bump version to 0.4.1 (#1870)

api/config.py

@@ -87,7 +87,7 @@ class Config:
         # ------------------------
         # General Configurations.
         # ------------------------
-        self.CURRENT_VERSION = "0.4.0"
+        self.CURRENT_VERSION = "0.4.1"
         self.COMMIT_SHA = get_env('COMMIT_SHA')
         self.EDITION = "SELF_HOSTED"
         self.DEPLOY_ENV = get_env('DEPLOY_ENV')

api/controllers/console/datasets/hit_testing.py

@@ -1,6 +1,8 @@
 import logging
 
 from flask_login import current_user
+
+from core.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required
 from flask_restful import Resource, reqparse, marshal
 from werkzeug.exceptions import InternalServerError, NotFound, Forbidden
@@ -8,7 +10,7 @@ from werkzeug.exceptions import InternalServerError, NotFound, Forbidden
 import services
 from controllers.console import api
 from controllers.console.app.error import ProviderNotInitializeError, ProviderQuotaExceededError, \
-    ProviderModelCurrentlyNotSupportError
+    ProviderModelCurrentlyNotSupportError, CompletionRequestError
 from controllers.console.datasets.error import HighQualityDatasetOnlyError, DatasetNotInitializedError
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
@@ -69,6 +71,8 @@ class HitTestingApi(Resource):
             raise ProviderNotInitializeError(
                 f"No Embedding Model or Reranking Model available. Please configure a valid provider "
                 f"in the Settings -> Model Provider.")
+        except InvokeError as e:
+            raise CompletionRequestError(e.description)
         except ValueError as e:
             raise ValueError(str(e))
         except Exception as e:

api/core/application_manager.py

@@ -376,7 +376,8 @@ class ApplicationManager:
                 and 'enabled' in copy_app_model_config_dict['agent_mode'] and copy_app_model_config_dict['agent_mode'][
             'enabled']:
             agent_dict = copy_app_model_config_dict.get('agent_mode')
-            if agent_dict['strategy'] in ['router', 'react_router']:
+            agent_strategy = agent_dict.get('strategy', 'router')
+            if agent_strategy in ['router', 'react_router']:
                 dataset_ids = []
                 for tool in agent_dict.get('tools', []):
                     key = list(tool.keys())[0]
@@ -402,7 +403,7 @@ class ApplicationManager:
                             retrieve_strategy=DatasetRetrieveConfigEntity.RetrieveStrategy.value_of(
                                 dataset_configs['retrieval_model']
                             ),
-                            single_strategy=agent_dict['strategy']
+                            single_strategy=agent_strategy
                         )
                     )
                 else:
@@ -419,7 +420,7 @@ class ApplicationManager:
                         )
                     )
             else:
-                if agent_dict['strategy'] == 'react':
+                if agent_strategy == 'react':
                     strategy = AgentEntity.Strategy.CHAIN_OF_THOUGHT
                 else:
                     strategy = AgentEntity.Strategy.FUNCTION_CALLING

api/core/model_runtime/entities/defaults.py

@@ -18,7 +18,7 @@ PARAMETER_RULE_TEMPLATE: Dict[DefaultParameterName, dict] = {
         'default': 0.0,
         'min': 0.0,
         'max': 1.0,
-        'precision': 1,
+        'precision': 2,
     },
     DefaultParameterName.TOP_P: {
         'label': {
@@ -34,7 +34,7 @@ PARAMETER_RULE_TEMPLATE: Dict[DefaultParameterName, dict] = {
         'default': 1.0,
         'min': 0.0,
         'max': 1.0,
-        'precision': 1,
+        'precision': 2,
     },
     DefaultParameterName.PRESENCE_PENALTY: {
         'label': {
@@ -50,7 +50,7 @@ PARAMETER_RULE_TEMPLATE: Dict[DefaultParameterName, dict] = {
         'default': 0.0,
         'min': 0.0,
         'max': 1.0,
-        'precision': 1,
+        'precision': 2,
     },
     DefaultParameterName.FREQUENCY_PENALTY: {
         'label': {
@@ -66,7 +66,7 @@ PARAMETER_RULE_TEMPLATE: Dict[DefaultParameterName, dict] = {
         'default': 0.0,
         'min': 0.0,
         'max': 1.0,
-        'precision': 1,
+        'precision': 2,
     },
     DefaultParameterName.MAX_TOKENS: {
         'label': {

api/core/model_runtime/model_providers/azure_openai/_constant.py

@@ -448,6 +448,46 @@ LLM_BASE_MODELS = [
                 currency='USD',
             )
         )
+    ),
+    AzureBaseModel(
+        base_model_name='text-davinci-003',
+        entity=AIModelEntity(
+            model='fake-deployment-name',
+            label=I18nObject(
+                en_US='fake-deployment-name-label',
+            ),
+            model_type=ModelType.LLM,
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={
+                'mode': LLMMode.COMPLETION.value,
+                'context_size': 4096,
+            },
+            parameter_rules=[
+                ParameterRule(
+                    name='temperature',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
+                ),
+                ParameterRule(
+                    name='top_p',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
+                ),
+                ParameterRule(
+                    name='presence_penalty',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.PRESENCE_PENALTY],
+                ),
+                ParameterRule(
+                    name='frequency_penalty',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.FREQUENCY_PENALTY],
+                ),
+                _get_max_tokens(default=512, min_val=1, max_val=4096),
+            ],
+            pricing=PriceConfig(
+                input=0.02,
+                output=0.02,
+                unit=0.001,
+                currency='USD',
+            )
+        )
     )
 ]
 

api/core/model_runtime/model_providers/xinference/xinference.yaml

@@ -31,7 +31,7 @@ model_credential_schema:
     label:
       zh_Hans: 服务器URL
       en_US: Server url
-    type: text-input
+    type: secret-input
     required: true
     placeholder:
       zh_Hans: 在此输入Xinference的服务器地址，如 https://example.com/xxx

api/core/provider_manager.py

@@ -3,6 +3,8 @@ from collections import defaultdict
 from json import JSONDecodeError
 from typing import Optional
 
+from sqlalchemy.exc import IntegrityError
+
 from core.entities.model_entities import DefaultModelEntity, DefaultModelProviderEntity
 from core.entities.provider_configuration import ProviderConfigurations, ProviderConfiguration, ProviderModelBundle
 from core.entities.provider_entities import CustomConfiguration, CustomProviderConfiguration, CustomModelConfiguration, \
@@ -380,17 +382,28 @@ class ProviderManager:
                 if quota.quota_type == ProviderQuotaType.TRIAL:
                     # Init trial provider records if not exists
                     if ProviderQuotaType.TRIAL not in provider_quota_to_provider_record_dict:
-                        provider_record = Provider(
-                            tenant_id=tenant_id,
-                            provider_name=provider_name,
-                            provider_type=ProviderType.SYSTEM.value,
-                            quota_type=ProviderQuotaType.TRIAL.value,
-                            quota_limit=quota.quota_limit,
-                            quota_used=0,
-                            is_valid=True
-                        )
-                        db.session.add(provider_record)
-                        db.session.commit()
+                        try:
+                            provider_record = Provider(
+                                tenant_id=tenant_id,
+                                provider_name=provider_name,
+                                provider_type=ProviderType.SYSTEM.value,
+                                quota_type=ProviderQuotaType.TRIAL.value,
+                                quota_limit=quota.quota_limit,
+                                quota_used=0,
+                                is_valid=True
+                            )
+                            db.session.add(provider_record)
+                            db.session.commit()
+                        except IntegrityError:
+                            db.session.rollback()
+                            provider_record = db.session.query(Provider) \
+                                .filter(
+                                Provider.tenant_id == tenant_id,
+                                Provider.provider_name == provider_name,
+                                Provider.provider_type == ProviderType.SYSTEM.value,
+                                Provider.quota_type == ProviderQuotaType.TRIAL.value,
+                                Provider.is_valid == True
+                            ).first()
 
                         provider_name_to_provider_records_dict[provider_name].append(provider_record)
 

docker/docker-compose.yaml

@@ -2,7 +2,7 @@ version: '3.1'
 services:
   # API service
   api:
-    image: langgenius/dify-api:0.4.0
+    image: langgenius/dify-api:0.4.1
     restart: always
     environment:
       # Startup mode, 'api' starts the API server.
@@ -128,7 +128,7 @@ services:
   # worker service
   # The Celery worker for processing the queue.
   worker:
-    image: langgenius/dify-api:0.4.0
+    image: langgenius/dify-api:0.4.1
     restart: always
     environment:
       # Startup mode, 'worker' starts the Celery worker for processing the queue.
@@ -196,7 +196,7 @@ services:
 
   # Frontend web application.
   web:
-    image: langgenius/dify-web:0.4.0
+    image: langgenius/dify-web:0.4.1
     restart: always
     environment:
       EDITION: SELF_HOSTED

web/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dify-web",
-  "version": "0.4.0",
+  "version": "0.4.1",
   "private": true,
   "scripts": {
     "dev": "next dev",