Fix: Merge main branch (#10377)

### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com>
Co-authored-by: AB <aj@Ajays-MacBook-Air.local>
Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com>
Co-authored-by: He Wang <wanghechn@qq.com>
Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com>
Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box>
Co-authored-by: Stephen Hu <stephenhu@seismic.com>
Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com>
Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com>
Co-authored-by: mxc <mxc@example.com>
Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com>
Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com>
Co-authored-by: mcoder6425 <mcoder64@gmail.com>
Co-authored-by: TeslaZY <TeslaZY@outlook.com>
Co-authored-by: lemsn <lemsn@msn.com>
Co-authored-by: lemsn <lemsn@126.com>
Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com>
Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com>
Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>

api/apps/__init__.py

@@ -27,7 +27,8 @@ from itsdangerous.url_safe import URLSafeTimedSerializer as Serializer
 from api.db import StatusEnum
 from api.db.db_models import close_connection
 from api.db.services import UserService
-from api.utils import CustomJSONEncoder, commands
+from api.utils.json import CustomJSONEncoder
+from api.utils import commands
 
 from flask_mail import Mail
 from flask_session import Session

api/apps/api_app.py

@@ -39,7 +39,7 @@ from api.utils.api_utils import server_error_response, get_data_error_result, ge
 
 from api.utils.file_utils import filename_type, thumbnail
 from rag.app.tag import label_question
-from rag.prompts import keyword_extraction
+from rag.prompts.generator import keyword_extraction
 from rag.utils.storage_factory import STORAGE_IMPL
 
 from api.db.services.canvas_service import UserCanvasService

api/apps/canvas_app.py

@@ -100,7 +100,7 @@ def save():
 def get(canvas_id):
     if not UserCanvasService.accessible(canvas_id, current_user.id):
         return get_data_error_result(message="canvas not found.")
-    e, c = UserCanvasService.get_by_tenant_id(canvas_id)
+    e, c = UserCanvasService.get_by_canvas_id(canvas_id)
     return get_json_result(data=c)
 
 
@@ -243,7 +243,7 @@ def reset():
 
 @manager.route("/upload/<canvas_id>", methods=["POST"])  # noqa: F821
 def upload(canvas_id):
-    e, cvs = UserCanvasService.get_by_tenant_id(canvas_id)
+    e, cvs = UserCanvasService.get_by_canvas_id(canvas_id)
     if not e:
         return get_data_error_result(message="canvas not found.")
 
@@ -393,6 +393,22 @@ def test_db_connect():
             cursor = db.cursor()
             cursor.execute("SELECT 1")
             cursor.close()
+        elif req["db_type"] == 'IBM DB2':
+            import ibm_db
+            conn_str = (
+                f"DATABASE={req['database']};"
+                f"HOSTNAME={req['host']};"
+                f"PORT={req['port']};"
+                f"PROTOCOL=TCPIP;"
+                f"UID={req['username']};"
+                f"PWD={req['password']};"
+            )
+            logging.info(conn_str)
+            conn = ibm_db.connect(conn_str, "", "")
+            stmt = ibm_db.exec_immediate(conn, "SELECT 1 FROM sysibm.sysdummy1")
+            ibm_db.fetch_assoc(stmt)
+            ibm_db.close(conn)
+            return get_json_result(data="Database Connection Successful!")
         else:
             return server_error_response("Unsupported database type.")
         if req["db_type"] != 'mssql':
@@ -529,7 +545,7 @@ def sessions(canvas_id):
 @manager.route('/prompts', methods=['GET'])  # noqa: F821
 @login_required
 def prompts():
-    from rag.prompts.prompts import ANALYZE_TASK_SYSTEM, ANALYZE_TASK_USER, NEXT_STEP, REFLECT, CITATION_PROMPT_TEMPLATE
+    from rag.prompts.generator import ANALYZE_TASK_SYSTEM, ANALYZE_TASK_USER, NEXT_STEP, REFLECT, CITATION_PROMPT_TEMPLATE
     return get_json_result(data={
         "task_analysis": ANALYZE_TASK_SYSTEM +"\n\n"+ ANALYZE_TASK_USER,
         "plan_generation": NEXT_STEP,

api/apps/chunk_app.py

@@ -33,8 +33,7 @@ from api.utils.api_utils import get_data_error_result, get_json_result, server_e
 from rag.app.qa import beAdoc, rmPrefix
 from rag.app.tag import label_question
 from rag.nlp import rag_tokenizer, search
-from rag.prompts import cross_languages, keyword_extraction
-from rag.prompts.prompts import gen_meta_filter
+from rag.prompts.generator import gen_meta_filter, cross_languages, keyword_extraction
 from rag.settings import PAGERANK_FLD
 from rag.utils import rmSpace
 

api/apps/conversation_app.py

@@ -15,7 +15,7 @@
 #
 import json
 import re
-import traceback
+import logging
 from copy import deepcopy
 from flask import Response, request
 from flask_login import current_user, login_required
@@ -29,8 +29,8 @@ from api.db.services.search_service import SearchService
 from api.db.services.tenant_llm_service import TenantLLMService
 from api.db.services.user_service import TenantService, UserTenantService
 from api.utils.api_utils import get_data_error_result, get_json_result, server_error_response, validate_request
-from rag.prompts.prompt_template import load_prompt
-from rag.prompts.prompts import chunks_format
+from rag.prompts.template import load_prompt
+from rag.prompts.generator import chunks_format
 
 
 @manager.route("/set", methods=["POST"])  # noqa: F821
@@ -226,7 +226,7 @@ def completion():
                 if not is_embedded:
                     ConversationService.update_by_id(conv.id, conv.to_dict())
             except Exception as e:
-                traceback.print_exc()
+                logging.exception(e)
                 yield "data:" + json.dumps({"code": 500, "message": str(e), "data": {"answer": "**ERROR**: " + str(e), "reference": []}}, ensure_ascii=False) + "\n\n"
             yield "data:" + json.dumps({"code": 0, "message": "", "data": True}, ensure_ascii=False) + "\n\n"
 

api/apps/document_app.py

@@ -577,7 +577,7 @@ def change_parser():
                 settings.docStoreConn.delete({"doc_id": doc.id}, search.index_name(tenant_id), doc.kb_id)
 
     try:
-        if req.get("pipeline_id"):
+        if "pipeline_id" in req:
             if doc.pipeline_id == req["pipeline_id"]:
                 return get_json_result(data=True)
             DocumentService.update_by_id(doc.id, {"pipeline_id": req["pipeline_id"]})

api/apps/file_app.py

@@ -246,6 +246,8 @@ def rm():
                 return get_data_error_result(message="File or Folder not found!")
             if not file.tenant_id:
                 return get_data_error_result(message="Tenant not found!")
+            if file.tenant_id != current_user.id:
+                return get_json_result(data=False, message='No authorization.', code=settings.RetCode.AUTHENTICATION_ERROR)
             if file.source_type == FileSource.KNOWLEDGEBASE:
                 continue
 
@@ -292,6 +294,8 @@ def rename():
         e, file = FileService.get_by_id(req["file_id"])
         if not e:
             return get_data_error_result(message="File not found!")
+        if file.tenant_id != current_user.id:
+            return get_json_result(data=False, message='No authorization.', code=settings.RetCode.AUTHENTICATION_ERROR)
         if file.type != FileType.FOLDER.value \
             and pathlib.Path(req["name"].lower()).suffix != pathlib.Path(
                 file.name.lower()).suffix:
@@ -328,6 +332,8 @@ def get(file_id):
         e, file = FileService.get_by_id(file_id)
         if not e:
             return get_data_error_result(message="Document not found!")
+        if file.tenant_id != current_user.id:
+            return get_json_result(data=False, message='No authorization.', code=settings.RetCode.AUTHENTICATION_ERROR)
 
         blob = STORAGE_IMPL.get(file.parent_id, file.location)
         if not blob:
@@ -367,6 +373,8 @@ def move():
                 return get_data_error_result(message="File or Folder not found!")
             if not file.tenant_id:
                 return get_data_error_result(message="Tenant not found!")
+            if file.tenant_id != current_user.id:
+                return get_json_result(data=False, message='No authorization.', code=settings.RetCode.AUTHENTICATION_ERROR)
         fe, _ = FileService.get_by_id(parent_id)
         if not fe:
             return get_data_error_result(message="Parent Folder not found!")

api/apps/sdk/doc.py

@@ -40,7 +40,7 @@ from api.utils.api_utils import check_duplicate_ids, construct_json_result, get_
 from rag.app.qa import beAdoc, rmPrefix
 from rag.app.tag import label_question
 from rag.nlp import rag_tokenizer, search
-from rag.prompts import cross_languages, keyword_extraction
+from rag.prompts.generator import cross_languages, keyword_extraction
 from rag.utils import rmSpace
 from rag.utils.storage_factory import STORAGE_IMPL
 

api/apps/sdk/files.py

@@ -3,9 +3,11 @@ import re
 
 import flask
 from flask import request
+from pathlib import Path
 
 from api.db.services.document_service import DocumentService
 from api.db.services.file2document_service import File2DocumentService
+from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.utils.api_utils import server_error_response, token_required
 from api.utils import get_uuid
 from api.db import FileType
@@ -81,16 +83,16 @@ def upload(tenant_id):
             return get_json_result(data=False, message="Can't find this folder!", code=404)
 
         for file_obj in file_objs:
-            # 文件路径处理
+            # Handle file path
             full_path = '/' + file_obj.filename
             file_obj_names = full_path.split('/')
             file_len = len(file_obj_names)
 
-            # 获取文件夹路径ID
+            # Get folder path ID
             file_id_list = FileService.get_id_list_by_id(pf_id, file_obj_names, 1, [pf_id])
             len_id_list = len(file_id_list)
 
-            # 创建文件夹结构
+            # Crete file folder
             if file_len != len_id_list:
                 e, file = FileService.get_by_id(file_id_list[len_id_list - 1])
                 if not e:
@@ -666,3 +668,71 @@ def move(tenant_id):
         return get_json_result(data=True)
     except Exception as e:
         return server_error_response(e)
+
+@manager.route('/file/convert', methods=['POST'])  # noqa: F821
+@token_required
+def convert(tenant_id):
+    req = request.json
+    kb_ids = req["kb_ids"]
+    file_ids = req["file_ids"]
+    file2documents = []
+
+    try:
+        files = FileService.get_by_ids(file_ids)
+        files_set = dict({file.id: file for file in files})
+        for file_id in file_ids:
+            file = files_set[file_id]
+            if not file:
+                return get_json_result(message="File not found!", code=404)
+            file_ids_list = [file_id]
+            if file.type == FileType.FOLDER.value:
+                file_ids_list = FileService.get_all_innermost_file_ids(file_id, [])
+            for id in file_ids_list:
+                informs = File2DocumentService.get_by_file_id(id)
+                # delete
+                for inform in informs:
+                    doc_id = inform.document_id
+                    e, doc = DocumentService.get_by_id(doc_id)
+                    if not e:
+                        return get_json_result(message="Document not found!", code=404)
+                    tenant_id = DocumentService.get_tenant_id(doc_id)
+                    if not tenant_id:
+                        return get_json_result(message="Tenant not found!", code=404)
+                    if not DocumentService.remove_document(doc, tenant_id):
+                        return get_json_result(
+                            message="Database error (Document removal)!", code=404)
+                File2DocumentService.delete_by_file_id(id)
+
+                # insert
+                for kb_id in kb_ids:
+                    e, kb = KnowledgebaseService.get_by_id(kb_id)
+                    if not e:
+                        return get_json_result(
+                            message="Can't find this knowledgebase!", code=404)
+                    e, file = FileService.get_by_id(id)
+                    if not e:
+                        return get_json_result(
+                            message="Can't find this file!", code=404)
+
+                    doc = DocumentService.insert({
+                        "id": get_uuid(),
+                        "kb_id": kb.id,
+                        "parser_id": FileService.get_parser(file.type, file.name, kb.parser_id),
+                        "parser_config": kb.parser_config,
+                        "created_by": tenant_id,
+                        "type": file.type,
+                        "name": file.name,
+                        "suffix": Path(file.name).suffix.lstrip("."),
+                        "location": file.location,
+                        "size": file.size
+                    })
+                    file2document = File2DocumentService.insert({
+                        "id": get_uuid(),
+                        "file_id": id,
+                        "document_id": doc.id,
+                    })
+
+                    file2documents.append(file2document.to_json())
+        return get_json_result(data=file2documents)
+    except Exception as e:
+        return server_error_response(e)

api/apps/sdk/session.py

@@ -38,9 +38,8 @@ from api.db.services.user_service import UserTenantService
 from api.utils import get_uuid
 from api.utils.api_utils import check_duplicate_ids, get_data_openai, get_error_data_result, get_json_result, get_result, server_error_response, token_required, validate_request
 from rag.app.tag import label_question
-from rag.prompts import chunks_format
-from rag.prompts.prompt_template import load_prompt
-from rag.prompts.prompts import cross_languages, gen_meta_filter, keyword_extraction
+from rag.prompts.template import load_prompt
+from rag.prompts.generator import cross_languages, gen_meta_filter, keyword_extraction, chunks_format
 
 
 @manager.route("/chats/<chat_id>/sessions", methods=["POST"])  # noqa: F821

api/apps/system_app.py

@@ -37,7 +37,8 @@ from timeit import default_timer as timer
 
 from rag.utils.redis_conn import REDIS_CONN
 from flask import jsonify
-from api.utils.health import run_health_checks
+from api.utils.health_utils import run_health_checks
+
 
 @manager.route("/version", methods=["GET"])  # noqa: F821
 @login_required

api/apps/user_app.py

@@ -34,7 +34,6 @@ from api.db.services.user_service import TenantService, UserService, UserTenantS
 from api.utils import (
     current_timestamp,
     datetime_format,
-    decrypt,
     download_img,
     get_format_time,
     get_uuid,
@@ -46,6 +45,7 @@ from api.utils.api_utils import (
     server_error_response,
     validate_request,
 )
+from api.utils.crypt import decrypt
 
 
 @manager.route("/login", methods=["POST", "GET"])  # noqa: F821
@@ -98,7 +98,14 @@ def login():
         return get_json_result(data=False, code=settings.RetCode.SERVER_ERROR, message="Fail to crypt password")
 
     user = UserService.query_user(email, password)
-    if user:
+
+    if user and hasattr(user, 'is_active') and user.is_active == "0":
+        return get_json_result(
+            data=False,
+            code=settings.RetCode.FORBIDDEN,
+            message="This account has been disabled, please contact the administrator!",
+        )
+    elif user:
         response_data = user.to_json()
         user.access_token = get_uuid()
         login_user(user)
@@ -227,6 +234,9 @@ def oauth_callback(channel):
         # User exists, try to log in
         user = users[0]
         user.access_token = get_uuid()
+        if user and hasattr(user, 'is_active') and user.is_active == "0":
+            return redirect("/?error=user_inactive")
+
         login_user(user)
         user.save()
         return redirect(f"/?auth={user.get_id()}")
@@ -317,6 +327,8 @@ def github_callback():
     # User has already registered, try to log in
     user = users[0]
     user.access_token = get_uuid()
+    if user and hasattr(user, 'is_active') and user.is_active == "0":
+        return redirect("/?error=user_inactive")
     login_user(user)
     user.save()
     return redirect("/?auth=%s" % user.get_id())
@@ -418,6 +430,8 @@ def feishu_callback():
 
     # User has already registered, try to log in
     user = users[0]
+    if user and hasattr(user, 'is_active') and user.is_active == "0":
+        return redirect("/?error=user_inactive")
     user.access_token = get_uuid()
     login_user(user)
     user.save()