refreshing #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Add data set configuration form #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Filter document by running status and file type. #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Save the configuration information of the knowledge base document
#3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Display the document configuration dialog with shadcn #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Support deleting knowledge graph #6747
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Put the configuration of different parsing methods into separate
components. #5467
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Modify the parsing method string to an enumeration type. #5467
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Add background color to GraphRag configuration #4980
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Display the knowledge graph on the knowledge base page #4543
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Add tag_kwd parameter to chunk configuration modal #4368
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
feat: Add EntityTypesForm #162
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
feat: change all file names to lowercase #1574
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Implements RAPTOR for better chunking #882
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Implements RAPTOR for better chunking #882
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
