Fix: Create dataset performance unmatched between HTTP api and web ui (#10960)

### What problem does this PR solve?

Fix: Create dataset performance unmatched between HTTP api and web ui
#10925

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Billy Bao
2025-11-04 13:45:14 +08:00
committed by GitHub
parent 1e45137284
commit 19f71a961a
12 changed files with 201 additions and 222 deletions

View File

@ -298,8 +298,34 @@ def get_parser_config(chunk_method, parser_config):
# Define default configurations for each chunking method
key_mapping = {
"naive": {"chunk_token_num": 512, "delimiter": r"\n", "html4excel": False, "layout_recognize": "DeepDOC",
"raptor": {"use_raptor": False}, "graphrag": {"use_graphrag": False}},
"naive": {
"layout_recognize": "DeepDOC",
"chunk_token_num": 512,
"delimiter": "\n",
"auto_keywords": 0,
"auto_questions": 0,
"html4excel": False,
"topn_tags": 3,
"raptor": {
"use_raptor": True,
"prompt": "Please summarize the following paragraphs. Be careful with the numbers, do not make things up. Paragraphs as following:\n {cluster_content}\nThe above is the content you need to summarize.",
"max_token": 256,
"threshold": 0.1,
"max_cluster": 64,
"random_seed": 0,
},
"graphrag": {
"use_graphrag": True,
"entity_types": [
"organization",
"person",
"geo",
"event",
"category",
],
"method": "light",
},
},
"qa": {"raptor": {"use_raptor": False}, "graphrag": {"use_graphrag": False}},
"tag": None,
"resume": None,