Merge branch 'fix/chore-fix' into dev/plugin-deploy

langgenius · Dec 6, 2024 · 1ce7990 · 1ce7990
2 parents fbcd4fe + 337eff2
commit 1ce7990
Show file tree

Hide file tree

Showing 85 changed files with 1,845 additions and 1,203 deletions.
diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
@@ -8,16 +8,9 @@ Please include a summary of the change and which issue is fixed. Please also inc
 
 # Screenshots
 
-<table>
-  <tr>
-  <td>Before: </td>
-  <td>After: </td>
-  </tr>
-  <tr>
-  <td>...</td>
-  <td>...</td>
-  </tr>
-</table>
+| Before | After |
+|--------|-------|
+| ...    | ...   |
 
 # Checklist
 

diff --git a/api/commands.py b/api/commands.py
@@ -260,15 +260,15 @@ def migrate_knowledge_vector_database():
     skipped_count = 0
     total_count = 0
     vector_type = dify_config.VECTOR_STORE
-    upper_colletion_vector_types = {
+    upper_collection_vector_types = {
         VectorType.MILVUS,
         VectorType.PGVECTOR,
         VectorType.RELYT,
         VectorType.WEAVIATE,
         VectorType.ORACLE,
         VectorType.ELASTICSEARCH,
     }
-    lower_colletion_vector_types = {
+    lower_collection_vector_types = {
         VectorType.ANALYTICDB,
         VectorType.CHROMA,
         VectorType.MYSCALE,
@@ -308,7 +308,7 @@ def migrate_knowledge_vector_database():
                         continue
                 collection_name = ""
                 dataset_id = dataset.id
-                if vector_type in upper_colletion_vector_types:
+                if vector_type in upper_collection_vector_types:
                     collection_name = Dataset.gen_collection_name_by_id(dataset_id)
                 elif vector_type == VectorType.QDRANT:
                     if dataset.collection_binding_id:
@@ -324,7 +324,7 @@ def migrate_knowledge_vector_database():
                     else:
                         collection_name = Dataset.gen_collection_name_by_id(dataset_id)
 
-                elif vector_type in lower_colletion_vector_types:
+                elif vector_type in lower_collection_vector_types:
                     collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
                 else:
                     raise ValueError(f"Vector store {vector_type} is not supported.")

diff --git 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="0.13.0",
+        default="0.13.1",
     )
 
     COMMIT_SHA: str = Field(

diff --git a/api/core/app/apps/README.md b/api/core/app/apps/README.md
@@ -2,7 +2,7 @@
 
 Due to the presence of tasks in App Runner that require long execution times, such as LLM generation and external requests, Flask-Sqlalchemy's strategy for database connection pooling is to allocate one connection (transaction) per request. This approach keeps a connection occupied even during non-DB tasks, leading to the inability to acquire new connections during high concurrency requests due to multiple long-running tasks.
 
-Therefore, the database operations in App Runner and Task Pipeline must ensure connections are closed immediately after use, and it's better to pass IDs rather than Model objects to avoid deattach errors.
+Therefore, the database operations in App Runner and Task Pipeline must ensure connections are closed immediately after use, and it's better to pass IDs rather than Model objects to avoid detach errors.
 
 Examples:
 

diff --git a/api/core/app/apps/base_app_generate_response_converter.py b/api/core/app/apps/base_app_generate_response_converter.py
@@ -72,7 +72,7 @@ def _get_simple_metadata(cls, metadata: dict[str, Any]):
             for resource in metadata["retriever_resources"]:
                 updated_resources.append(
                     {
-                        "segment_id": resource["segment_id"],
+                        "segment_id": resource.get("segment_id", ""),
                         "position": resource["position"],
                         "document_name": resource["document_name"],
                         "score": resource["score"],

diff --git a/api/core/model_runtime/docs/zh_Hans/interfaces.md b/api/core/model_runtime/docs/zh_Hans/interfaces.md
@@ -91,7 +91,7 @@ class XinferenceProvider(Provider):
       """
   ```
 
-  也可以直接抛出对应Erros，并做如下定义，这样在之后的调用中可以直接抛出`InvokeConnectionError`等异常。
+  也可以直接抛出对应 Errors，并做如下定义，这样在之后的调用中可以直接抛出`InvokeConnectionError`等异常。
 
     ```python
     @property

diff --git a/api/core/prompt/prompt_templates/advanced_prompt_templates.py b/api/core/prompt/prompt_templates/advanced_prompt_templates.py
@@ -5,7 +5,7 @@
 CHAT_APP_COMPLETION_PROMPT_CONFIG = {
     "completion_prompt_config": {
         "prompt": {
-            "text": "{{#pre_prompt#}}\nHere is the chat histories between human and assistant, inside <histories></histories> XML tags.\n\n<histories>\n{{#histories#}}\n</histories>\n\n\nHuman: {{#query#}}\n\nAssistant: "  # noqa: E501
+            "text": "{{#pre_prompt#}}\nHere are the chat histories between human and assistant, inside <histories></histories> XML tags.\n\n<histories>\n{{#histories#}}\n</histories>\n\n\nHuman: {{#query#}}\n\nAssistant: "  # noqa: E501
         },
         "conversation_histories_role": {"user_prefix": "Human", "assistant_prefix": "Assistant"},
     },

diff --git a/api/core/rag/datasource/vdb/tidb_on_qdrant/tidb_on_qdrant_vector.py b/api/core/rag/datasource/vdb/tidb_on_qdrant/tidb_on_qdrant_vector.py
@@ -375,7 +375,6 @@ def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
         for result in results:
             if result:
                 document = self._document_from_scored_point(result, Field.CONTENT_KEY.value, Field.METADATA_KEY.value)
-                document.metadata["vector"] = result.vector
                 documents.append(document)
 
         return documents
@@ -394,6 +393,7 @@ def _document_from_scored_point(
     ) -> Document:
         return Document(
             page_content=scored_point.payload.get(content_payload_key),
+            vector=scored_point.vector,
             metadata=scored_point.payload.get(metadata_payload_key) or {},
         )
 

diff --git a/api/core/workflow/nodes/if_else/if_else_node.py b/api/core/workflow/nodes/if_else/if_else_node.py
@@ -24,7 +24,7 @@ def _run(self) -> NodeRunResult:
         """
         node_inputs: dict[str, list] = {"conditions": []}
 
-        process_datas: dict[str, list] = {"condition_results": []}
+        process_data: dict[str, list] = {"condition_results": []}
 
         input_conditions = []
         final_result = False
@@ -40,7 +40,7 @@ def _run(self) -> NodeRunResult:
                         operator=case.logical_operator,
                     )
 
-                    process_datas["condition_results"].append(
+                    process_data["condition_results"].append(
                         {
                             "group": case.model_dump(),
                             "results": group_result,
@@ -65,23 +65,23 @@ def _run(self) -> NodeRunResult:
 
                 selected_case_id = "true" if final_result else "false"
 
-                process_datas["condition_results"].append(
+                process_data["condition_results"].append(
                     {"group": "default", "results": group_result, "final_result": final_result}
                 )
 
             node_inputs["conditions"] = input_conditions
 
         except Exception as e:
             return NodeRunResult(
-                status=WorkflowNodeExecutionStatus.FAILED, inputs=node_inputs, process_data=process_datas, error=str(e)
+                status=WorkflowNodeExecutionStatus.FAILED, inputs=node_inputs, process_data=process_data, error=str(e)
             )
 
         outputs = {"result": final_result, "selected_case_id": selected_case_id}
 
         data = NodeRunResult(
             status=WorkflowNodeExecutionStatus.SUCCEEDED,
             inputs=node_inputs,
-            process_data=process_datas,
+            process_data=process_data,
             edge_source_handle=selected_case_id or "false",  # Use case ID or 'default'
             outputs=outputs,
         )

diff --git a/api/core/workflow/nodes/iteration/iteration_node.py b/api/core/workflow/nodes/iteration/iteration_node.py
@@ -117,7 +117,7 @@ def _run(self) -> Generator[NodeEvent | InNodeEvent, None, None]:
         variable_pool.add([self.node_id, "item"], iterator_list_value[0])
 
         # init graph engine
-        from core.workflow.graph_engine.graph_engine import GraphEngine
+        from core.workflow.graph_engine.graph_engine import GraphEngine, GraphEngineThreadPool
 
         graph_engine = GraphEngine(
             tenant_id=self.tenant_id,
@@ -163,8 +163,7 @@ def _run(self) -> Generator[NodeEvent | InNodeEvent, None, None]:
             if self.node_data.is_parallel:
                 futures: list[Future] = []
                 q = Queue()
-                thread_pool = graph_engine.workflow_thread_pool_mapping[graph_engine.thread_pool_id]
-                thread_pool._max_workers = self.node_data.parallel_nums
+                thread_pool = GraphEngineThreadPool(max_workers=self.node_data.parallel_nums, max_submit_count=100)
                 for index, item in enumerate(iterator_list_value):
                     future: Future = thread_pool.submit(
                         self._run_single_iter_parallel,

diff --git a/api/core/workflow/nodes/llm/node.py b/api/core/workflow/nodes/llm/node.py
@@ -815,7 +815,7 @@ def get_default_config(cls, filters: Optional[dict] = None) -> dict:
                     "completion_model": {
                         "conversation_histories_role": {"user_prefix": "Human", "assistant_prefix": "Assistant"},
                         "prompt": {
-                            "text": "Here is the chat histories between human and assistant, inside "
+                            "text": "Here are the chat histories between human and assistant, inside "
                             "<histories></histories> XML tags.\n\n<histories>\n{{"
                             "#histories#}}\n</histories>\n\n\nHuman: {{#sys.query#}}\n\nAssistant:",
                             "edition_type": "basic",

diff --git a/api/core/workflow/nodes/parameter_extractor/prompts.py b/api/core/workflow/nodes/parameter_extractor/prompts.py
@@ -98,7 +98,7 @@
 Step 4: Ensure that the JSON object is properly formatted and valid. The output should not contain any XML tags. Only the JSON object should be outputted.
 
 ### Memory
-Here is the chat histories between human and assistant, inside <histories></histories> XML tags.
+Here are the chat histories between human and assistant, inside <histories></histories> XML tags.
 <histories>
 {histories}
 </histories>
@@ -125,7 +125,7 @@
 The structure of the JSON object you can found in the instructions.
 
 ### Memory
-Here is the chat histories between human and assistant, inside <histories></histories> XML tags.
+Here are the chat histories between human and assistant, inside <histories></histories> XML tags.
 <histories>
 {histories}
 </histories>

diff --git a/api/core/workflow/nodes/question_classifier/template_prompts.py b/api/core/workflow/nodes/question_classifier/template_prompts.py
@@ -8,7 +8,7 @@
     ### Constraint
     DO NOT include anything other than the JSON array in your response.
     ### Memory
-    Here is the chat histories between human and assistant, inside <histories></histories> XML tags.
+    Here are the chat histories between human and assistant, inside <histories></histories> XML tags.
     <histories>
     {histories}
     </histories>
@@ -66,7 +66,7 @@
 Assistant:{{"keywords": ["bad service", "slow", "food", "tip", "terrible", "waitresses"],"category_id": "f6ff5bc3-aca0-4e4a-8627-e760d0aca78f","category_name": "Experience"}}
 </example> 
 ### Memory
-Here is the chat histories between human and assistant, inside <histories></histories> XML tags.
+Here are the chat histories between human and assistant, inside <histories></histories> XML tags.
 <histories>
 {histories}
 </histories>

diff --git a/api/core/workflow/nodes/variable_assigner/v2/exc.py b/api/core/workflow/nodes/variable_assigner/v2/exc.py
@@ -7,8 +7,8 @@
 
 
 class OperationNotSupportedError(VariableOperatorNodeError):
-    def __init__(self, *, operation: Operation, varialbe_type: str):
-        super().__init__(f"Operation {operation} is not supported for type {varialbe_type}")
+    def __init__(self, *, operation: Operation, variable_type: str):
+        super().__init__(f"Operation {operation} is not supported for type {variable_type}")
 
 
 class InputTypeNotSupportedError(VariableOperatorNodeError):

diff --git a/api/core/workflow/nodes/variable_assigner/v2/node.py b/api/core/workflow/nodes/variable_assigner/v2/node.py
@@ -45,7 +45,7 @@ def _run(self) -> NodeRunResult:
 
                 # Check if operation is supported
                 if not helpers.is_operation_supported(variable_type=variable.value_type, operation=item.operation):
-                    raise OperationNotSupportedError(operation=item.operation, varialbe_type=variable.value_type)
+                    raise OperationNotSupportedError(operation=item.operation, variable_type=variable.value_type)
 
                 # Check if variable input is supported
                 if item.input_type == InputType.VARIABLE and not helpers.is_variable_input_supported(
@@ -156,4 +156,4 @@ def _handle_item(
             case Operation.DIVIDE:
                 return variable.value / value
             case _:
-                raise OperationNotSupportedError(operation=operation, varialbe_type=variable.value_type)
+                raise OperationNotSupportedError(operation=operation, variable_type=variable.value_type)