Refactor (#537)

### What problem does this PR solve?

### Type of change

- [x] Refactoring

api/apps/document_app.py

@@ -58,7 +58,8 @@ def upload():
         if not e:
             return get_data_error_result(
                 retmsg="Can't find this knowledgebase!")
-        if DocumentService.get_doc_count(kb.tenant_id) >= int(os.environ.get('MAX_FILE_NUM_PER_USER', 8192)):
+        MAX_FILE_NUM_PER_USER = int(os.environ.get('MAX_FILE_NUM_PER_USER', 0))
+        if MAX_FILE_NUM_PER_USER > 0 and DocumentService.get_doc_count(kb.tenant_id) >= MAX_FILE_NUM_PER_USER:
             return get_data_error_result(
                 retmsg="Exceed the maximum file number of a free user!")
 

api/apps/llm_app.py

@@ -28,7 +28,7 @@ from rag.llm import EmbeddingModel, ChatModel
 def factories():
     try:
         fac = LLMFactoriesService.get_all()
-        return get_json_result(data=[f.to_dict() for f in fac if f.name not in ["QAnything", "FastEmbed"]])
+        return get_json_result(data=[f.to_dict() for f in fac if f.name not in ["Youdao", "FastEmbed"]])
     except Exception as e:
         return server_error_response(e)
 
@@ -174,7 +174,7 @@ def list():
         llms = [m.to_dict()
                 for m in llms if m.status == StatusEnum.VALID.value]
         for m in llms:
-            m["available"] = m["fid"] in facts or m["llm_name"].lower() == "flag-embedding" or m["fid"] in ["QAnything","FastEmbed"]
+            m["available"] = m["fid"] in facts or m["llm_name"].lower() == "flag-embedding" or m["fid"] in ["Youdao","FastEmbed"]
 
         llm_set = set([m["llm_name"] for m in llms])
         for o in objs:

api/db/db_models.py

@@ -697,7 +697,7 @@ class Dialog(DataBaseModel):
         null=True,
         default="Chinese",
         help_text="English|Chinese")
-    llm_id = CharField(max_length=32, null=False, help_text="default llm ID")
+    llm_id = CharField(max_length=128, null=False, help_text="default llm ID")
     llm_setting = JSONField(null=False, default={"temperature": 0.1, "top_p": 0.3, "frequency_penalty": 0.7,
                                                  "presence_penalty": 0.4, "max_tokens": 215})
     prompt_type = CharField(

api/db/init_data.py

@@ -120,7 +120,7 @@ factory_infos = [{
     "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",
         "status": "1",
 },{
-    "name": "QAnything",
+    "name": "Youdao",
     "logo": "",
     "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",
         "status": "1",
@@ -323,7 +323,7 @@ def init_llm_factory():
             "max_tokens": 2147483648,
             "model_type": LLMType.EMBEDDING.value
         },
-        # ------------------------ QAnything -----------------------
+        # ------------------------ Youdao -----------------------
         {
             "fid": factory_infos[7]["name"],
             "llm_name": "maidalun1020/bce-embedding-base_v1",
@@ -347,7 +347,9 @@ def init_llm_factory():
     LLMService.filter_delete([LLM.fid == "Local"])
     LLMService.filter_delete([LLM.fid == "Moonshot", LLM.llm_name == "flag-embedding"])
     TenantLLMService.filter_delete([TenantLLM.llm_factory == "Moonshot", TenantLLM.llm_name == "flag-embedding"])
-
+    LLMFactoriesService.filter_update([LLMFactoriesService.model.name == "QAnything"], {"name": "Youdao"})
+    LLMService.filter_update([LLMService.model.fid == "QAnything"], {"fid": "Youdao"})
+    TenantLLMService.filter_update([TenantLLMService.model.llm_factory == "QAnything"], {"llm_factory": "Youdao"})
     """
     drop table llm;
     drop table llm_factories;

api/db/services/llm_service.py

@@ -81,7 +81,7 @@ class TenantLLMService(CommonService):
         if not model_config:
             if llm_type == LLMType.EMBEDDING.value:
                 llm = LLMService.query(llm_name=llm_name)
-                if llm and llm[0].fid in ["QAnything", "FastEmbed"]:
+                if llm and llm[0].fid in ["Youdao", "FastEmbed"]:
                     model_config = {"llm_factory": llm[0].fid, "api_key":"", "llm_name": llm_name, "api_base": ""}
             if not model_config:
                 if llm_name == "flag-embedding":

api/db/services/task_service.py

@@ -21,6 +21,7 @@ from api.db import StatusEnum, FileType, TaskStatus
 from api.db.db_models import Task, Document, Knowledgebase, Tenant
 from api.db.services.common_service import CommonService
 from api.db.services.document_service import DocumentService
+from api.utils import current_timestamp
 
 
 class TaskService(CommonService):
@@ -70,6 +71,25 @@ class TaskService(CommonService):
                 cls.model.id == docs[0]["id"]).execute()
             return docs
 
+    @classmethod
+    @DB.connection_context()
+    def get_ongoing_doc_name(cls):
+        with DB.lock("get_task", -1):
+            docs = cls.model.select(*[Document.kb_id, Document.location]) \
+                .join(Document, on=(cls.model.doc_id == Document.id)) \
+                .where(
+                    Document.status == StatusEnum.VALID.value,
+                    Document.run == TaskStatus.RUNNING.value,
+                    ~(Document.type == FileType.VIRTUAL.value),
+                    cls.model.progress >= 0,
+                    cls.model.progress < 1,
+                    cls.model.create_time >= current_timestamp() - 180000
+                )
+            docs = list(docs.dicts())
+            if not docs: return []
+
+            return list(set([(d["kb_id"], d["location"]) for d in docs]))
+
     @classmethod
     @DB.connection_context()
     def do_cancel(cls, id):