kudzues/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-04-05 09:49:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: use EnumText for ApiToolProvider.schema_type_str and Docume… (#33983)

Browse Source
This commit is contained in:
tmimmanuel
2026-03-24 05:27:50 +01:00
committed by GitHub
parent ecd3a964c1
commit 8b634a9bee
46 changed files with 255 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
api/tasks/batch_create_segment_to_index_task.py
View File

@@ -11,6 +11,7 @@ from sqlalchemy import func
from core.db.session_factory import session_factory
from core.model_manager import ModelManager
from core.rag.index_processor.constant.index_type import IndexStructureType
from dify_graph.model_runtime.entities.model_entities import ModelType
from extensions.ext_redis import redis_client
from extensions.ext_storage import storage
@@ -109,7 +110,7 @@ def batch_create_segment_to_index_task(
df = pd.read_csv(file_path)
content = []
for _, row in df.iterrows():
if document_config["doc_form"] == "qa_model":
if document_config["doc_form"] == IndexStructureType.QA_INDEX:
data = {"content": row.iloc[0], "answer": row.iloc[1]}
else:
data = {"content": row.iloc[0]}
@@ -159,7 +160,7 @@ def batch_create_segment_to_index_task(
status="completed",
completed_at=naive_utc_now(),
)
if document_config["doc_form"] == "qa_model":
if document_config["doc_form"] == IndexStructureType.QA_INDEX:
segment_document.answer = segment["answer"]
segment_document.word_count += len(segment["answer"])
word_count_change += segment_document.word_count

3
api/tasks/document_indexing_task.py
View File

@@ -10,6 +10,7 @@ from configs import dify_config
from core.db.session_factory import session_factory
from core.entities.document_task import DocumentTask
from core.indexing_runner import DocumentIsPausedError, IndexingRunner
from core.rag.index_processor.constant.index_type import IndexStructureType
from core.rag.pipeline.queue import TenantIsolatedTaskQueue
from enums.cloud_plan import CloudPlan
from libs.datetime_utils import naive_utc_now
@@ -150,7 +151,7 @@ def _document_indexing(dataset_id: str, document_ids: Sequence[str]):
)
if (
document.indexing_status == IndexingStatus.COMPLETED
and document.doc_form != "qa_model"
and document.doc_form != IndexStructureType.QA_INDEX
and document.need_summary is True
):
try:

5
api/tasks/regenerate_summary_index_task.py
View File

@@ -9,6 +9,7 @@ from celery import shared_task
from sqlalchemy import or_, select
from core.db.session_factory import session_factory
from core.rag.index_processor.constant.index_type import IndexStructureType
from models.dataset import Dataset, DocumentSegment, DocumentSegmentSummary
from models.dataset import Document as DatasetDocument
from services.summary_index_service import SummaryIndexService
@@ -106,7 +107,7 @@ def regenerate_summary_index_task(
),
DatasetDocument.enabled == True, # Document must be enabled
DatasetDocument.archived == False, # Document must not be archived
DatasetDocument.doc_form != "qa_model", # Skip qa_model documents
DatasetDocument.doc_form != IndexStructureType.QA_INDEX, # Skip qa_model documents
)
.order_by(DocumentSegment.document_id.asc(), DocumentSegment.position.asc())
.all()
@@ -209,7 +210,7 @@ def regenerate_summary_index_task(
for dataset_document in dataset_documents:
# Skip qa_model documents
if dataset_document.doc_form == "qa_model":
if dataset_document.doc_form == IndexStructureType.QA_INDEX:
continue
try: