Austin/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2024-11-16 03:32:23 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Fix some RAG bugs (#2570)

Browse Source 
Co-authored-by: jyong <jyong@dify.ai>
This commit is contained in:
Jyong 2024-02-27 11:39:05 +08:00 committed by GitHub
parent 562ca45e07
commit 5b953c1ef2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
10 changed files with 33 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
api/controllers/console/datasets/data_source.py
View File

@ -178,7 +178,8 @@ class DataSourceNotionApi(Resource):
notion_workspace_id=workspace_id,
notion_obj_id=page_id,
notion_page_type=page_type,
notion_access_token=data_source_binding.access_token
notion_access_token=data_source_binding.access_token,
tenant_id=current_user.current_tenant_id
)
text_docs = extractor.extract()
@ -208,7 +209,8 @@ class DataSourceNotionApi(Resource):
notion_info={
"notion_workspace_id": workspace_id,
"notion_obj_id": page['page_id'],
"notion_page_type": page['type']
"notion_page_type": page['type'],
"tenant_id": current_user.current_tenant_id
},
document_model=args['doc_form']
)

3
api/controllers/console/datasets/datasets.py
View File

@ -298,7 +298,8 @@ class DatasetIndexingEstimateApi(Resource):
notion_info={
"notion_workspace_id": workspace_id,
"notion_obj_id": page['page_id'],
"notion_page_type": page['type']
"notion_page_type": page['type'],
"tenant_id": current_user.current_tenant_id
},
document_model=args['doc_form']
)

3
api/controllers/console/datasets/datasets_document.py
View File

@ -455,7 +455,8 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
notion_info={
"notion_workspace_id": data_source_info['notion_workspace_id'],
"notion_obj_id": data_source_info['notion_page_id'],
"notion_page_type": data_source_info['type']
"notion_page_type": data_source_info['type'],
"tenant_id": current_user.current_tenant_id
},
document_model=document.doc_form
)

3
api/core/indexing_runner.py
View File

@ -366,7 +366,8 @@ class IndexingRunner:
"notion_workspace_id": data_source_info['notion_workspace_id'],
"notion_obj_id": data_source_info['notion_page_id'],
"notion_page_type": data_source_info['type'],
"document": dataset_document
"document": dataset_document,
"tenant_id": dataset_document.tenant_id
},
document_model=dataset_document.doc_form
)

3
api/core/rag/datasource/retrieval_service.py
View File

@ -39,7 +39,8 @@ class RetrievalService:
'flask_app': current_app._get_current_object(),
'dataset_id': dataset_id,
'query': query,
'top_k': top_k
'top_k': top_k,
'all_documents': all_documents
})
threads.append(keyword_thread)
keyword_thread.start()

1
api/core/rag/extractor/entity/extract_setting.py
View File

@ -12,6 +12,7 @@ class NotionInfo(BaseModel):
notion_obj_id: str
notion_page_type: str
document: Document = None
tenant_id: str
class Config:
arbitrary_types_allowed = True

3
api/core/rag/extractor/extract_processor.py
View File

@ -132,7 +132,8 @@ class ExtractProcessor:
notion_workspace_id=extract_setting.notion_info.notion_workspace_id,
notion_obj_id=extract_setting.notion_info.notion_obj_id,
notion_page_type=extract_setting.notion_info.notion_page_type,
document_model=extract_setting.notion_info.document
document_model=extract_setting.notion_info.document,
tenant_id=extract_setting.notion_info.tenant_id,
)
return extractor.extract()
else:

63
api/core/rag/extractor/html_extractor.py
View File

@ -1,13 +1,14 @@
"""Abstract interface for document loader implementations."""
from typing import Optional
from bs4 import BeautifulSoup
from core.rag.extractor.extractor_base import BaseExtractor
from core.rag.extractor.helpers import detect_file_encodings
from core.rag.models.document import Document
class HtmlExtractor(BaseExtractor):
"""Load html files.
"""
Load html files.
Args:
@ -15,57 +16,19 @@ class HtmlExtractor(BaseExtractor):
"""
def __init__(
self,
file_path: str,
encoding: Optional[str] = None,
autodetect_encoding: bool = False,
source_column: Optional[str] = None,
csv_args: Optional[dict] = None,
self,
file_path: str
):
"""Initialize with file path."""
self._file_path = file_path
self._encoding = encoding
self._autodetect_encoding = autodetect_encoding
self.source_column = source_column
self.csv_args = csv_args or {}
def extract(self) -> list[Document]:
"""Load data into document objects."""
try:
with open(self._file_path, newline="", encoding=self._encoding) as csvfile:
docs = self._read_from_file(csvfile)
except UnicodeDecodeError as e:
if self._autodetect_encoding:
detected_encodings = detect_file_encodings(self._file_path)
for encoding in detected_encodings:
try:
with open(self._file_path, newline="", encoding=encoding.encoding) as csvfile:
docs = self._read_from_file(csvfile)
break
except UnicodeDecodeError:
continue
else:
raise RuntimeError(f"Error loading {self._file_path}") from e
return [Document(page_content=self._load_as_text())]
return docs
def _load_as_text(self) -> str:
with open(self._file_path, "rb") as fp:
soup = BeautifulSoup(fp, 'html.parser')
text = soup.get_text()
text = text.strip() if text else ''
def _read_from_file(self, csvfile) -> list[Document]:
docs = []
csv_reader = csv.DictReader(csvfile, **self.csv_args) # type: ignore
for i, row in enumerate(csv_reader):
content = "\n".join(f"{k.strip()}: {v.strip()}" for k, v in row.items())
try:
source = (
row[self.source_column]
if self.source_column is not None
else ''
)
except KeyError:
raise ValueError(
f"Source column '{self.source_column}' not found in CSV file."
)
metadata = {"source": source, "row": i}
doc = Document(page_content=content, metadata=metadata)
docs.append(doc)
return docs
return text

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

@ -30,8 +30,10 @@ class NotionExtractor(BaseExtractor):
notion_workspace_id: str,
notion_obj_id: str,
notion_page_type: str,
tenant_id: str,
document_model: Optional[DocumentModel] = None,
notion_access_token: Optional[str] = None
notion_access_token: Optional[str] = None,
):
self._notion_access_token = None
self._document_model = document_model

3
api/tasks/document_indexing_sync_task.py
View File

@ -58,7 +58,8 @@ def document_indexing_sync_task(dataset_id: str, document_id: str):
notion_workspace_id=workspace_id,
notion_obj_id=page_id,
notion_page_type=page_type,
notion_access_token=data_source_binding.access_token
notion_access_token=data_source_binding.access_token,
tenant_id=document.tenant_id
)
last_edited_time = loader.get_notion_last_edited_time()