pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-23 15:06:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
### 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
Download Patch File Download Diff File Expand all files Collapse all files

29
test/testcases/test_http_api/test_dataset_mangement/test_create_dataset.py
View File

@ -23,7 +23,7 @@ from libs.auth import RAGFlowHttpApiAuth
from utils import encode_avatar
from utils.file_utils import create_image_file
from utils.hypothesis_utils import valid_names
from configs import DEFAULT_PARSER_CONFIG
@pytest.mark.usefixtures("clear_datasets")
class TestAuthorization:
@ -637,42 +637,21 @@ class TestDatasetCreate:
payload = {"name": "parser_config_empty", "parser_config": {}}
res = create_dataset(HttpApiAuth, payload)
assert res["code"] == 0, res
assert res["data"]["parser_config"] == {
"chunk_token_num": 512,
"delimiter": r"\n",
"html4excel": False,
"layout_recognize": "DeepDOC",
"raptor": {"use_raptor": False},
"graphrag": {"use_graphrag": False},
}, res
assert res["data"]["parser_config"] == DEFAULT_PARSER_CONFIG, res
@pytest.mark.p2
def test_parser_config_unset(self, HttpApiAuth):
payload = {"name": "parser_config_unset"}
res = create_dataset(HttpApiAuth, payload)
assert res["code"] == 0, res
assert res["data"]["parser_config"] == {
"chunk_token_num": 512,
"delimiter": r"\n",
"html4excel": False,
"layout_recognize": "DeepDOC",
"raptor": {"use_raptor": False},
"graphrag": {"use_graphrag": False},
}, res
assert res["data"]["parser_config"] == DEFAULT_PARSER_CONFIG, res
@pytest.mark.p3
def test_parser_config_none(self, HttpApiAuth):
payload = {"name": "parser_config_none", "parser_config": None}
res = create_dataset(HttpApiAuth, payload)
assert res["code"] == 0, res
assert res["data"]["parser_config"] == {
"chunk_token_num": 512,
"delimiter": "\\n",
"html4excel": False,
"layout_recognize": "DeepDOC",
"raptor": {"use_raptor": False},
"graphrag": {"use_graphrag": False},
}, res
assert res["data"]["parser_config"] == DEFAULT_PARSER_CONFIG, res
@pytest.mark.p2
@pytest.mark.parametrize(

20
test/testcases/test_http_api/test_dataset_mangement/test_update_dataset.py
View File

@ -25,7 +25,7 @@ from libs.auth import RAGFlowHttpApiAuth
from utils import encode_avatar
from utils.file_utils import create_image_file
from utils.hypothesis_utils import valid_names
from configs import DEFAULT_PARSER_CONFIG
# TODO: Missing scenario for updating embedding_model with chunk_count != 0
@ -748,14 +748,7 @@ class TestDatasetUpdate:
res = list_datasets(HttpApiAuth)
assert res["code"] == 0, res
assert res["data"][0]["parser_config"] == {
"chunk_token_num": 512,
"delimiter": r"\n",
"html4excel": False,
"layout_recognize": "DeepDOC",
"raptor": {"use_raptor": False},
"graphrag": {"use_graphrag": False},
}, res
assert res["data"][0]["parser_config"] == DEFAULT_PARSER_CONFIG, res
@pytest.mark.p3
def test_parser_config_none(self, HttpApiAuth, add_dataset_func):
@ -766,14 +759,7 @@ class TestDatasetUpdate:
res = list_datasets(HttpApiAuth, {"id": dataset_id})
assert res["code"] == 0, res
assert res["data"][0]["parser_config"] == {
"chunk_token_num": 512,
"delimiter": r"\n",
"html4excel": False,
"layout_recognize": "DeepDOC",
"raptor": {"use_raptor": False},
"graphrag": {"use_graphrag": False},
}, res
assert res["data"][0]["parser_config"] == DEFAULT_PARSER_CONFIG, res
@pytest.mark.p3
def test_parser_config_empty_with_chunk_method_change(self, HttpApiAuth, add_dataset_func):