mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-12 06:35:44 +08:00
2717ee283f
### 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>
105 lines
2.4 KiB
TypeScript
105 lines
2.4 KiB
TypeScript
/**
|
|
* Utility functions for extracting parser and raptor config extensions.
|
|
* These functions extract known fields from parser/raptor config objects
|
|
* and merge unknown fields into the `ext` field for flexible configuration.
|
|
*/
|
|
|
|
/**
|
|
* Extracts Raptor configuration with extra fields merged into ext.
|
|
* @param raptorConfig - The raptor configuration object
|
|
* @returns Processed raptor config with extra fields in ext
|
|
*/
|
|
export const extractRaptorConfigExt = (
|
|
raptorConfig: Record<string, any> | undefined,
|
|
) => {
|
|
if (!raptorConfig) return raptorConfig;
|
|
const {
|
|
use_raptor,
|
|
prompt,
|
|
max_token,
|
|
threshold,
|
|
max_cluster,
|
|
random_seed,
|
|
scope,
|
|
clustering_method,
|
|
tree_builder,
|
|
auto_disable_for_structured_data,
|
|
ext,
|
|
...raptorExt
|
|
} = raptorConfig;
|
|
const extClusteringMethod = ext?.clustering_method;
|
|
const normalizedClusteringMethod =
|
|
clustering_method ?? extClusteringMethod ?? 'gmm';
|
|
const normalizedTreeBuilder = tree_builder ?? ext?.tree_builder ?? 'raptor';
|
|
|
|
return {
|
|
use_raptor,
|
|
prompt,
|
|
max_token,
|
|
threshold,
|
|
max_cluster,
|
|
random_seed,
|
|
scope,
|
|
auto_disable_for_structured_data,
|
|
ext: {
|
|
...ext,
|
|
...raptorExt,
|
|
clustering_method: normalizedClusteringMethod,
|
|
tree_builder: normalizedTreeBuilder,
|
|
},
|
|
};
|
|
};
|
|
|
|
/**
|
|
* Extracts Parser configuration with extra fields merged into ext.
|
|
* @param parserConfig - The parser configuration object
|
|
* @returns Processed parser config with extra fields in ext
|
|
*/
|
|
export const extractParserConfigExt = (
|
|
parserConfig: Record<string, any> | undefined,
|
|
) => {
|
|
if (!parserConfig) return parserConfig;
|
|
const {
|
|
auto_keywords,
|
|
auto_questions,
|
|
chunk_token_num,
|
|
delimiter,
|
|
graphrag,
|
|
html4excel,
|
|
layout_recognize,
|
|
raptor,
|
|
tag_kb_ids,
|
|
topn_tags,
|
|
filename_embd_weight,
|
|
task_page_size,
|
|
pages,
|
|
children_delimiter,
|
|
use_parent_child,
|
|
enable_children,
|
|
ext,
|
|
...parserExt
|
|
} = parserConfig;
|
|
return {
|
|
auto_keywords,
|
|
auto_questions,
|
|
chunk_token_num,
|
|
delimiter,
|
|
graphrag,
|
|
html4excel,
|
|
layout_recognize,
|
|
raptor: extractRaptorConfigExt(raptor),
|
|
tag_kb_ids,
|
|
topn_tags,
|
|
filename_embd_weight,
|
|
task_page_size,
|
|
pages,
|
|
parent_child: enable_children
|
|
? {
|
|
children_delimiter,
|
|
use_parent_child: use_parent_child ?? enable_children,
|
|
}
|
|
: undefined,
|
|
ext: { ...ext, ...parserExt },
|
|
};
|
|
};
|