Files
ragflow/web/src/interfaces/request/document.ts

50 lines
1.1 KiB
TypeScript
Raw Normal View History

export interface IChangeParserConfigRequestBody {
pages?: number[][];
chunk_token_num?: number;
layout_recognize?: string;
task_page_size?: number;
delimiter?: string;
auto_keywords?: number;
auto_questions?: number;
html4excel?: boolean;
toc_extraction?: boolean;
image_table_context_window?: number;
image_context_size?: number;
table_context_size?: number;
feat(raptor): add Psi tree builder with original-space ranking and safe migration (#14679) ### 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>
2026-05-11 15:42:31 -10:00
raptor?: {
use_raptor?: boolean;
prompt?: string;
max_token?: number;
threshold?: number;
max_cluster?: number;
random_seed?: number;
scope?: string;
clustering_method?: 'gmm' | 'ahc';
tree_builder?: 'raptor' | 'psi';
};
// Metadata fields
metadata?: Array<{
key?: string;
description?: string;
enum?: string[];
}>;
built_in_metadata?: Array<{
key?: string;
description?: string;
enum?: string[];
}>;
enable_metadata?: boolean;
}
export interface IChangeParserRequestBody {
parser_id: string;
feat(raptor): add Psi tree builder with original-space ranking and safe migration (#14679) ### 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>
2026-05-11 15:42:31 -10:00
pipeline_id?: string;
doc_id?: string;
parser_config: IChangeParserConfigRequestBody;
}
export interface IDocumentMetaRequestBody {
documentId: string;
meta: string; // json format string
}