diff --git a/CONTRIBUTING_CN.md b/CONTRIBUTING_CN.md index 0478d2e1fa..69ae7071bb 100644 --- a/CONTRIBUTING_CN.md +++ b/CONTRIBUTING_CN.md @@ -6,7 +6,7 @@ 本指南和 Dify 一样在不断完善中。如果有任何滞后于项目实际情况的地方，恳请谅解，我们也欢迎任何改进建议。 -关于许可证，请花一分钟阅读我们简短的[许可和贡献者协议](./LICENSE)。社区同时也遵循[行为准则](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)。 +关于许可证，请花一分钟阅读我们简短的[许可和贡献者协议](./LICENSE)。同时也请遵循社区[行为准则](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)。 ## 开始之前 diff --git a/README.md b/README.md index 65e8001dd2..efb37d6083 100644 --- a/README.md +++ b/README.md @@ -54,7 +54,7 @@ README in বাংলা

-Dify is an open-source LLM app development platform. Its intuitive interface combines agentic AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. +Dify is an open-source LLM app development platform. Its intuitive interface combines agentic AI workflow, RAG pipeline, agent capabilities, model management, observability features, and more, allowing you to quickly move from prototype to production. ## Quick start @@ -188,7 +188,7 @@ All of Dify's offerings come with corresponding APIs, so you could effortlessly - **Dify for enterprise / organizations
** We provide additional enterprise-centric features. [Log your questions for us through this chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs.
- > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. It's an affordable AMI offering with the option to create apps with custom logo and branding. + > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one click. It's an affordable AMI offering with the option to create apps with custom logo and branding. ## Staying ahead @@ -233,7 +233,7 @@ Deploy Dify to AWS with [CDK](https://aws.amazon.com/cdk/) For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). At the same time, please consider supporting Dify by sharing it on social media and at events and conferences. -> We are looking for contributors to help with translating Dify to languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c). +> We are looking for contributors to help translate Dify into languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c). ## Community & contact diff --git a/api/.env.example b/api/.env.example index b5820fcdc2..2cc6410cdd 100644 --- a/api/.env.example +++ b/api/.env.example @@ -297,6 +297,7 @@ LINDORM_URL=http://ld-*******************-proxy-search-pub.lindorm.aliyuncs.com: LINDORM_USERNAME=admin LINDORM_PASSWORD=admin USING_UGC_INDEX=False +LINDORM_QUERY_TIMEOUT=1 # OceanBase Vector configuration OCEANBASE_VECTOR_HOST=127.0.0.1 diff --git a/api/commands.py b/api/commands.py index e70d6e0b49..c5394c6f87 100644 --- a/api/commands.py +++ b/api/commands.py @@ -271,6 +271,7 @@ def migrate_knowledge_vector_database(): upper_collection_vector_types = { VectorType.MILVUS, VectorType.PGVECTOR, + VectorType.VASTBASE, VectorType.RELYT, VectorType.WEAVIATE, VectorType.ORACLE, diff --git a/api/configs/middleware/__init__.py b/api/configs/middleware/__init__.py index c2ad24094a..d285515998 100644 --- a/api/configs/middleware/__init__.py +++ b/api/configs/middleware/__init__.py @@ -39,6 +39,7 @@ from .vdb.tencent_vector_config import TencentVectorDBConfig from .vdb.tidb_on_qdrant_config import TidbOnQdrantConfig from .vdb.tidb_vector_config import TiDBVectorConfig from .vdb.upstash_config import UpstashConfig +from .vdb.vastbase_vector_config import VastbaseVectorConfig from .vdb.vikingdb_config import VikingDBConfig from .vdb.weaviate_config import WeaviateConfig @@ -270,6 +271,7 @@ class MiddlewareConfig( OpenSearchConfig, OracleConfig, PGVectorConfig, + VastbaseVectorConfig, PGVectoRSConfig, QdrantConfig, RelytConfig, diff --git a/api/configs/middleware/vdb/lindorm_config.py b/api/configs/middleware/vdb/lindorm_config.py index 95e1d1cfca..e80e3f4a35 100644 --- a/api/configs/middleware/vdb/lindorm_config.py +++ b/api/configs/middleware/vdb/lindorm_config.py @@ -32,3 +32,4 @@ class LindormConfig(BaseSettings): description="Using UGC index will store the same type of Index in a single index but can retrieve separately.", default=False, ) + LINDORM_QUERY_TIMEOUT: Optional[float] = Field(description="The lindorm search request timeout (s)", default=2.0) diff --git a/api/configs/middleware/vdb/vastbase_vector_config.py b/api/configs/middleware/vdb/vastbase_vector_config.py new file mode 100644 index 0000000000..816d6df90a --- /dev/null +++ b/api/configs/middleware/vdb/vastbase_vector_config.py @@ -0,0 +1,45 @@ +from typing import Optional + +from pydantic import Field, PositiveInt +from pydantic_settings import BaseSettings + + +class VastbaseVectorConfig(BaseSettings): + """ + Configuration settings for Vector (Vastbase with vector extension) + """ + + VASTBASE_HOST: Optional[str] = Field( + description="Hostname or IP address of the Vastbase server with Vector extension (e.g., 'localhost')", + default=None, + ) + + VASTBASE_PORT: PositiveInt = Field( + description="Port number on which the Vastbase server is listening (default is 5432)", + default=5432, + ) + + VASTBASE_USER: Optional[str] = Field( + description="Username for authenticating with the Vastbase database", + default=None, + ) + + VASTBASE_PASSWORD: Optional[str] = Field( + description="Password for authenticating with the Vastbase database", + default=None, + ) + + VASTBASE_DATABASE: Optional[str] = Field( + description="Name of the Vastbase database to connect to", + default=None, + ) + + VASTBASE_MIN_CONNECTION: PositiveInt = Field( + description="Min connection of the Vastbase database", + default=1, + ) + + VASTBASE_MAX_CONNECTION: PositiveInt = Field( + description="Max connection of the Vastbase database", + default=5, + ) diff --git a/api/configs/packaging/__init__.py b/api/configs/packaging/__init__.py index c7aedc5b8a..a33c7727dc 100644 --- a/api/configs/packaging/__init__.py +++ b/api/configs/packaging/__init__.py @@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings): CURRENT_VERSION: str = Field( description="Dify version", - default="1.2.0", + default="1.3.0", ) COMMIT_SHA: str = Field( diff --git a/api/controllers/console/app/audio.py b/api/controllers/console/app/audio.py index 12d9157dda..7519ae96c0 100644 --- a/api/controllers/console/app/audio.py +++ b/api/controllers/console/app/audio.py @@ -80,8 +80,6 @@ class ChatMessageTextApi(Resource): @account_initialization_required @get_app_model def post(self, app_model: App): - from werkzeug.exceptions import InternalServerError - try: parser = reqparse.RequestParser() parser.add_argument("message_id", type=str, location="json") diff --git a/api/controllers/console/datasets/datasets.py b/api/controllers/console/datasets/datasets.py index 752d124735..43615af709 100644 --- a/api/controllers/console/datasets/datasets.py +++ b/api/controllers/console/datasets/datasets.py @@ -657,6 +657,7 @@ class DatasetRetrievalSettingApi(Resource): | VectorType.ELASTICSEARCH | VectorType.ELASTICSEARCH_JA | VectorType.PGVECTOR + | VectorType.VASTBASE | VectorType.TIDB_ON_QDRANT | VectorType.LINDORM | VectorType.COUCHBASE @@ -706,6 +707,7 @@ class DatasetRetrievalSettingMockApi(Resource): | VectorType.ELASTICSEARCH_JA | VectorType.COUCHBASE | VectorType.PGVECTOR + | VectorType.VASTBASE | VectorType.LINDORM | VectorType.OPENGAUSS | VectorType.OCEANBASE diff --git a/api/controllers/console/workspace/endpoint.py b/api/controllers/console/workspace/endpoint.py index a5bd2a4bcf..46dee20f8b 100644 --- a/api/controllers/console/workspace/endpoint.py +++ b/api/controllers/console/workspace/endpoint.py @@ -5,6 +5,7 @@ from werkzeug.exceptions import Forbidden from controllers.console import api from controllers.console.wraps import account_initialization_required, setup_required from core.model_runtime.utils.encoders import jsonable_encoder +from core.plugin.manager.exc import PluginPermissionDeniedError from libs.login import login_required from services.plugin.endpoint_service import EndpointService @@ -28,15 +29,18 @@ class EndpointCreateApi(Resource): settings = args["settings"] name = args["name"] - return { - "success": EndpointService.create_endpoint( - tenant_id=user.current_tenant_id, - user_id=user.id, - plugin_unique_identifier=plugin_unique_identifier, - name=name, - settings=settings, - ) - } + try: + return { + "success": EndpointService.create_endpoint( + tenant_id=user.current_tenant_id, + user_id=user.id, + plugin_unique_identifier=plugin_unique_identifier, + name=name, + settings=settings, + ) + } + except PluginPermissionDeniedError as e: + raise ValueError(e.description) from e class EndpointListApi(Resource): diff --git a/api/controllers/console/wraps.py b/api/controllers/console/wraps.py index e5e8038ad7..6911181d82 100644 --- a/api/controllers/console/wraps.py +++ b/api/controllers/console/wraps.py @@ -10,6 +10,7 @@ from configs import dify_config from controllers.console.workspace.error import AccountNotInitializedError from extensions.ext_database import db from extensions.ext_redis import redis_client +from models.account import AccountStatus from models.dataset import RateLimitLog from models.model import DifySetup from services.feature_service import FeatureService, LicenseStatus @@ -24,7 +25,7 @@ def account_initialization_required(view): # check account initialization account = current_user - if account.status == "uninitialized": + if account.status == AccountStatus.UNINITIALIZED: raise AccountNotInitializedError() return view(*args, **kwargs) diff --git a/api/controllers/service_api/app/conversation.py b/api/controllers/service_api/app/conversation.py index 334f2c5620..55600a3fd0 100644 --- a/api/controllers/service_api/app/conversation.py +++ b/api/controllers/service_api/app/conversation.py @@ -14,6 +14,9 @@ from fields.conversation_fields import ( conversation_infinite_scroll_pagination_fields, simple_conversation_fields, ) +from fields.conversation_variable_fields import ( + conversation_variable_infinite_scroll_pagination_fields, +) from libs.helper import uuid_value from models.model import App, AppMode, EndUser from services.conversation_service import ConversationService @@ -93,6 +96,31 @@ class ConversationRenameApi(Resource): raise NotFound("Conversation Not Exists.") +class ConversationVariablesApi(Resource): + @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.QUERY)) + @marshal_with(conversation_variable_infinite_scroll_pagination_fields) + def get(self, app_model: App, end_user: EndUser, c_id): + # conversational variable only for chat app + app_mode = AppMode.value_of(app_model.mode) + if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}: + raise NotChatAppError() + + conversation_id = str(c_id) + + parser = reqparse.RequestParser() + parser.add_argument("last_id", type=uuid_value, location="args") + parser.add_argument("limit", type=int_range(1, 100), required=False, default=20, location="args") + args = parser.parse_args() + + try: + return ConversationService.get_conversational_variable( + app_model, conversation_id, end_user, args["limit"], args["last_id"] + ) + except services.errors.conversation.ConversationNotExistsError: + raise NotFound("Conversation Not Exists.") + + api.add_resource(ConversationRenameApi, "/conversations//name", endpoint="conversation_name") api.add_resource(ConversationApi, "/conversations") api.add_resource(ConversationDetailApi, "/conversations/", endpoint="conversation_detail") +api.add_resource(ConversationVariablesApi, "/conversations//variables", endpoint="conversation_variables") diff --git a/api/controllers/service_api/app/workflow.py b/api/controllers/service_api/app/workflow.py index 8b10a028f3..ca3e35aab8 100644 --- a/api/controllers/service_api/app/workflow.py +++ b/api/controllers/service_api/app/workflow.py @@ -59,7 +59,7 @@ class WorkflowRunDetailApi(Resource): Get a workflow task running detail """ app_mode = AppMode.value_of(app_model.mode) - if app_mode != AppMode.WORKFLOW: + if app_mode not in [AppMode.WORKFLOW, AppMode.ADVANCED_CHAT]: raise NotWorkflowAppError() workflow_run = db.session.query(WorkflowRun).filter(WorkflowRun.id == workflow_run_id).first() diff --git a/api/core/app/apps/advanced_chat/app_generator.py b/api/core/app/apps/advanced_chat/app_generator.py index ef582d28e0..6079b51daa 100644 --- a/api/core/app/apps/advanced_chat/app_generator.py +++ b/api/core/app/apps/advanced_chat/app_generator.py @@ -7,6 +7,7 @@ from typing import Any, Literal, Optional, Union, overload from flask import Flask, current_app from pydantic import ValidationError +from sqlalchemy.orm import sessionmaker import contexts from configs import dify_config @@ -24,6 +25,8 @@ from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotA from core.model_runtime.errors.invoke import InvokeAuthorizationError from core.ops.ops_trace_manager import TraceQueueManager from core.prompt.utils.get_thread_messages_length import get_thread_messages_length +from core.repository import RepositoryFactory +from core.repository.workflow_node_execution_repository import WorkflowNodeExecutionRepository from extensions.ext_database import db from factories import file_factory from models.account import Account @@ -158,11 +161,22 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): contexts.plugin_tool_providers.set({}) contexts.plugin_tool_providers_lock.set(threading.Lock()) + # Create workflow node execution repository + session_factory = sessionmaker(bind=db.engine, expire_on_commit=False) + workflow_node_execution_repository = RepositoryFactory.create_workflow_node_execution_repository( + params={ + "tenant_id": application_generate_entity.app_config.tenant_id, + "app_id": application_generate_entity.app_config.app_id, + "session_factory": session_factory, + } + ) + return self._generate( workflow=workflow, user=user, invoke_from=invoke_from, application_generate_entity=application_generate_entity, + workflow_node_execution_repository=workflow_node_execution_repository, conversation=conversation, stream=streaming, ) @@ -215,11 +229,22 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): contexts.plugin_tool_providers.set({}) contexts.plugin_tool_providers_lock.set(threading.Lock()) + # Create workflow node execution repository + session_factory = sessionmaker(bind=db.engine, expire_on_commit=False) + workflow_node_execution_repository = RepositoryFactory.create_workflow_node_execution_repository( + params={ + "tenant_id": application_generate_entity.app_config.tenant_id, + "app_id": application_generate_entity.app_config.app_id, + "session_factory": session_factory, + } + ) + return self._generate( workflow=workflow, user=user, invoke_from=InvokeFrom.DEBUGGER, application_generate_entity=application_generate_entity, + workflow_node_execution_repository=workflow_node_execution_repository, conversation=None, stream=streaming, ) @@ -270,11 +295,22 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): contexts.plugin_tool_providers.set({}) contexts.plugin_tool_providers_lock.set(threading.Lock()) + # Create workflow node execution repository + session_factory = sessionmaker(bind=db.engine, expire_on_commit=False) + workflow_node_execution_repository = RepositoryFactory.create_workflow_node_execution_repository( + params={ + "tenant_id": application_generate_entity.app_config.tenant_id, + "app_id": application_generate_entity.app_config.app_id, + "session_factory": session_factory, + } + ) + return self._generate( workflow=workflow, user=user, invoke_from=InvokeFrom.DEBUGGER, application_generate_entity=application_generate_entity, + workflow_node_execution_repository=workflow_node_execution_repository, conversation=None, stream=streaming, ) @@ -286,6 +322,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): user: Union[Account, EndUser], invoke_from: InvokeFrom, application_generate_entity: AdvancedChatAppGenerateEntity, + workflow_node_execution_repository: WorkflowNodeExecutionRepository, conversation: Optional[Conversation] = None, stream: bool = True, ) -> Mapping[str, Any] | Generator[str | Mapping[str, Any], Any, None]: @@ -296,6 +333,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): :param user: account or end user :param invoke_from: invoke from source :param application_generate_entity: application generate entity + :param workflow_node_execution_repository: repository for workflow node execution :param conversation: conversation :param stream: is stream """ @@ -348,6 +386,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): conversation=conversation, message=message, user=user, + workflow_node_execution_repository=workflow_node_execution_repository, stream=stream, ) @@ -419,6 +458,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): conversation: Conversation, message: Message, user: Union[Account, EndUser], + workflow_node_execution_repository: WorkflowNodeExecutionRepository, stream: bool = False, ) -> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]: """ @@ -430,6 +470,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): :param message: message :param user: account or end user :param stream: is stream + :param workflow_node_execution_repository: optional repository for workflow node execution :return: """ # init generate task pipeline @@ -442,6 +483,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): user=user, stream=stream, dialogue_count=self._dialogue_count, + workflow_node_execution_repository=workflow_node_execution_repository, ) try: diff --git a/api/core/app/apps/advanced_chat/generate_task_pipeline.py b/api/core/app/apps/advanced_chat/generate_task_pipeline.py index 3bf6c330db..43ccaea9c0 100644 --- a/api/core/app/apps/advanced_chat/generate_task_pipeline.py +++ b/api/core/app/apps/advanced_chat/generate_task_pipeline.py @@ -62,6 +62,7 @@ from core.app.task_pipeline.workflow_cycle_manage import WorkflowCycleManage from core.model_runtime.entities.llm_entities import LLMUsage from core.model_runtime.utils.encoders import jsonable_encoder from core.ops.ops_trace_manager import TraceQueueManager +from core.repository.workflow_node_execution_repository import WorkflowNodeExecutionRepository from core.workflow.enums import SystemVariableKey from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState from core.workflow.nodes import NodeType @@ -93,6 +94,7 @@ class AdvancedChatAppGenerateTaskPipeline: user: Union[Account, EndUser], stream: bool, dialogue_count: int, + workflow_node_execution_repository: WorkflowNodeExecutionRepository, ) -> None: self._base_task_pipeline = BasedGenerateTaskPipeline( application_generate_entity=application_generate_entity, @@ -123,6 +125,7 @@ class AdvancedChatAppGenerateTaskPipeline: SystemVariableKey.WORKFLOW_ID: workflow.id, SystemVariableKey.WORKFLOW_RUN_ID: application_generate_entity.workflow_run_id, }, + workflow_node_execution_repository=workflow_node_execution_repository, ) self._task_state = WorkflowTaskState() @@ -684,7 +687,9 @@ class AdvancedChatAppGenerateTaskPipeline: ) elif isinstance(event, QueueMessageReplaceEvent): # published by moderation - yield self._message_cycle_manager._message_replace_to_stream_response(answer=event.text) + yield self._message_cycle_manager._message_replace_to_stream_response( + answer=event.text, reason=event.reason + ) elif isinstance(event, QueueAdvancedChatMessageEndEvent): if not graph_runtime_state: raise ValueError("graph runtime state not initialized.") @@ -695,7 +700,8 @@ class AdvancedChatAppGenerateTaskPipeline: if output_moderation_answer: self._task_state.answer = output_moderation_answer yield self._message_cycle_manager._message_replace_to_stream_response( - answer=output_moderation_answer + answer=output_moderation_answer, + reason=QueueMessageReplaceEvent.MessageReplaceReason.OUTPUT_MODERATION, ) # Save message diff --git a/api/core/app/apps/message_based_app_generator.py b/api/core/app/apps/message_based_app_generator.py index b1f527c0f2..995082b79d 100644 --- a/api/core/app/apps/message_based_app_generator.py +++ b/api/core/app/apps/message_based_app_generator.py @@ -153,6 +153,8 @@ class MessageBasedAppGenerator(BaseAppGenerator): query = application_generate_entity.query or "New conversation" else: query = next(iter(application_generate_entity.inputs.values()), "New conversation") + if isinstance(query, int): + query = str(query) query = query or "New conversation" conversation_name = (query[:20] + "…") if len(query) > 20 else query diff --git a/api/core/app/apps/workflow/app_generator.py b/api/core/app/apps/workflow/app_generator.py index 08986b16f0..6be3a7331d 100644 --- a/api/core/app/apps/workflow/app_generator.py +++ b/api/core/app/apps/workflow/app_generator.py @@ -7,6 +7,7 @@ from typing import Any, Literal, Optional, Union, overload from flask import Flask, current_app from pydantic import ValidationError +from sqlalchemy.orm import sessionmaker import contexts from configs import dify_config @@ -22,6 +23,8 @@ from core.app.entities.app_invoke_entities import InvokeFrom, WorkflowAppGenerat from core.app.entities.task_entities import WorkflowAppBlockingResponse, WorkflowAppStreamResponse from core.model_runtime.errors.invoke import InvokeAuthorizationError from core.ops.ops_trace_manager import TraceQueueManager +from core.repository import RepositoryFactory +from core.repository.workflow_node_execution_repository import WorkflowNodeExecutionRepository from extensions.ext_database import db from factories import file_factory from models import Account, App, EndUser, Workflow @@ -133,12 +136,23 @@ class WorkflowAppGenerator(BaseAppGenerator): contexts.plugin_tool_providers.set({}) contexts.plugin_tool_providers_lock.set(threading.Lock()) + # Create workflow node execution repository + session_factory = sessionmaker(bind=db.engine, expire_on_commit=False) + workflow_node_execution_repository = RepositoryFactory.create_workflow_node_execution_repository( + params={ + "tenant_id": application_generate_entity.app_config.tenant_id, + "app_id": application_generate_entity.app_config.app_id, + "session_factory": session_factory, + } + ) + return self._generate( app_model=app_model, workflow=workflow, user=user, application_generate_entity=application_generate_entity, invoke_from=invoke_from, + workflow_node_execution_repository=workflow_node_execution_repository, streaming=streaming, workflow_thread_pool_id=workflow_thread_pool_id, ) @@ -151,6 +165,7 @@ class WorkflowAppGenerator(BaseAppGenerator): user: Union[Account, EndUser], application_generate_entity: WorkflowAppGenerateEntity, invoke_from: InvokeFrom, + workflow_node_execution_repository: WorkflowNodeExecutionRepository, streaming: bool = True, workflow_thread_pool_id: Optional[str] = None, ) -> Union[Mapping[str, Any], Generator[str | Mapping[str, Any], None, None]]: @@ -162,6 +177,7 @@ class WorkflowAppGenerator(BaseAppGenerator): :param user: account or end user :param application_generate_entity: application generate entity :param invoke_from: invoke from source + :param workflow_node_execution_repository: repository for workflow node execution :param streaming: is stream :param workflow_thread_pool_id: workflow thread pool id """ @@ -193,6 +209,7 @@ class WorkflowAppGenerator(BaseAppGenerator): workflow=workflow, queue_manager=queue_manager, user=user, + workflow_node_execution_repository=workflow_node_execution_repository, stream=streaming, ) @@ -245,12 +262,23 @@ class WorkflowAppGenerator(BaseAppGenerator): contexts.plugin_tool_providers.set({}) contexts.plugin_tool_providers_lock.set(threading.Lock()) + # Create workflow node execution repository + session_factory = sessionmaker(bind=db.engine, expire_on_commit=False) + workflow_node_execution_repository = RepositoryFactory.create_workflow_node_execution_repository( + params={ + "tenant_id": application_generate_entity.app_config.tenant_id, + "app_id": application_generate_entity.app_config.app_id, + "session_factory": session_factory, + } + ) + return self._generate( app_model=app_model, workflow=workflow, user=user, invoke_from=InvokeFrom.DEBUGGER, application_generate_entity=application_generate_entity, + workflow_node_execution_repository=workflow_node_execution_repository, streaming=streaming, ) @@ -299,12 +327,23 @@ class WorkflowAppGenerator(BaseAppGenerator): contexts.plugin_tool_providers.set({}) contexts.plugin_tool_providers_lock.set(threading.Lock()) + # Create workflow node execution repository + session_factory = sessionmaker(bind=db.engine, expire_on_commit=False) + workflow_node_execution_repository = RepositoryFactory.create_workflow_node_execution_repository( + params={ + "tenant_id": application_generate_entity.app_config.tenant_id, + "app_id": application_generate_entity.app_config.app_id, + "session_factory": session_factory, + } + ) + return self._generate( app_model=app_model, workflow=workflow, user=user, invoke_from=InvokeFrom.DEBUGGER, application_generate_entity=application_generate_entity, + workflow_node_execution_repository=workflow_node_execution_repository, streaming=streaming, ) @@ -361,6 +400,7 @@ class WorkflowAppGenerator(BaseAppGenerator): workflow: Workflow, queue_manager: AppQueueManager, user: Union[Account, EndUser], + workflow_node_execution_repository: WorkflowNodeExecutionRepository, stream: bool = False, ) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]: """ @@ -370,6 +410,7 @@ class WorkflowAppGenerator(BaseAppGenerator): :param queue_manager: queue manager :param user: account or end user :param stream: is stream + :param workflow_node_execution_repository: optional repository for workflow node execution :return: """ # init generate task pipeline @@ -379,6 +420,7 @@ class WorkflowAppGenerator(BaseAppGenerator): queue_manager=queue_manager, user=user, stream=stream, + workflow_node_execution_repository=workflow_node_execution_repository, ) try: diff --git a/api/core/app/apps/workflow/generate_task_pipeline.py b/api/core/app/apps/workflow/generate_task_pipeline.py index 1f998edb6a..68131a7463 100644 --- a/api/core/app/apps/workflow/generate_task_pipeline.py +++ b/api/core/app/apps/workflow/generate_task_pipeline.py @@ -54,6 +54,7 @@ from core.app.entities.task_entities import ( from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline from core.app.task_pipeline.workflow_cycle_manage import WorkflowCycleManage from core.ops.ops_trace_manager import TraceQueueManager +from core.repository.workflow_node_execution_repository import WorkflowNodeExecutionRepository from core.workflow.enums import SystemVariableKey from extensions.ext_database import db from models.account import Account @@ -82,6 +83,7 @@ class WorkflowAppGenerateTaskPipeline: queue_manager: AppQueueManager, user: Union[Account, EndUser], stream: bool, + workflow_node_execution_repository: WorkflowNodeExecutionRepository, ) -> None: self._base_task_pipeline = BasedGenerateTaskPipeline( application_generate_entity=application_generate_entity, @@ -109,6 +111,7 @@ class WorkflowAppGenerateTaskPipeline: SystemVariableKey.WORKFLOW_ID: workflow.id, SystemVariableKey.WORKFLOW_RUN_ID: application_generate_entity.workflow_run_id, }, + workflow_node_execution_repository=workflow_node_execution_repository, ) self._application_generate_entity = application_generate_entity diff --git a/api/core/app/entities/queue_entities.py b/api/core/app/entities/queue_entities.py index 3702326406..7228020e9b 100644 --- a/api/core/app/entities/queue_entities.py +++ b/api/core/app/entities/queue_entities.py @@ -264,8 +264,16 @@ class QueueMessageReplaceEvent(AppQueueEvent): QueueMessageReplaceEvent entity """ + class MessageReplaceReason(StrEnum): + """ + Reason for message replace event + """ + + OUTPUT_MODERATION = "output_moderation" + event: QueueEvent = QueueEvent.MESSAGE_REPLACE text: str + reason: str class QueueRetrieverResourcesEvent(AppQueueEvent): diff --git a/api/core/app/entities/task_entities.py b/api/core/app/entities/task_entities.py index f23ee1b9fd..817699bd20 100644 --- a/api/core/app/entities/task_entities.py +++ b/api/core/app/entities/task_entities.py @@ -148,6 +148,7 @@ class MessageReplaceStreamResponse(StreamResponse): event: StreamEvent = StreamEvent.MESSAGE_REPLACE answer: str + reason: str class AgentThoughtStreamResponse(StreamResponse): diff --git a/api/core/app/task_pipeline/based_generate_task_pipeline.py b/api/core/app/task_pipeline/based_generate_task_pipeline.py index a2e06d4e1f..5331c0cc94 100644 --- a/api/core/app/task_pipeline/based_generate_task_pipeline.py +++ b/api/core/app/task_pipeline/based_generate_task_pipeline.py @@ -126,12 +126,12 @@ class BasedGenerateTaskPipeline: if self._output_moderation_handler: self._output_moderation_handler.stop_thread() - completion = self._output_moderation_handler.moderation_completion( + completion, flagged = self._output_moderation_handler.moderation_completion( completion=completion, public_event=False ) self._output_moderation_handler = None - - return completion + if flagged: + return completion return None diff --git a/api/core/app/task_pipeline/message_cycle_manage.py b/api/core/app/task_pipeline/message_cycle_manage.py index 3972f1e897..a6d826f08b 100644 --- a/api/core/app/task_pipeline/message_cycle_manage.py +++ b/api/core/app/task_pipeline/message_cycle_manage.py @@ -182,10 +182,12 @@ class MessageCycleManage: from_variable_selector=from_variable_selector, ) - def _message_replace_to_stream_response(self, answer: str) -> MessageReplaceStreamResponse: + def _message_replace_to_stream_response(self, answer: str, reason: str = "") -> MessageReplaceStreamResponse: """ Message replace to stream response. :param answer: answer :return: """ - return MessageReplaceStreamResponse(task_id=self._application_generate_entity.task_id, answer=answer) + return MessageReplaceStreamResponse( + task_id=self._application_generate_entity.task_id, answer=answer, reason=reason + ) diff --git a/api/core/app/task_pipeline/workflow_cycle_manage.py b/api/core/app/task_pipeline/workflow_cycle_manage.py index 5ce9f737d1..38e7c9eb12 100644 --- a/api/core/app/task_pipeline/workflow_cycle_manage.py +++ b/api/core/app/task_pipeline/workflow_cycle_manage.py @@ -6,7 +6,7 @@ from typing import Any, Optional, Union, cast from uuid import uuid4 from sqlalchemy import func, select -from sqlalchemy.orm import Session, sessionmaker +from sqlalchemy.orm import Session from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom, WorkflowAppGenerateEntity from core.app.entities.queue_entities import ( @@ -49,14 +49,13 @@ from core.file import FILE_MODEL_IDENTITY, File from core.model_runtime.utils.encoders import jsonable_encoder from core.ops.entities.trace_entity import TraceTaskName from core.ops.ops_trace_manager import TraceQueueManager, TraceTask -from core.repository import RepositoryFactory +from core.repository.workflow_node_execution_repository import WorkflowNodeExecutionRepository from core.tools.tool_manager import ToolManager from core.workflow.entities.node_entities import NodeRunMetadataKey from core.workflow.enums import SystemVariableKey from core.workflow.nodes import NodeType from core.workflow.nodes.tool.entities import ToolNodeData from core.workflow.workflow_entry import WorkflowEntry -from extensions.ext_database import db from models.account import Account from models.enums import CreatedByRole, WorkflowRunTriggeredFrom from models.model import EndUser @@ -76,26 +75,13 @@ class WorkflowCycleManage: *, application_generate_entity: Union[AdvancedChatAppGenerateEntity, WorkflowAppGenerateEntity], workflow_system_variables: dict[SystemVariableKey, Any], + workflow_node_execution_repository: WorkflowNodeExecutionRepository, ) -> None: self._workflow_run: WorkflowRun | None = None self._workflow_node_executions: dict[str, WorkflowNodeExecution] = {} self._application_generate_entity = application_generate_entity self._workflow_system_variables = workflow_system_variables - - # Initialize the session factory and repository - # We use the global db engine instead of the session passed to methods - # Disable expire_on_commit to avoid the need for merging objects - self._session_factory = sessionmaker(bind=db.engine, expire_on_commit=False) - self._workflow_node_execution_repository = RepositoryFactory.create_workflow_node_execution_repository( - params={ - "tenant_id": self._application_generate_entity.app_config.tenant_id, - "app_id": self._application_generate_entity.app_config.app_id, - "session_factory": self._session_factory, - } - ) - - # We'll still keep the cache for backward compatibility and performance - # but use the repository for database operations + self._workflow_node_execution_repository = workflow_node_execution_repository def _handle_workflow_run_start( self, diff --git a/api/core/entities/provider_configuration.py b/api/core/entities/provider_configuration.py index b3affc91a6..86887c9b4a 100644 --- a/api/core/entities/provider_configuration.py +++ b/api/core/entities/provider_configuration.py @@ -798,7 +798,25 @@ class ProviderConfiguration(BaseModel): provider_models = [m for m in provider_models if m.status == ModelStatus.ACTIVE] # resort provider_models - return sorted(provider_models, key=lambda x: x.model_type.value) + # Optimize sorting logic: first sort by provider.position order, then by model_type.value + # Get the position list for model types (retrieve only once for better performance) + model_type_positions = {} + if hasattr(self.provider, "position") and self.provider.position: + model_type_positions = self.provider.position + + def get_sort_key(model: ModelWithProviderEntity): + # Get the position list for the current model type + positions = model_type_positions.get(model.model_type.value, []) + + # If the model name is in the position list, use its index for sorting + # Otherwise use a large value (list length) to place undefined models at the end + position_index = positions.index(model.model) if model.model in positions else len(positions) + + # Return composite sort key: (model_type value, model position index) + return (model.model_type.value, position_index) + + # Sort using the composite sort key + return sorted(provider_models, key=get_sort_key) def _get_system_provider_models( self, diff --git a/api/core/llm_generator/prompts.py b/api/core/llm_generator/prompts.py index 82d22d7f89..fad7cea01c 100644 --- a/api/core/llm_generator/prompts.py +++ b/api/core/llm_generator/prompts.py @@ -1,7 +1,7 @@ # Written by YORKI MINAKO🤡, Edited by Xiaoyi CONVERSATION_TITLE_PROMPT = """You need to decompose the user's input into "subject" and "intention" in order to accurately figure out what the user's input language actually is. -Notice: the language type user use could be diverse, which can be English, Chinese, Italian, Español, Arabic, Japanese, French, and etc. -MAKE SURE your output is the SAME language as the user's input! +Notice: the language type user uses could be diverse, which can be English, Chinese, Italian, Español, Arabic, Japanese, French, and etc. +ENSURE your output is in the SAME language as the user's input! Your output is restricted only to: (Input language) Intention + Subject(short as possible) Your output MUST be a valid JSON. @@ -19,7 +19,7 @@ User Input: hi, yesterday i had some burgers. example 2: User Input: hello { - "Language Type": "The user's input is written in pure English", + "Language Type": "The user's input is pure English", "Your Reasoning": "The language of my output must be pure English.", "Your Output": "Greeting myself☺️" } @@ -46,7 +46,7 @@ example 5: User Input: why小红的年龄is老than小明？ { "Language Type": "The user's input is English-Chinese mixed", - "Your Reasoning": "The English parts are subjective particles, the main intention is written in Chinese, besides, Chinese occupies a greater \"actual meaning\" than English, so the language of my output must be using Chinese.", + "Your Reasoning": "The English parts are filler words, the main intention is written in Chinese, besides, Chinese occupies a greater \"actual meaning\" than English, so the language of my output must be using Chinese.", "Your Output": "询问小红和小明的年龄" } @@ -114,6 +114,13 @@ JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE = ( "4. The returned object should contain at least one key-value pair.\n\n" "5. The returned object should always be in the format: {result: ...}\n\n" "Example:\n" + "/**\n" + " * Multiplies two numbers together.\n" + " *\n" + " * @param {number} arg1 - The first number to multiply.\n" + " * @param {number} arg2 - The second number to multiply.\n" + " * @returns {{ result: number }} The result of the multiplication.\n" + " */\n" "function main(arg1, arg2) {\n" " return {\n" " result: arg1 * arg2\n" @@ -130,7 +137,7 @@ JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE = ( SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT = ( "Please help me predict the three most likely questions that human would ask, " - "and keeping each question under 20 characters.\n" + "and keep each question under 20 characters.\n" "MAKE SURE your output is the SAME language as the Assistant's latest response. " "The output must be an array in JSON format following the specified schema:\n" '["question1","question2","question3"]\n' @@ -157,9 +164,9 @@ Here is a task description for which I would like you to create a high-quality p Based on task description, please create a well-structured prompt template that another AI could use to consistently complete the task. The prompt template should include: - Do not include or section and variables in the prompt, assume user will add them at their own will. -- Clear instructions for the AI that will be using this prompt, demarcated with tags. The instructions should provide step-by-step directions on how to complete the task using the input variables. Also Specifies in the instructions that the output should not contain any xml tag. +- Clear instructions for the AI that will be using this prompt, demarcated with tags. The instructions should provide step-by-step directions on how to complete the task using the input variables. Also Specifies in the instructions that the output should not contain any xml tag. - Relevant examples if needed to clarify the task further, demarcated with tags. Do not include variables in the prompt. Give three pairs of input and output examples. -- Include other relevant sections demarcated with appropriate XML tags like , . +- Include other relevant sections demarcated with appropriate XML tags like , . - Use the same language as task description. - Output in ``` xml ``` and start with Please generate the full prompt template with at least 300 words and output only the prompt template. @@ -172,7 +179,7 @@ Here is a task description for which I would like you to create a high-quality p Based on task description, please create a well-structured prompt template that another AI could use to consistently complete the task. The prompt template should include: - Descriptive variable names surrounded by {{ }} (two curly brackets) to indicate where the actual values will be substituted in. Choose variable names that clearly indicate the type of value expected. Variable names have to be composed of number, english alphabets and underline and nothing else. -- Clear instructions for the AI that will be using this prompt, demarcated with tags. The instructions should provide step-by-step directions on how to complete the task using the input variables. Also Specifies in the instructions that the output should not contain any xml tag. +- Clear instructions for the AI that will be using this prompt, demarcated with tags. The instructions should provide step-by-step directions on how to complete the task using the input variables. Also Specifies in the instructions that the output should not contain any xml tag. - Relevant examples if needed to clarify the task further, demarcated with tags. Do not use curly brackets any other than in section. - Any other relevant sections demarcated with appropriate XML tags like , , etc. - Use the same language as task description. @@ -291,32 +298,30 @@ Your task is to convert simple user descriptions into properly formatted JSON Sc { "type": "object", "properties": { - "properties": { - "songs": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "id": { - "type": "string" - }, - "duration": { - "type": "string" - }, - "aritst": { - "type": "string" - } + "songs": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "id": { + "type": "string" + }, + "duration": { + "type": "string" }, - "required": [ - "name", - "id", - "duration", - "aritst" - ] - } + "aritst": { + "type": "string" + } + }, + "required": [ + "name", + "id", + "duration", + "aritst" + ] } } }, diff --git a/api/core/model_runtime/entities/provider_entities.py b/api/core/model_runtime/entities/provider_entities.py index 85321bed94..d0f9ee13e5 100644 --- a/api/core/model_runtime/entities/provider_entities.py +++ b/api/core/model_runtime/entities/provider_entities.py @@ -134,6 +134,9 @@ class ProviderEntity(BaseModel): # pydantic configs model_config = ConfigDict(protected_namespaces=()) + # position from plugin _position.yaml + position: Optional[dict[str, list[str]]] = {} + @field_validator("models", mode="before") @classmethod def validate_models(cls, v): diff --git a/api/core/moderation/output_moderation.py b/api/core/moderation/output_moderation.py index e595be126c..2ec315417f 100644 --- a/api/core/moderation/output_moderation.py +++ b/api/core/moderation/output_moderation.py @@ -46,14 +46,14 @@ class OutputModeration(BaseModel): if not self.thread: self.thread = self.start_thread() - def moderation_completion(self, completion: str, public_event: bool = False) -> str: + def moderation_completion(self, completion: str, public_event: bool = False) -> tuple[str, bool]: self.buffer = completion self.is_final_chunk = True result = self.moderation(tenant_id=self.tenant_id, app_id=self.app_id, moderation_buffer=completion) if not result or not result.flagged: - return completion + return completion, False if result.action == ModerationAction.DIRECT_OUTPUT: final_output = result.preset_response @@ -61,9 +61,14 @@ class OutputModeration(BaseModel): final_output = result.text if public_event: - self.queue_manager.publish(QueueMessageReplaceEvent(text=final_output), PublishFrom.TASK_PIPELINE) + self.queue_manager.publish( + QueueMessageReplaceEvent( + text=final_output, reason=QueueMessageReplaceEvent.MessageReplaceReason.OUTPUT_MODERATION + ), + PublishFrom.TASK_PIPELINE, + ) - return final_output + return final_output, True def start_thread(self) -> threading.Thread: buffer_size = dify_config.MODERATION_BUFFER_SIZE @@ -112,7 +117,12 @@ class OutputModeration(BaseModel): # trigger replace event if self.thread_running: - self.queue_manager.publish(QueueMessageReplaceEvent(text=final_output), PublishFrom.TASK_PIPELINE) + self.queue_manager.publish( + QueueMessageReplaceEvent( + text=final_output, reason=QueueMessageReplaceEvent.MessageReplaceReason.OUTPUT_MODERATION + ), + PublishFrom.TASK_PIPELINE, + ) if result.action == ModerationAction.DIRECT_OUTPUT: break diff --git a/api/core/rag/datasource/vdb/lindorm/lindorm_vector.py b/api/core/rag/datasource/vdb/lindorm/lindorm_vector.py index 643ac2df4e..e9ff1ce43d 100644 --- a/api/core/rag/datasource/vdb/lindorm/lindorm_vector.py +++ b/api/core/rag/datasource/vdb/lindorm/lindorm_vector.py @@ -32,6 +32,7 @@ class LindormVectorStoreConfig(BaseModel): username: Optional[str] = None password: Optional[str] = None using_ugc: Optional[bool] = False + request_timeout: Optional[float] = 1.0 # timeout units: s @model_validator(mode="before") @classmethod @@ -251,9 +252,9 @@ class LindormVectorStore(BaseVector): query = default_vector_search_query(query_vector=query_vector, k=top_k, filters=filters, **kwargs) try: - params = {} + params = {"timeout": self._client_config.request_timeout} if self._using_ugc: - params["routing"] = self._routing + params["routing"] = self._routing # type: ignore response = self._client.search(index=self._collection_name, body=query, params=params) except Exception: logger.exception(f"Error executing vector search, query: {query}") @@ -304,8 +305,8 @@ class LindormVectorStore(BaseVector): routing=routing, routing_field=self._routing_field, ) - - response = self._client.search(index=self._collection_name, body=full_text_query) + params = {"timeout": self._client_config.request_timeout} + response = self._client.search(index=self._collection_name, body=full_text_query, params=params) docs = [] for hit in response["hits"]["hits"]: docs.append( @@ -554,6 +555,7 @@ class LindormVectorStoreFactory(AbstractVectorFactory): username=dify_config.LINDORM_USERNAME, password=dify_config.LINDORM_PASSWORD, using_ugc=dify_config.USING_UGC_INDEX, + request_timeout=dify_config.LINDORM_QUERY_TIMEOUT, ) using_ugc = dify_config.USING_UGC_INDEX if using_ugc is None: diff --git a/api/core/rag/datasource/vdb/pyvastbase/__init__.py b/api/core/rag/datasource/vdb/pyvastbase/__init__.py new file mode 100644 index 0000000000..e69de29bb2 diff --git a/api/core/rag/datasource/vdb/pyvastbase/vastbase_vector.py b/api/core/rag/datasource/vdb/pyvastbase/vastbase_vector.py new file mode 100644 index 0000000000..a61d571e16 --- /dev/null +++ b/api/core/rag/datasource/vdb/pyvastbase/vastbase_vector.py @@ -0,0 +1,243 @@ +import json +import uuid +from contextlib import contextmanager +from typing import Any + +import psycopg2.extras # type: ignore +import psycopg2.pool # type: ignore +from pydantic import BaseModel, model_validator + +from configs import dify_config +from core.rag.datasource.vdb.vector_base import BaseVector +from core.rag.datasource.vdb.vector_factory import AbstractVectorFactory +from core.rag.datasource.vdb.vector_type import VectorType +from core.rag.embedding.embedding_base import Embeddings +from core.rag.models.document import Document +from extensions.ext_redis import redis_client +from models.dataset import Dataset + + +class VastbaseVectorConfig(BaseModel): + host: str + port: int + user: str + password: str + database: str + min_connection: int + max_connection: int + + @model_validator(mode="before") + @classmethod + def validate_config(cls, values: dict) -> dict: + if not values["host"]: + raise ValueError("config VASTBASE_HOST is required") + if not values["port"]: + raise ValueError("config VASTBASE_PORT is required") + if not values["user"]: + raise ValueError("config VASTBASE_USER is required") + if not values["password"]: + raise ValueError("config VASTBASE_PASSWORD is required") + if not values["database"]: + raise ValueError("config VASTBASE_DATABASE is required") + if not values["min_connection"]: + raise ValueError("config VASTBASE_MIN_CONNECTION is required") + if not values["max_connection"]: + raise ValueError("config VASTBASE_MAX_CONNECTION is required") + if values["min_connection"] > values["max_connection"]: + raise ValueError("config VASTBASE_MIN_CONNECTION should less than VASTBASE_MAX_CONNECTION") + return values + + +SQL_CREATE_TABLE = """ +CREATE TABLE IF NOT EXISTS {table_name} ( + id UUID PRIMARY KEY, + text TEXT NOT NULL, + meta JSONB NOT NULL, + embedding floatvector({dimension}) NOT NULL +); +""" + +SQL_CREATE_INDEX = """ +CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name} +USING hnsw (embedding floatvector_cosine_ops) WITH (m = 16, ef_construction = 64); +""" + + +class VastbaseVector(BaseVector): + def __init__(self, collection_name: str, config: VastbaseVectorConfig): + super().__init__(collection_name) + self.pool = self._create_connection_pool(config) + self.table_name = f"embedding_{collection_name}" + + def get_type(self) -> str: + return VectorType.VASTBASE + + def _create_connection_pool(self, config: VastbaseVectorConfig): + return psycopg2.pool.SimpleConnectionPool( + config.min_connection, + config.max_connection, + host=config.host, + port=config.port, + user=config.user, + password=config.password, + database=config.database, + ) + + @contextmanager + def _get_cursor(self): + conn = self.pool.getconn() + cur = conn.cursor() + try: + yield cur + finally: + cur.close() + conn.commit() + self.pool.putconn(conn) + + def create(self, texts: list[Document], embeddings: list[list[float]], **kwargs): + dimension = len(embeddings[0]) + self._create_collection(dimension) + return self.add_texts(texts, embeddings) + + def add_texts(self, documents: list[Document], embeddings: list[list[float]], **kwargs): + values = [] + pks = [] + for i, doc in enumerate(documents): + if doc.metadata is not None: + doc_id = doc.metadata.get("doc_id", str(uuid.uuid4())) + pks.append(doc_id) + values.append( + ( + doc_id, + doc.page_content, + json.dumps(doc.metadata), + embeddings[i], + ) + ) + with self._get_cursor() as cur: + psycopg2.extras.execute_values( + cur, f"INSERT INTO {self.table_name} (id, text, meta, embedding) VALUES %s", values + ) + return pks + + def text_exists(self, id: str) -> bool: + with self._get_cursor() as cur: + cur.execute(f"SELECT id FROM {self.table_name} WHERE id = %s", (id,)) + return cur.fetchone() is not None + + def get_by_ids(self, ids: list[str]) -> list[Document]: + with self._get_cursor() as cur: + cur.execute(f"SELECT meta, text FROM {self.table_name} WHERE id IN %s", (tuple(ids),)) + docs = [] + for record in cur: + docs.append(Document(page_content=record[1], metadata=record[0])) + return docs + + def delete_by_ids(self, ids: list[str]) -> None: + # Avoiding crashes caused by performing delete operations on empty lists in certain scenarios + # Scenario 1: extract a document fails, resulting in a table not being created. + # Then clicking the retry button triggers a delete operation on an empty list. + if not ids: + return + with self._get_cursor() as cur: + cur.execute(f"DELETE FROM {self.table_name} WHERE id IN %s", (tuple(ids),)) + + def delete_by_metadata_field(self, key: str, value: str) -> None: + with self._get_cursor() as cur: + cur.execute(f"DELETE FROM {self.table_name} WHERE meta->>%s = %s", (key, value)) + + def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]: + """ + Search the nearest neighbors to a vector. + + :param query_vector: The input vector to search for similar items. + :param top_k: The number of nearest neighbors to return, default is 5. + :return: List of Documents that are nearest to the query vector. + """ + top_k = kwargs.get("top_k", 4) + + if not isinstance(top_k, int) or top_k <= 0: + raise ValueError("top_k must be a positive integer") + with self._get_cursor() as cur: + cur.execute( + f"SELECT meta, text, embedding <=> %s AS distance FROM {self.table_name}" + f" ORDER BY distance LIMIT {top_k}", + (json.dumps(query_vector),), + ) + docs = [] + score_threshold = float(kwargs.get("score_threshold") or 0.0) + for record in cur: + metadata, text, distance = record + score = 1 - distance + metadata["score"] = score + if score > score_threshold: + docs.append(Document(page_content=text, metadata=metadata)) + return docs + + def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]: + top_k = kwargs.get("top_k", 5) + + if not isinstance(top_k, int) or top_k <= 0: + raise ValueError("top_k must be a positive integer") + with self._get_cursor() as cur: + cur.execute( + f"""SELECT meta, text, ts_rank(to_tsvector(coalesce(text, '')), plainto_tsquery(%s)) AS score + FROM {self.table_name} + WHERE to_tsvector(text) @@ plainto_tsquery(%s) + ORDER BY score DESC + LIMIT {top_k}""", + # f"'{query}'" is required in order to account for whitespace in query + (f"'{query}'", f"'{query}'"), + ) + + docs = [] + + for record in cur: + metadata, text, score = record + metadata["score"] = score + docs.append(Document(page_content=text, metadata=metadata)) + + return docs + + def delete(self) -> None: + with self._get_cursor() as cur: + cur.execute(f"DROP TABLE IF EXISTS {self.table_name}") + + def _create_collection(self, dimension: int): + cache_key = f"vector_indexing_{self._collection_name}" + lock_name = f"{cache_key}_lock" + with redis_client.lock(lock_name, timeout=20): + collection_exist_cache_key = f"vector_indexing_{self._collection_name}" + if redis_client.get(collection_exist_cache_key): + return + + with self._get_cursor() as cur: + cur.execute(SQL_CREATE_TABLE.format(table_name=self.table_name, dimension=dimension)) + # Vastbase 支持的向量维度取值范围为 [1,16000] + if dimension <= 16000: + cur.execute(SQL_CREATE_INDEX.format(table_name=self.table_name)) + redis_client.set(collection_exist_cache_key, 1, ex=3600) + + +class VastbaseVectorFactory(AbstractVectorFactory): + def init_vector(self, dataset: Dataset, attributes: list, embeddings: Embeddings) -> VastbaseVector: + if dataset.index_struct_dict: + class_prefix: str = dataset.index_struct_dict["vector_store"]["class_prefix"] + collection_name = class_prefix + else: + dataset_id = dataset.id + collection_name = Dataset.gen_collection_name_by_id(dataset_id) + dataset.index_struct = json.dumps(self.gen_index_struct_dict(VectorType.VASTBASE, collection_name)) + + return VastbaseVector( + collection_name=collection_name, + config=VastbaseVectorConfig( + host=dify_config.VASTBASE_HOST or "localhost", + port=dify_config.VASTBASE_PORT, + user=dify_config.VASTBASE_USER or "dify", + password=dify_config.VASTBASE_PASSWORD or "", + database=dify_config.VASTBASE_DATABASE or "dify", + min_connection=dify_config.VASTBASE_MIN_CONNECTION, + max_connection=dify_config.VASTBASE_MAX_CONNECTION, + ), + ) diff --git a/api/core/rag/datasource/vdb/vector_factory.py b/api/core/rag/datasource/vdb/vector_factory.py index 05158cc7ca..66e002312a 100644 --- a/api/core/rag/datasource/vdb/vector_factory.py +++ b/api/core/rag/datasource/vdb/vector_factory.py @@ -74,6 +74,10 @@ class Vector: from core.rag.datasource.vdb.pgvector.pgvector import PGVectorFactory return PGVectorFactory + case VectorType.VASTBASE: + from core.rag.datasource.vdb.pyvastbase.vastbase_vector import VastbaseVectorFactory + + return VastbaseVectorFactory case VectorType.PGVECTO_RS: from core.rag.datasource.vdb.pgvecto_rs.pgvecto_rs import PGVectoRSFactory diff --git a/api/core/rag/datasource/vdb/vector_type.py b/api/core/rag/datasource/vdb/vector_type.py index 0421be3458..7a81565e37 100644 --- a/api/core/rag/datasource/vdb/vector_type.py +++ b/api/core/rag/datasource/vdb/vector_type.py @@ -7,7 +7,9 @@ class VectorType(StrEnum): MILVUS = "milvus" MYSCALE = "myscale" PGVECTOR = "pgvector" + VASTBASE = "vastbase" PGVECTO_RS = "pgvecto-rs" + QDRANT = "qdrant" RELYT = "relyt" TIDB_VECTOR = "tidb_vector" diff --git a/api/core/tools/builtin_tool/provider.py b/api/core/tools/builtin_tool/provider.py index 4f733f0ea1..cf75bd3d7e 100644 --- a/api/core/tools/builtin_tool/provider.py +++ b/api/core/tools/builtin_tool/provider.py @@ -35,8 +35,9 @@ class BuiltinToolProviderController(ToolProviderController): provider_yaml["credentials_for_provider"][credential_name]["name"] = credential_name credentials_schema = [] - for credential in provider_yaml.get("credentials_for_provider", {}).values(): - credentials_schema.append(credential) + for credential in provider_yaml.get("credentials_for_provider", {}): + credential_dict = provider_yaml.get("credentials_for_provider", {}).get(credential, {}) + credentials_schema.append(credential_dict) super().__init__( entity=ToolProviderEntity( diff --git a/api/fields/conversation_variable_fields.py b/api/fields/conversation_variable_fields.py index c6385efb5a..3aa3838def 100644 --- a/api/fields/conversation_variable_fields.py +++ b/api/fields/conversation_variable_fields.py @@ -19,3 +19,9 @@ paginated_conversation_variable_fields = { "has_more": fields.Boolean, "data": fields.List(fields.Nested(conversation_variable_fields), attribute="data"), } + +conversation_variable_infinite_scroll_pagination_fields = { + "limit": fields.Integer, + "has_more": fields.Boolean, + "data": fields.List(fields.Nested(conversation_variable_fields)), +} diff --git a/api/models/model.py b/api/models/model.py index 07bb217636..ed189f5b05 100644 --- a/api/models/model.py +++ b/api/models/model.py @@ -3,8 +3,8 @@ import re import uuid from collections.abc import Mapping from datetime import datetime -from enum import Enum -from typing import TYPE_CHECKING, Optional +from enum import Enum, StrEnum +from typing import TYPE_CHECKING, Any, Literal, Optional, cast from core.plugin.entities.plugin import GenericProviderID from core.tools.entities.tool_entities import ToolProviderType @@ -14,9 +14,6 @@ from services.plugin.plugin_service import PluginService if TYPE_CHECKING: from models.workflow import Workflow -from enum import StrEnum -from typing import TYPE_CHECKING, Any, Literal, cast - import sqlalchemy as sa from flask import request from flask_login import UserMixin # type: ignore diff --git a/api/models/workflow.py b/api/models/workflow.py index 5a67fa47a8..da60617de5 100644 --- a/api/models/workflow.py +++ b/api/models/workflow.py @@ -1,14 +1,12 @@ import json from collections.abc import Mapping, Sequence from datetime import UTC, datetime -from enum import Enum +from enum import Enum, StrEnum from typing import TYPE_CHECKING, Any, Optional, Self, Union from uuid import uuid4 if TYPE_CHECKING: from models.model import AppMode -from enum import StrEnum -from typing import TYPE_CHECKING import sqlalchemy as sa from sqlalchemy import Index, PrimaryKeyConstraint, func diff --git a/api/pyproject.toml b/api/pyproject.toml index 4992178423..6f526bc705 100644 --- a/api/pyproject.toml +++ b/api/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "dify-api" -version = "1.2.0" +version = "1.3.0" requires-python = ">=3.11,<3.13" dependencies = [ diff --git a/api/services/app_dsl_service.py b/api/services/app_dsl_service.py index 2e2b729021..a2775fe6ad 100644 --- a/api/services/app_dsl_service.py +++ b/api/services/app_dsl_service.py @@ -40,7 +40,7 @@ IMPORT_INFO_REDIS_KEY_PREFIX = "app_import_info:" CHECK_DEPENDENCIES_REDIS_KEY_PREFIX = "app_check_dependencies:" IMPORT_INFO_REDIS_EXPIRY = 10 * 60 # 10 minutes DSL_MAX_SIZE = 10 * 1024 * 1024 # 10MB -CURRENT_DSL_VERSION = "0.1.5" +CURRENT_DSL_VERSION = "0.2.0" class ImportMode(StrEnum): @@ -77,13 +77,19 @@ def _check_version_compatibility(imported_version: str) -> ImportStatus: except version.InvalidVersion: return ImportStatus.FAILED - # Compare major version and minor version - if current_ver.major != imported_ver.major or current_ver.minor != imported_ver.minor: + # If imported version is newer than current, always return PENDING + if imported_ver > current_ver: return ImportStatus.PENDING - if current_ver.micro != imported_ver.micro: + # If imported version is older than current's major, return PENDING + if imported_ver.major < current_ver.major: + return ImportStatus.PENDING + + # If imported version is older than current's minor, return COMPLETED_WITH_WARNINGS + if imported_ver.minor < current_ver.minor: return ImportStatus.COMPLETED_WITH_WARNINGS + # If imported version equals or is older than current's micro, return COMPLETED return ImportStatus.COMPLETED diff --git a/api/services/conversation_service.py b/api/services/conversation_service.py index 6485cbf37d..afdaa49465 100644 --- a/api/services/conversation_service.py +++ b/api/services/conversation_service.py @@ -9,9 +9,14 @@ from core.app.entities.app_invoke_entities import InvokeFrom from core.llm_generator.llm_generator import LLMGenerator from extensions.ext_database import db from libs.infinite_scroll_pagination import InfiniteScrollPagination +from models import ConversationVariable from models.account import Account from models.model import App, Conversation, EndUser, Message -from services.errors.conversation import ConversationNotExistsError, LastConversationNotExistsError +from services.errors.conversation import ( + ConversationNotExistsError, + ConversationVariableNotExistsError, + LastConversationNotExistsError, +) from services.errors.message import MessageNotExistsError @@ -166,3 +171,50 @@ class ConversationService: conversation.is_deleted = True conversation.updated_at = datetime.now(UTC).replace(tzinfo=None) db.session.commit() + + @classmethod + def get_conversational_variable( + cls, + app_model: App, + conversation_id: str, + user: Optional[Union[Account, EndUser]], + limit: int, + last_id: Optional[str], + ) -> InfiniteScrollPagination: + conversation = cls.get_conversation(app_model, conversation_id, user) + + stmt = ( + select(ConversationVariable) + .where(ConversationVariable.app_id == app_model.id) + .where(ConversationVariable.conversation_id == conversation.id) + .order_by(ConversationVariable.created_at) + ) + + with Session(db.engine) as session: + if last_id: + last_variable = session.scalar(stmt.where(ConversationVariable.id == last_id)) + if not last_variable: + raise ConversationVariableNotExistsError() + + # Filter for variables created after the last_id + stmt = stmt.where(ConversationVariable.created_at > last_variable.created_at) + + # Apply limit to query + query_stmt = stmt.limit(limit) # Get one extra to check if there are more + rows = session.scalars(query_stmt).all() + + has_more = False + if len(rows) > limit: + has_more = True + rows = rows[:limit] # Remove the extra item + + variables = [ + { + "created_at": row.created_at, + "updated_at": row.updated_at, + **row.to_variable().model_dump(), + } + for row in rows + ] + + return InfiniteScrollPagination(variables, limit, has_more) diff --git a/api/services/errors/conversation.py b/api/services/errors/conversation.py index 139dd9a70a..f8051e3417 100644 --- a/api/services/errors/conversation.py +++ b/api/services/errors/conversation.py @@ -11,3 +11,7 @@ class ConversationNotExistsError(BaseServiceError): class ConversationCompletedError(Exception): pass + + +class ConversationVariableNotExistsError(BaseServiceError): + pass diff --git a/api/tests/integration_tests/vdb/pyvastbase/__init__.py b/api/tests/integration_tests/vdb/pyvastbase/__init__.py new file mode 100644 index 0000000000..e69de29bb2 diff --git a/api/tests/integration_tests/vdb/pyvastbase/test_vastbase_vector.py b/api/tests/integration_tests/vdb/pyvastbase/test_vastbase_vector.py new file mode 100644 index 0000000000..3d7873442b --- /dev/null +++ b/api/tests/integration_tests/vdb/pyvastbase/test_vastbase_vector.py @@ -0,0 +1,27 @@ +from core.rag.datasource.vdb.pyvastbase.vastbase_vector import VastbaseVector, VastbaseVectorConfig +from tests.integration_tests.vdb.test_vector_store import ( + AbstractVectorTest, + get_example_text, + setup_mock_redis, +) + + +class VastbaseVectorTest(AbstractVectorTest): + def __init__(self): + super().__init__() + self.vector = VastbaseVector( + collection_name=self.collection_name, + config=VastbaseVectorConfig( + host="localhost", + port=5434, + user="dify", + password="Difyai123456", + database="dify", + min_connection=1, + max_connection=5, + ), + ) + + +def test_vastbase_vector(setup_mock_redis): + VastbaseVectorTest().run_all_tests() diff --git a/api/uv.lock b/api/uv.lock index 6c8699dd7c..0e2dd9c92a 100644 --- a/api/uv.lock +++ b/api/uv.lock @@ -1148,7 +1148,7 @@ wheels = [ [[package]] name = "dify-api" -version = "1.2.0" +version = "1.3.0" source = { virtual = "." } dependencies = [ { name = "authlib" }, diff --git a/docker/.env.example b/docker/.env.example index 0b80dccb37..83d975cec5 100644 --- a/docker/.env.example +++ b/docker/.env.example @@ -406,6 +406,7 @@ QDRANT_GRPC_PORT=6334 # Milvus configuration. Only available when VECTOR_STORE is `milvus`. # The milvus uri. MILVUS_URI=http://host.docker.internal:19530 +MILVUS_DATABASE= MILVUS_TOKEN= MILVUS_USER= MILVUS_PASSWORD= @@ -441,6 +442,15 @@ PGVECTOR_MAX_CONNECTION=5 PGVECTOR_PG_BIGM=false PGVECTOR_PG_BIGM_VERSION=1.2-20240606 +# vastbase configurations, only available when VECTOR_STORE is `vastbase` +VASTBASE_HOST=vastbase +VASTBASE_PORT=5432 +VASTBASE_USER=dify +VASTBASE_PASSWORD=Difyai123456 +VASTBASE_DATABASE=dify +VASTBASE_MIN_CONNECTION=1 +VASTBASE_MAX_CONNECTION=5 + # pgvecto-rs configurations, only available when VECTOR_STORE is `pgvecto-rs` PGVECTO_RS_HOST=pgvecto-rs PGVECTO_RS_PORT=5432 @@ -553,6 +563,7 @@ VIKINGDB_SOCKET_TIMEOUT=30 LINDORM_URL=http://lindorm:30070 LINDORM_USERNAME=lindorm LINDORM_PASSWORD=lindorm +LINDORM_QUERY_TIMEOUT=1 # OceanBase Vector configuration, only available when VECTOR_STORE is `oceanbase` OCEANBASE_VECTOR_HOST=oceanbase diff --git a/docker/docker-compose-template.yaml b/docker/docker-compose-template.yaml index 377ff9c117..9ab1304492 100644 --- a/docker/docker-compose-template.yaml +++ b/docker/docker-compose-template.yaml @@ -2,7 +2,7 @@ x-shared-env: &shared-api-worker-env services: # API service api: - image: langgenius/dify-api:1.2.0 + image: langgenius/dify-api:1.3.0 restart: always environment: # Use the shared environment variables. @@ -31,7 +31,7 @@ services: # worker service # The Celery worker for processing the queue. worker: - image: langgenius/dify-api:1.2.0 + image: langgenius/dify-api:1.3.0 restart: always environment: # Use the shared environment variables. @@ -57,7 +57,7 @@ services: # Frontend web application. web: - image: langgenius/dify-web:1.2.0 + image: langgenius/dify-web:1.3.0 restart: always environment: CONSOLE_API_URL: ${CONSOLE_API_URL:-} @@ -142,7 +142,7 @@ services: # plugin daemon plugin_daemon: - image: langgenius/dify-plugin-daemon:0.0.7-local + image: langgenius/dify-plugin-daemon:0.0.9-local restart: always environment: # Use the shared environment variables. @@ -363,6 +363,30 @@ services: timeout: 3s retries: 30 + # get image from https://www.vastdata.com.cn/ + vastbase: + image: vastdata/vastbase-vector + profiles: + - vastbase + restart: always + environment: + - VB_DBCOMPATIBILITY=PG + - VB_DB=dify + - VB_USERNAME=dify + - VB_PASSWORD=Difyai123456 + ports: + - '5434:5432' + volumes: + - ./vastbase/lic:/home/vastbase/vastbase/lic + - ./vastbase/data:/home/vastbase/data + - ./vastbase/backup:/home/vastbase/backup + - ./vastbase/backup_log:/home/vastbase/backup_log + healthcheck: + test: [ 'CMD', 'pg_isready' ] + interval: 1s + timeout: 3s + retries: 30 + # pgvecto-rs vector store pgvecto-rs: image: tensorchord/pgvecto-rs:pg16-v0.3.0 diff --git a/docker/docker-compose.middleware.yaml b/docker/docker-compose.middleware.yaml index 1702a5395f..01c7573a95 100644 --- a/docker/docker-compose.middleware.yaml +++ b/docker/docker-compose.middleware.yaml @@ -71,7 +71,7 @@ services: # plugin daemon plugin_daemon: - image: langgenius/dify-plugin-daemon:0.0.7-local + image: langgenius/dify-plugin-daemon:0.0.9-local restart: always env_file: - ./middleware.env diff --git a/docker/docker-compose.yaml b/docker/docker-compose.yaml index 81fa651ed9..8edcd497c6 100644 --- a/docker/docker-compose.yaml +++ b/docker/docker-compose.yaml @@ -138,6 +138,7 @@ x-shared-env: &shared-api-worker-env QDRANT_GRPC_ENABLED: ${QDRANT_GRPC_ENABLED:-false} QDRANT_GRPC_PORT: ${QDRANT_GRPC_PORT:-6334} MILVUS_URI: ${MILVUS_URI:-http://host.docker.internal:19530} + MILVUS_DATABASE: ${MILVUS_DATABASE:-} MILVUS_TOKEN: ${MILVUS_TOKEN:-} MILVUS_USER: ${MILVUS_USER:-} MILVUS_PASSWORD: ${MILVUS_PASSWORD:-} @@ -163,6 +164,13 @@ x-shared-env: &shared-api-worker-env PGVECTOR_MAX_CONNECTION: ${PGVECTOR_MAX_CONNECTION:-5} PGVECTOR_PG_BIGM: ${PGVECTOR_PG_BIGM:-false} PGVECTOR_PG_BIGM_VERSION: ${PGVECTOR_PG_BIGM_VERSION:-1.2-20240606} + VASTBASE_HOST: ${VASTBASE_HOST:-vastbase} + VASTBASE_PORT: ${VASTBASE_PORT:-5432} + VASTBASE_USER: ${VASTBASE_USER:-dify} + VASTBASE_PASSWORD: ${VASTBASE_PASSWORD:-Difyai123456} + VASTBASE_DATABASE: ${VASTBASE_DATABASE:-dify} + VASTBASE_MIN_CONNECTION: ${VASTBASE_MIN_CONNECTION:-1} + VASTBASE_MAX_CONNECTION: ${VASTBASE_MAX_CONNECTION:-5} PGVECTO_RS_HOST: ${PGVECTO_RS_HOST:-pgvecto-rs} PGVECTO_RS_PORT: ${PGVECTO_RS_PORT:-5432} PGVECTO_RS_USER: ${PGVECTO_RS_USER:-postgres} @@ -250,6 +258,7 @@ x-shared-env: &shared-api-worker-env LINDORM_URL: ${LINDORM_URL:-http://lindorm:30070} LINDORM_USERNAME: ${LINDORM_USERNAME:-lindorm} LINDORM_PASSWORD: ${LINDORM_PASSWORD:-lindorm} + LINDORM_QUERY_TIMEOUT: ${LINDORM_QUERY_TIMEOUT:-1} OCEANBASE_VECTOR_HOST: ${OCEANBASE_VECTOR_HOST:-oceanbase} OCEANBASE_VECTOR_PORT: ${OCEANBASE_VECTOR_PORT:-2881} OCEANBASE_VECTOR_USER: ${OCEANBASE_VECTOR_USER:-root@test} @@ -479,7 +488,7 @@ x-shared-env: &shared-api-worker-env services: # API service api: - image: langgenius/dify-api:1.2.0 + image: langgenius/dify-api:1.3.0 restart: always environment: # Use the shared environment variables. @@ -508,7 +517,7 @@ services: # worker service # The Celery worker for processing the queue. worker: - image: langgenius/dify-api:1.2.0 + image: langgenius/dify-api:1.3.0 restart: always environment: # Use the shared environment variables. @@ -534,7 +543,7 @@ services: # Frontend web application. web: - image: langgenius/dify-web:1.2.0 + image: langgenius/dify-web:1.3.0 restart: always environment: CONSOLE_API_URL: ${CONSOLE_API_URL:-} @@ -619,7 +628,7 @@ services: # plugin daemon plugin_daemon: - image: langgenius/dify-plugin-daemon:0.0.7-local + image: langgenius/dify-plugin-daemon:0.0.9-local restart: always environment: # Use the shared environment variables. @@ -840,6 +849,30 @@ services: timeout: 3s retries: 30 + # get image from https://www.vastdata.com.cn/ + vastbase: + image: vastdata/vastbase-vector + profiles: + - vastbase + restart: always + environment: + - VB_DBCOMPATIBILITY=PG + - VB_DB=dify + - VB_USERNAME=dify + - VB_PASSWORD=Difyai123456 + ports: + - '5434:5432' + volumes: + - ./vastbase/lic:/home/vastbase/vastbase/lic + - ./vastbase/data:/home/vastbase/data + - ./vastbase/backup:/home/vastbase/backup + - ./vastbase/backup_log:/home/vastbase/backup_log + healthcheck: + test: [ 'CMD', 'pg_isready' ] + interval: 1s + timeout: 3s + retries: 30 + # pgvecto-rs vector store pgvecto-rs: image: tensorchord/pgvecto-rs:pg16-v0.3.0 diff --git a/sdks/php-client/.gitignore b/sdks/php-client/.gitignore new file mode 100644 index 0000000000..61ead86667 --- /dev/null +++ b/sdks/php-client/.gitignore @@ -0,0 +1 @@ +/vendor diff --git a/sdks/php-client/README.md b/sdks/php-client/README.md index b0a435bbaf..812980d834 100644 --- a/sdks/php-client/README.md +++ b/sdks/php-client/README.md @@ -9,6 +9,21 @@ This is the PHP SDK for the Dify API, which allows you to easily integrate Dify ## Usage +If you want to try the example, you can run `composer install` in this directory. + +In exist project, copy the `dify-client.php` to you project, and merge the following to your `composer.json` file, then run `composer install && composer dump-autoload` to install. Guzzle does not require 7.9, other versions have not been tested, but you can try. + +```json +{ + "require": { + "guzzlehttp/guzzle": "^7.9" + }, + "autoload": { + "files": ["path/to/dify-client.php"] + } +} +``` + After installing the SDK, you can use it in your project like this: ```php @@ -16,10 +31,6 @@ After installing the SDK, you can use it in your project like this: require 'vendor/autoload.php'; -use YourVendorName\DifyPHP\DifyClient; -use YourVendorName\DifyPHP\CompletionClient; -use YourVendorName\DifyPHP\ChatClient; - $apiKey = 'your-api-key-here'; $difyClient = new DifyClient($apiKey); diff --git a/sdks/php-client/composer.json b/sdks/php-client/composer.json new file mode 100644 index 0000000000..6e49e44075 --- /dev/null +++ b/sdks/php-client/composer.json @@ -0,0 +1,9 @@ +{ + "require": { + "php": ">=7.2", + "guzzlehttp/guzzle": "^7.9" + }, + "autoload": { + "files": ["dify-client.php"] + } +} diff --git a/sdks/php-client/composer.lock b/sdks/php-client/composer.lock new file mode 100644 index 0000000000..aa07dc03ef --- /dev/null +++ b/sdks/php-client/composer.lock @@ -0,0 +1,663 @@ +{ + "_readme": [ + "This file locks the dependencies of your project to a known state", + "Read more about it at https://getcomposer.org/doc/01-basic-usage.md#installing-dependencies", + "This file is @generated automatically" + ], + "content-hash": "7827c548fdcc7e87cb0ae341dd2c6b1b", + "packages": [ + { + "name": "guzzlehttp/guzzle", + "version": "7.9.2", + "source": { + "type": "git", + "url": "https://github.com/guzzle/guzzle.git", + "reference": "d281ed313b989f213357e3be1a179f02196ac99b" + }, + "dist": { + "type": "zip", + "url": "https://api.github.com/repos/guzzle/guzzle/zipball/d281ed313b989f213357e3be1a179f02196ac99b", + "reference": "d281ed313b989f213357e3be1a179f02196ac99b", + "shasum": "", + "mirrors": [ + { + "url": "https://mirrors.aliyun.com/composer/dists/%package%/%reference%.%type%", + "preferred": true + } + ] + }, + "require": { + "ext-json": "*", + "guzzlehttp/promises": "^1.5.3 || ^2.0.3", + "guzzlehttp/psr7": "^2.7.0", + "php": "^7.2.5 || ^8.0", + "psr/http-client": "^1.0", + "symfony/deprecation-contracts": "^2.2 || ^3.0" + }, + "provide": { + "psr/http-client-implementation": "1.0" + }, + "require-dev": { + "bamarni/composer-bin-plugin": "^1.8.2", + "ext-curl": "*", + "guzzle/client-integration-tests": "3.0.2", + "php-http/message-factory": "^1.1", + "phpunit/phpunit": "^8.5.39 || ^9.6.20", + "psr/log": "^1.1 || ^2.0 || ^3.0" + }, + "suggest": { + "ext-curl": "Required for CURL handler support", + "ext-intl": "Required for Internationalized Domain Name (IDN) support", + "psr/log": "Required for using the Log middleware" + }, + "type": "library", + "extra": { + "bamarni-bin": { + "bin-links": true, + "forward-command": false + } + }, + "autoload": { + "files": [ + "src/functions_include.php" + ], + "psr-4": { + "GuzzleHttp\\": "src/" + } + }, + "notification-url": "https://packagist.org/downloads/", + "license": [ + "MIT" + ], + "authors": [ + { + "name": "Graham Campbell", + "email": "hello@gjcampbell.co.uk", + "homepage": "https://github.com/GrahamCampbell" + }, + { + "name": "Michael Dowling", + "email": "mtdowling@gmail.com", + "homepage": "https://github.com/mtdowling" + }, + { + "name": "Jeremy Lindblom", + "email": "jeremeamia@gmail.com", + "homepage": "https://github.com/jeremeamia" + }, + { + "name": "George Mponos", + "email": "gmponos@gmail.com", + "homepage": "https://github.com/gmponos" + }, + { + "name": "Tobias Nyholm", + "email": "tobias.nyholm@gmail.com", + "homepage": "https://github.com/Nyholm" + }, + { + "name": "Márk Sági-Kazár", + "email": "mark.sagikazar@gmail.com", + "homepage": "https://github.com/sagikazarmark" + }, + { + "name": "Tobias Schultze", + "email": "webmaster@tubo-world.de", + "homepage": "https://github.com/Tobion" + } + ], + "description": "Guzzle is a PHP HTTP client library", + "keywords": [ + "client", + "curl", + "framework", + "http", + "http client", + "psr-18", + "psr-7", + "rest", + "web service" + ], + "support": { + "issues": "https://github.com/guzzle/guzzle/issues", + "source": "https://github.com/guzzle/guzzle/tree/7.9.2" + }, + "funding": [ + { + "url": "https://github.com/GrahamCampbell", + "type": "github" + }, + { + "url": "https://github.com/Nyholm", + "type": "github" + }, + { + "url": "https://tidelift.com/funding/github/packagist/guzzlehttp/guzzle", + "type": "tidelift" + } + ], + "time": "2024-07-24T11:22:20+00:00" + }, + { + "name": "guzzlehttp/promises", + "version": "2.2.0", + "source": { + "type": "git", + "url": "https://github.com/guzzle/promises.git", + "reference": "7c69f28996b0a6920945dd20b3857e499d9ca96c" + }, + "dist": { + "type": "zip", + "url": "https://api.github.com/repos/guzzle/promises/zipball/7c69f28996b0a6920945dd20b3857e499d9ca96c", + "reference": "7c69f28996b0a6920945dd20b3857e499d9ca96c", + "shasum": "", + "mirrors": [ + { + "url": "https://mirrors.aliyun.com/composer/dists/%package%/%reference%.%type%", + "preferred": true + } + ] + }, + "require": { + "php": "^7.2.5 || ^8.0" + }, + "require-dev": { + "bamarni/composer-bin-plugin": "^1.8.2", + "phpunit/phpunit": "^8.5.39 || ^9.6.20" + }, + "type": "library", + "extra": { + "bamarni-bin": { + "bin-links": true, + "forward-command": false + } + }, + "autoload": { + "psr-4": { + "GuzzleHttp\\Promise\\": "src/" + } + }, + "notification-url": "https://packagist.org/downloads/", + "license": [ + "MIT" + ], + "authors": [ + { + "name": "Graham Campbell", + "email": "hello@gjcampbell.co.uk", + "homepage": "https://github.com/GrahamCampbell" + }, + { + "name": "Michael Dowling", + "email": "mtdowling@gmail.com", + "homepage": "https://github.com/mtdowling" + }, + { + "name": "Tobias Nyholm", + "email": "tobias.nyholm@gmail.com", + "homepage": "https://github.com/Nyholm" + }, + { + "name": "Tobias Schultze", + "email": "webmaster@tubo-world.de", + "homepage": "https://github.com/Tobion" + } + ], + "description": "Guzzle promises library", + "keywords": [ + "promise" + ], + "support": { + "issues": "https://github.com/guzzle/promises/issues", + "source": "https://github.com/guzzle/promises/tree/2.2.0" + }, + "funding": [ + { + "url": "https://github.com/GrahamCampbell", + "type": "github" + }, + { + "url": "https://github.com/Nyholm", + "type": "github" + }, + { + "url": "https://tidelift.com/funding/github/packagist/guzzlehttp/promises", + "type": "tidelift" + } + ], + "time": "2025-03-27T13:27:01+00:00" + }, + { + "name": "guzzlehttp/psr7", + "version": "2.7.1", + "source": { + "type": "git", + "url": "https://github.com/guzzle/psr7.git", + "reference": "c2270caaabe631b3b44c85f99e5a04bbb8060d16" + }, + "dist": { + "type": "zip", + "url": "https://api.github.com/repos/guzzle/psr7/zipball/c2270caaabe631b3b44c85f99e5a04bbb8060d16", + "reference": "c2270caaabe631b3b44c85f99e5a04bbb8060d16", + "shasum": "", + "mirrors": [ + { + "url": "https://mirrors.aliyun.com/composer/dists/%package%/%reference%.%type%", + "preferred": true + } + ] + }, + "require": { + "php": "^7.2.5 || ^8.0", + "psr/http-factory": "^1.0", + "psr/http-message": "^1.1 || ^2.0", + "ralouphie/getallheaders": "^3.0" + }, + "provide": { + "psr/http-factory-implementation": "1.0", + "psr/http-message-implementation": "1.0" + }, + "require-dev": { + "bamarni/composer-bin-plugin": "^1.8.2", + "http-interop/http-factory-tests": "0.9.0", + "phpunit/phpunit": "^8.5.39 || ^9.6.20" + }, + "suggest": { + "laminas/laminas-httphandlerrunner": "Emit PSR-7 responses" + }, + "type": "library", + "extra": { + "bamarni-bin": { + "bin-links": true, + "forward-command": false + } + }, + "autoload": { + "psr-4": { + "GuzzleHttp\\Psr7\\": "src/" + } + }, + "notification-url": "https://packagist.org/downloads/", + "license": [ + "MIT" + ], + "authors": [ + { + "name": "Graham Campbell", + "email": "hello@gjcampbell.co.uk", + "homepage": "https://github.com/GrahamCampbell" + }, + { + "name": "Michael Dowling", + "email": "mtdowling@gmail.com", + "homepage": "https://github.com/mtdowling" + }, + { + "name": "George Mponos", + "email": "gmponos@gmail.com", + "homepage": "https://github.com/gmponos" + }, + { + "name": "Tobias Nyholm", + "email": "tobias.nyholm@gmail.com", + "homepage": "https://github.com/Nyholm" + }, + { + "name": "Márk Sági-Kazár", + "email": "mark.sagikazar@gmail.com", + "homepage": "https://github.com/sagikazarmark" + }, + { + "name": "Tobias Schultze", + "email": "webmaster@tubo-world.de", + "homepage": "https://github.com/Tobion" + }, + { + "name": "Márk Sági-Kazár", + "email": "mark.sagikazar@gmail.com", + "homepage": "https://sagikazarmark.hu" + } + ], + "description": "PSR-7 message implementation that also provides common utility methods", + "keywords": [ + "http", + "message", + "psr-7", + "request", + "response", + "stream", + "uri", + "url" + ], + "support": { + "issues": "https://github.com/guzzle/psr7/issues", + "source": "https://github.com/guzzle/psr7/tree/2.7.1" + }, + "funding": [ + { + "url": "https://github.com/GrahamCampbell", + "type": "github" + }, + { + "url": "https://github.com/Nyholm", + "type": "github" + }, + { + "url": "https://tidelift.com/funding/github/packagist/guzzlehttp/psr7", + "type": "tidelift" + } + ], + "time": "2025-03-27T12:30:47+00:00" + }, + { + "name": "psr/http-client", + "version": "1.0.3", + "source": { + "type": "git", + "url": "https://github.com/php-fig/http-client.git", + "reference": "bb5906edc1c324c9a05aa0873d40117941e5fa90" + }, + "dist": { + "type": "zip", + "url": "https://api.github.com/repos/php-fig/http-client/zipball/bb5906edc1c324c9a05aa0873d40117941e5fa90", + "reference": "bb5906edc1c324c9a05aa0873d40117941e5fa90", + "shasum": "", + "mirrors": [ + { + "url": "https://mirrors.aliyun.com/composer/dists/%package%/%reference%.%type%", + "preferred": true + } + ] + }, + "require": { + "php": "^7.0 || ^8.0", + "psr/http-message": "^1.0 || ^2.0" + }, + "type": "library", + "extra": { + "branch-alias": { + "dev-master": "1.0.x-dev" + } + }, + "autoload": { + "psr-4": { + "Psr\\Http\\Client\\": "src/" + } + }, + "notification-url": "https://packagist.org/downloads/", + "license": [ + "MIT" + ], + "authors": [ + { + "name": "PHP-FIG", + "homepage": "https://www.php-fig.org/" + } + ], + "description": "Common interface for HTTP clients", + "homepage": "https://github.com/php-fig/http-client", + "keywords": [ + "http", + "http-client", + "psr", + "psr-18" + ], + "support": { + "source": "https://github.com/php-fig/http-client" + }, + "time": "2023-09-23T14:17:50+00:00" + }, + { + "name": "psr/http-factory", + "version": "1.0.2", + "source": { + "type": "git", + "url": "https://github.com/php-fig/http-factory.git", + "reference": "e616d01114759c4c489f93b099585439f795fe35" + }, + "dist": { + "type": "zip", + "url": "https://api.github.com/repos/php-fig/http-factory/zipball/e616d01114759c4c489f93b099585439f795fe35", + "reference": "e616d01114759c4c489f93b099585439f795fe35", + "shasum": "", + "mirrors": [ + { + "url": "https://mirrors.aliyun.com/composer/dists/%package%/%reference%.%type%", + "preferred": true + } + ] + }, + "require": { + "php": ">=7.0.0", + "psr/http-message": "^1.0 || ^2.0" + }, + "type": "library", + "extra": { + "branch-alias": { + "dev-master": "1.0.x-dev" + } + }, + "autoload": { + "psr-4": { + "Psr\\Http\\Message\\": "src/" + } + }, + "notification-url": "https://packagist.org/downloads/", + "license": [ + "MIT" + ], + "authors": [ + { + "name": "PHP-FIG", + "homepage": "https://www.php-fig.org/" + } + ], + "description": "Common interfaces for PSR-7 HTTP message factories", + "keywords": [ + "factory", + "http", + "message", + "psr", + "psr-17", + "psr-7", + "request", + "response" + ], + "support": { + "source": "https://github.com/php-fig/http-factory/tree/1.0.2" + }, + "time": "2023-04-10T20:10:41+00:00" + }, + { + "name": "psr/http-message", + "version": "2.0", + "source": { + "type": "git", + "url": "https://github.com/php-fig/http-message.git", + "reference": "402d35bcb92c70c026d1a6a9883f06b2ead23d71" + }, + "dist": { + "type": "zip", + "url": "https://api.github.com/repos/php-fig/http-message/zipball/402d35bcb92c70c026d1a6a9883f06b2ead23d71", + "reference": "402d35bcb92c70c026d1a6a9883f06b2ead23d71", + "shasum": "", + "mirrors": [ + { + "url": "https://mirrors.aliyun.com/composer/dists/%package%/%reference%.%type%", + "preferred": true + } + ] + }, + "require": { + "php": "^7.2 || ^8.0" + }, + "type": "library", + "extra": { + "branch-alias": { + "dev-master": "2.0.x-dev" + } + }, + "autoload": { + "psr-4": { + "Psr\\Http\\Message\\": "src/" + } + }, + "notification-url": "https://packagist.org/downloads/", + "license": [ + "MIT" + ], + "authors": [ + { + "name": "PHP-FIG", + "homepage": "https://www.php-fig.org/" + } + ], + "description": "Common interface for HTTP messages", + "homepage": "https://github.com/php-fig/http-message", + "keywords": [ + "http", + "http-message", + "psr", + "psr-7", + "request", + "response" + ], + "support": { + "source": "https://github.com/php-fig/http-message/tree/2.0" + }, + "time": "2023-04-04T09:54:51+00:00" + }, + { + "name": "ralouphie/getallheaders", + "version": "3.0.3", + "source": { + "type": "git", + "url": "https://github.com/ralouphie/getallheaders.git", + "reference": "120b605dfeb996808c31b6477290a714d356e822" + }, + "dist": { + "type": "zip", + "url": "https://api.github.com/repos/ralouphie/getallheaders/zipball/120b605dfeb996808c31b6477290a714d356e822", + "reference": "120b605dfeb996808c31b6477290a714d356e822", + "shasum": "", + "mirrors": [ + { + "url": "https://mirrors.aliyun.com/composer/dists/%package%/%reference%.%type%", + "preferred": true + } + ] + }, + "require": { + "php": ">=5.6" + }, + "require-dev": { + "php-coveralls/php-coveralls": "^2.1", + "phpunit/phpunit": "^5 || ^6.5" + }, + "type": "library", + "autoload": { + "files": [ + "src/getallheaders.php" + ] + }, + "notification-url": "https://packagist.org/downloads/", + "license": [ + "MIT" + ], + "authors": [ + { + "name": "Ralph Khattar", + "email": "ralph.khattar@gmail.com" + } + ], + "description": "A polyfill for getallheaders.", + "support": { + "issues": "https://github.com/ralouphie/getallheaders/issues", + "source": "https://github.com/ralouphie/getallheaders/tree/develop" + }, + "time": "2019-03-08T08:55:37+00:00" + }, + { + "name": "symfony/deprecation-contracts", + "version": "v3.5.1", + "source": { + "type": "git", + "url": "https://github.com/symfony/deprecation-contracts.git", + "reference": "74c71c939a79f7d5bf3c1ce9f5ea37ba0114c6f6" + }, + "dist": { + "type": "zip", + "url": "https://api.github.com/repos/symfony/deprecation-contracts/zipball/74c71c939a79f7d5bf3c1ce9f5ea37ba0114c6f6", + "reference": "74c71c939a79f7d5bf3c1ce9f5ea37ba0114c6f6", + "shasum": "", + "mirrors": [ + { + "url": "https://mirrors.aliyun.com/composer/dists/%package%/%reference%.%type%", + "preferred": true + } + ] + }, + "require": { + "php": ">=8.1" + }, + "type": "library", + "extra": { + "branch-alias": { + "dev-main": "3.5-dev" + }, + "thanks": { + "name": "symfony/contracts", + "url": "https://github.com/symfony/contracts" + } + }, + "autoload": { + "files": [ + "function.php" + ] + }, + "notification-url": "https://packagist.org/downloads/", + "license": [ + "MIT" + ], + "authors": [ + { + "name": "Nicolas Grekas", + "email": "p@tchwork.com" + }, + { + "name": "Symfony Community", + "homepage": "https://symfony.com/contributors" + } + ], + "description": "A generic function and convention to trigger deprecation notices", + "homepage": "https://symfony.com", + "support": { + "source": "https://github.com/symfony/deprecation-contracts/tree/v3.5.1" + }, + "funding": [ + { + "url": "https://symfony.com/sponsor", + "type": "custom" + }, + { + "url": "https://github.com/fabpot", + "type": "github" + }, + { + "url": "https://tidelift.com/funding/github/packagist/symfony/symfony", + "type": "tidelift" + } + ], + "time": "2024-09-25T14:20:29+00:00" + } + ], + "packages-dev": [], + "aliases": [], + "minimum-stability": "stable", + "stability-flags": [], + "prefer-stable": false, + "prefer-lowest": false, + "platform": [], + "platform-dev": [], + "plugin-api-version": "2.6.0" +} diff --git a/sdks/php-client/dify-client.php b/sdks/php-client/dify-client.php index ccd61f091a..acb862093a 100644 --- a/sdks/php-client/dify-client.php +++ b/sdks/php-client/dify-client.php @@ -1,7 +1,5 @@ api_key = $api_key; - $this->base_url = $base_url ?? "https://api.dify.ai/v1/"; + $this->base_url = $base_url ?? 'https://api.dify.ai/v1/'; $this->client = new Client([ 'base_uri' => $this->base_url, 'headers' => [ @@ -19,13 +17,6 @@ class DifyClient { 'Content-Type' => 'application/json', ], ]); - $this->file_client = new Client([ - 'base_uri' => $this->base_url, - 'headers' => [ - 'Authorization' => 'Bearer ' . $this->api_key, - 'Content-Type' => 'multipart/form-data', - ], - ]); } protected function send_request($method, $endpoint, $data = null, $params = null, $stream = false) { @@ -58,7 +49,7 @@ class DifyClient { 'multipart' => $this->prepareMultipart($data, $files) ]; - return $this->file_client->request('POST', 'files/upload', $options); + return $this->client->request('POST', 'files/upload', $options); } protected function prepareMultipart($data, $files) { @@ -132,7 +123,7 @@ class ChatClient extends DifyClient { public function get_suggestions($message_id, $user) { $params = [ 'user' => $user - ] + ]; return $this->send_request('GET', "messages/{$message_id}/suggested", null, $params); } @@ -188,10 +179,9 @@ class ChatClient extends DifyClient { 'user' => $user, ]; $options = [ - 'multipart' => $this->prepareMultipart($data, $files) + 'multipart' => $this->prepareMultipart($data, $audio_file) ]; - return $this->file_client->request('POST', 'audio-to-text', $options); - + return $this->client->request('POST', 'audio-to-text', $options); } } diff --git a/web/app/components/app/configuration/dataset-config/select-dataset/index.tsx b/web/app/components/app/configuration/dataset-config/select-dataset/index.tsx index 64a7f6dc46..ffdb714f08 100644 --- a/web/app/components/app/configuration/dataset-config/select-dataset/index.tsx +++ b/web/app/components/app/configuration/dataset-config/select-dataset/index.tsx @@ -14,6 +14,7 @@ import Loading from '@/app/components/base/loading' import Badge from '@/app/components/base/badge' import { useKnowledge } from '@/hooks/use-knowledge' import cn from '@/utils/classnames' +import { basePath } from '@/utils/var' export type ISelectDataSetProps = { isShow: boolean @@ -111,7 +112,7 @@ const SelectDataSet: FC = ({ }} > {t('appDebug.feature.dataSet.noDataSet')} - {t('appDebug.feature.dataSet.toCreate')} + {t('appDebug.feature.dataSet.toCreate')} )} diff --git a/web/app/components/app/overview/embedded/index.tsx b/web/app/components/app/overview/embedded/index.tsx index d4e5dd8898..691b727b8e 100644 --- a/web/app/components/app/overview/embedded/index.tsx +++ b/web/app/components/app/overview/embedded/index.tsx @@ -29,7 +29,7 @@ const OPTION_MAP = { iframe: { getContent: (url: string, token: string) => `