admin/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Refactor: use DatasourceType.XX.value instead of hardcoded (#25015)

Browse Source 
Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
Yongtao Huang
2025-09-03 08:56:48 +08:00
committed by GitHub
parent f540d0b747
commit bc9efa7ea8
6 changed files with 21 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
api/core/indexing_runner.py
View File

@@ -19,6 +19,7 @@ from core.model_runtime.entities.model_entities import ModelType
from core.rag.cleaner.clean_processor import CleanProcessor
from core.rag.datasource.keyword.keyword_factory import Keyword
from core.rag.docstore.dataset_docstore import DatasetDocumentStore
from core.rag.extractor.entity.datasource_type import DatasourceType
from core.rag.extractor.entity.extract_setting import ExtractSetting
from core.rag.index_processor.constant.index_type import IndexType
from core.rag.index_processor.index_processor_base import BaseIndexProcessor
@@ -340,7 +341,9 @@ class IndexingRunner:
if file_detail:
extract_setting = ExtractSetting(
datasource_type="upload_file", upload_file=file_detail, document_model=dataset_document.doc_form
datasource_type=DatasourceType.FILE.value,
upload_file=file_detail,
document_model=dataset_document.doc_form,
)
text_docs = index_processor.extract(extract_setting, process_rule_mode=process_rule["mode"])
elif dataset_document.data_source_type == "notion_import":
@@ -351,7 +354,7 @@ class IndexingRunner:
):
raise ValueError("no notion import info found")
extract_setting = ExtractSetting(
datasource_type="notion_import",
datasource_type=DatasourceType.NOTION.value,
notion_info={
"notion_workspace_id": data_source_info["notion_workspace_id"],
"notion_obj_id": data_source_info["notion_page_id"],
@@ -371,7 +374,7 @@ class IndexingRunner:
):
raise ValueError("no website import info found")
extract_setting = ExtractSetting(
datasource_type="website_crawl",
datasource_type=DatasourceType.WEBSITE.value,
website_info={
"provider": data_source_info["provider"],
"job_id": data_source_info["job_id"],

4
api/core/rag/extractor/extract_processor.py
View File

@@ -45,7 +45,7 @@ class ExtractProcessor:
cls, upload_file: UploadFile, return_text: bool = False, is_automatic: bool = False
) -> Union[list[Document], str]:
extract_setting = ExtractSetting(
datasource_type="upload_file", upload_file=upload_file, document_model="text_model"
datasource_type=DatasourceType.FILE.value, upload_file=upload_file, document_model="text_model"
)
if return_text:
delimiter = "\n"
@@ -76,7 +76,7 @@ class ExtractProcessor:
# https://stackoverflow.com/questions/26541416/generate-temporary-file-names-without-creating-actual-file-in-python#comment90414256_26541521
file_path = f"{temp_dir}/{tempfile.gettempdir()}{suffix}"
Path(file_path).write_bytes(response.content)
extract_setting = ExtractSetting(datasource_type="upload_file", document_model="text_model")
extract_setting = ExtractSetting(datasource_type=DatasourceType.FILE.value, document_model="text_model")
if return_text:
delimiter = "\n"
return delimiter.join(