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

kb

Browse source
This commit is contained in:
yongtenglei 2025-12-02 14:09:38 +08:00
parent 3c3cc95a62
commit b2fa0a861d
1 changed files with 36 additions and 24 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

60
api/apps/kb_app.py
View file

@ -17,6 +17,7 @@ import json
import logging import logging
import random import random
import re import re
import asyncio
from quart import request from quart import request
import numpy as np import numpy as np
@ -116,12 +117,22 @@ async def update():
if kb.pagerank != req.get("pagerank", 0): if kb.pagerank != req.get("pagerank", 0):
if req.get("pagerank", 0) > 0: if req.get("pagerank", 0) > 0:
settings.docStoreConn.update({"kb_id": kb.id}, {PAGERANK_FLD: req["pagerank"]}, await asyncio.to_thread(
search.index_name(kb.tenant_id), kb.id) settings.docStoreConn.update,
{"kb_id": kb.id},
{PAGERANK_FLD: req["pagerank"]},
search.index_name(kb.tenant_id),
kb.id,
)
else: else:
# Elasticsearch requires PAGERANK_FLD be non-zero! # Elasticsearch requires PAGERANK_FLD be non-zero!
settings.docStoreConn.update({"exists": PAGERANK_FLD}, {"remove": PAGERANK_FLD}, await asyncio.to_thread(
search.index_name(kb.tenant_id), kb.id) settings.docStoreConn.update,
{"exists": PAGERANK_FLD},
{"remove": PAGERANK_FLD},
search.index_name(kb.tenant_id),
kb.id,
)
e, kb = KnowledgebaseService.get_by_id(kb.id) e, kb = KnowledgebaseService.get_by_id(kb.id)
if not e: if not e:
@ -224,25 +235,28 @@ async def rm():
data=False, message='Only owner of knowledgebase authorized for this operation.', data=False, message='Only owner of knowledgebase authorized for this operation.',
code=RetCode.OPERATING_ERROR) code=RetCode.OPERATING_ERROR)
for doc in DocumentService.query(kb_id=req["kb_id"]): def _rm_sync():
if not DocumentService.remove_document(doc, kbs[0].tenant_id): for doc in DocumentService.query(kb_id=req["kb_id"]):
if not DocumentService.remove_document(doc, kbs[0].tenant_id):
return get_data_error_result(
message="Database error (Document removal)!")
f2d = File2DocumentService.get_by_document_id(doc.id)
if f2d:
FileService.filter_delete([File.source_type == FileSource.KNOWLEDGEBASE, File.id == f2d[0].file_id])
File2DocumentService.delete_by_document_id(doc.id)
FileService.filter_delete(
[File.source_type == FileSource.KNOWLEDGEBASE, File.type == "folder", File.name == kbs[0].name])
if not KnowledgebaseService.delete_by_id(req["kb_id"]):
return get_data_error_result( return get_data_error_result(
message="Database error (Document removal)!") message="Database error (Knowledgebase removal)!")
f2d = File2DocumentService.get_by_document_id(doc.id) for kb in kbs:
if f2d: settings.docStoreConn.delete({"kb_id": kb.id}, search.index_name(kb.tenant_id), kb.id)
FileService.filter_delete([File.source_type == FileSource.KNOWLEDGEBASE, File.id == f2d[0].file_id]) settings.docStoreConn.deleteIdx(search.index_name(kb.tenant_id), kb.id)
File2DocumentService.delete_by_document_id(doc.id) if hasattr(settings.STORAGE_IMPL, 'remove_bucket'):
FileService.filter_delete( settings.STORAGE_IMPL.remove_bucket(kb.id)
[File.source_type == FileSource.KNOWLEDGEBASE, File.type == "folder", File.name == kbs[0].name]) return get_json_result(data=True)
if not KnowledgebaseService.delete_by_id(req["kb_id"]):
return get_data_error_result( return await asyncio.to_thread(_rm_sync)
message="Database error (Knowledgebase removal)!")
for kb in kbs:
settings.docStoreConn.delete({"kb_id": kb.id}, search.index_name(kb.tenant_id), kb.id)
settings.docStoreConn.deleteIdx(search.index_name(kb.tenant_id), kb.id)
if hasattr(settings.STORAGE_IMPL, 'remove_bucket'):
settings.STORAGE_IMPL.remove_bucket(kb.id)
return get_json_result(data=True)
except Exception as e: except Exception as e:
return server_error_response(e) return server_error_response(e)
@ -922,5 +936,3 @@ async def check_embedding():
if summary["avg_cos_sim"] > 0.9: if summary["avg_cos_sim"] > 0.9:
return get_json_result(data={"summary": summary, "results": results}) return get_json_result(data={"summary": summary, "results": results})
return get_json_result(code=RetCode.NOT_EFFECTIVE, message="Embedding model switch failed: the average similarity between old and new vectors is below 0.9, indicating incompatible vector spaces.", data={"summary": summary, "results": results}) return get_json_result(code=RetCode.NOT_EFFECTIVE, message="Embedding model switch failed: the average similarity between old and new vectors is below 0.9, indicating incompatible vector spaces.", data={"summary": summary, "results": results})