pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor retieval_test, add SQl retrieval methods (#61)

Browse Source
This commit is contained in:
KevinHuSh
2024-02-08 17:01:01 +08:00
committed by GitHub
parent 0a903c7714
commit 5e0a689c43
16 changed files with 238 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
api/apps/document_app.py
View File

@ -13,9 +13,10 @@
# See the License for the specific language governing permissions and
# limitations under the License
#
#
import base64
import pathlib
import re
import flask
from elasticsearch_dsl import Q
@ -27,7 +28,7 @@ from api.db.services import duplicate_name
from api.db.services.knowledgebase_service import KnowledgebaseService
from api.utils.api_utils import server_error_response, get_data_error_result, validate_request
from api.utils import get_uuid
from api.db import FileType, TaskStatus
from api.db import FileType, TaskStatus, ParserType
from api.db.services.document_service import DocumentService
from api.settings import RetCode
from api.utils.api_utils import get_json_result
@ -66,7 +67,7 @@ def upload():
location += "_"
blob = request.files['file'].read()
MINIO.put(kb_id, location, blob)
doc = DocumentService.insert({
doc = {
"id": get_uuid(),
"kb_id": kb.id,
"parser_id": kb.parser_id,
@ -77,7 +78,12 @@ def upload():
"location": location,
"size": len(blob),
"thumbnail": thumbnail(filename, blob)
})
}
if doc["type"] == FileType.VISUAL:
doc["parser_id"] = ParserType.PICTURE.value
if re.search(r"\.(ppt|pptx|pages)$", filename):
doc["parser_id"] = ParserType.PRESENTATION.value
doc = DocumentService.insert(doc)
return get_json_result(data=doc.to_json())
except Exception as e:
return server_error_response(e)
@ -283,6 +289,9 @@ def change_parser():
if doc.parser_id.lower() == req["parser_id"].lower():
return get_json_result(data=True)
if doc.type == FileType.VISUAL or re.search(r"\.(ppt|pptx|pages)$", doc.name):
return get_data_error_result(retmsg="Not supported yet!")
e = DocumentService.update_by_id(doc.id, {"parser_id": req["parser_id"], "progress":0, "progress_msg": ""})
if not e:
return get_data_error_result(retmsg="Document not found!")