gmakstutis/ragflow
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Continue

Browse source
This commit is contained in:
Kevin Hu 2025-11-18 12:53:03 +08:00
parent d62a3dcf77
commit cec8f30205
1 changed files with 10 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
api/apps/sdk/doc.py
View file

@ -35,7 +35,8 @@ from api.db.services.llm_service import LLMBundle
from api.db.services.tenant_llm_service import TenantLLMService from api.db.services.tenant_llm_service import TenantLLMService
from api.db.services.task_service import TaskService, queue_tasks from api.db.services.task_service import TaskService, queue_tasks
from api.db.services.dialog_service import meta_filter, convert_conditions from api.db.services.dialog_service import meta_filter, convert_conditions
from api.utils.api_utils import check_duplicate_ids, construct_json_result, get_error_data_result, get_parser_config, get_result, server_error_response, token_required from api.utils.api_utils import check_duplicate_ids, construct_json_result, get_error_data_result, get_parser_config, get_result, server_error_response, token_required, \
request_json
from rag.app.qa import beAdoc, rmPrefix from rag.app.qa import beAdoc, rmPrefix
from rag.app.tag import label_question from rag.app.tag import label_question
from rag.nlp import rag_tokenizer, search from rag.nlp import rag_tokenizer, search
@ -230,7 +231,7 @@ async def update_doc(tenant_id, dataset_id, document_id):
schema: schema:
type: object type: object
""" """
req = await request.json req = await request_json()
if not KnowledgebaseService.query(id=dataset_id, tenant_id=tenant_id): if not KnowledgebaseService.query(id=dataset_id, tenant_id=tenant_id):
return get_error_data_result(message="You don't own the dataset.") return get_error_data_result(message="You don't own the dataset.")
e, kb = KnowledgebaseService.get_by_id(dataset_id) e, kb = KnowledgebaseService.get_by_id(dataset_id)
@ -630,7 +631,7 @@ async def delete(tenant_id, dataset_id):
""" """
if not KnowledgebaseService.accessible(kb_id=dataset_id, user_id=tenant_id): if not KnowledgebaseService.accessible(kb_id=dataset_id, user_id=tenant_id):
return get_error_data_result(message=f"You don't own the dataset {dataset_id}. ") return get_error_data_result(message=f"You don't own the dataset {dataset_id}. ")
req = await request.json req = await request_json()
if not req: if not req:
doc_ids = None doc_ids = None
else: else:
@ -740,7 +741,7 @@ async def parse(tenant_id, dataset_id):
""" """
if not KnowledgebaseService.accessible(kb_id=dataset_id, user_id=tenant_id): if not KnowledgebaseService.accessible(kb_id=dataset_id, user_id=tenant_id):
return get_error_data_result(message=f"You don't own the dataset {dataset_id}.") return get_error_data_result(message=f"You don't own the dataset {dataset_id}.")
req = await request.json req = await request_json()
if not req.get("document_ids"): if not req.get("document_ids"):
return get_error_data_result("`document_ids` is required") return get_error_data_result("`document_ids` is required")
doc_list = req.get("document_ids") doc_list = req.get("document_ids")
@ -823,7 +824,7 @@ async def stop_parsing(tenant_id, dataset_id):
""" """
if not KnowledgebaseService.accessible(kb_id=dataset_id, user_id=tenant_id): if not KnowledgebaseService.accessible(kb_id=dataset_id, user_id=tenant_id):
return get_error_data_result(message=f"You don't own the dataset {dataset_id}.") return get_error_data_result(message=f"You don't own the dataset {dataset_id}.")
req = await request.json req = await request_json()
if not req.get("document_ids"): if not req.get("document_ids"):
return get_error_data_result("`document_ids` is required") return get_error_data_result("`document_ids` is required")
@ -1095,7 +1096,7 @@ async def add_chunk(tenant_id, dataset_id, document_id):
if not doc: if not doc:
return get_error_data_result(message=f"You don't own the document {document_id}.") return get_error_data_result(message=f"You don't own the document {document_id}.")
doc = doc[0] doc = doc[0]
req = await request.json req = await request_json()
if not str(req.get("content", "")).strip(): if not str(req.get("content", "")).strip():
return get_error_data_result(message="`content` is required") return get_error_data_result(message="`content` is required")
if "important_keywords" in req: if "important_keywords" in req:
@ -1201,7 +1202,7 @@ async def rm_chunk(tenant_id, dataset_id, document_id):
docs = DocumentService.get_by_ids([document_id]) docs = DocumentService.get_by_ids([document_id])
if not docs: if not docs:
raise LookupError(f"Can't find the document with ID {document_id}!") raise LookupError(f"Can't find the document with ID {document_id}!")
req = await request.json req = await request_json()
condition = {"doc_id": document_id} condition = {"doc_id": document_id}
if "chunk_ids" in req: if "chunk_ids" in req:
unique_chunk_ids, duplicate_messages = check_duplicate_ids(req["chunk_ids"], "chunk") unique_chunk_ids, duplicate_messages = check_duplicate_ids(req["chunk_ids"], "chunk")
@ -1287,7 +1288,7 @@ async def update_chunk(tenant_id, dataset_id, document_id, chunk_id):
if not doc: if not doc:
return get_error_data_result(message=f"You don't own the document {document_id}.") return get_error_data_result(message=f"You don't own the document {document_id}.")
doc = doc[0] doc = doc[0]
req = await request.json req = await request_json()
if "content" in req: if "content" in req:
content = req["content"] content = req["content"]
else: else:
@ -1410,7 +1411,7 @@ async def retrieval_test(tenant_id):
format: float format: float
description: Similarity score. description: Similarity score.
""" """
req = await request.json req = await request_json()
if not req.get("dataset_ids"): if not req.get("dataset_ids"):
return get_error_data_result("`dataset_ids` is required.") return get_error_data_result("`dataset_ids` is required.")
kb_ids = req["dataset_ids"] kb_ids = req["dataset_ids"]