Merge branch 'main' into feat/rag-2

# Conflicts:
#	api/core/app/entities/queue_entities.py
#	api/core/workflow/graph_engine/entities/event.py

api/core/app/entities/queue_entities.py

@@ -169,7 +169,7 @@ class QueueLoopNextEvent(AppQueueEvent):
     parent_parallel_start_node_id: Optional[str] = None
     """parent parallel start node id if node is in parallel"""
     parallel_mode_run_id: Optional[str] = None
-    """iteratoin run in parallel mode run id"""
+    """iteration run in parallel mode run id"""
     node_run_index: int
     output: Optional[Any] = None  # output for the current loop
 

api/core/app/task_pipeline/exc.py

@@ -1,8 +1,8 @@
-class TaskPipilineError(ValueError):
+class TaskPipelineError(ValueError):
     pass
 
 
-class RecordNotFoundError(TaskPipilineError):
+class RecordNotFoundError(TaskPipelineError):
     def __init__(self, record_name: str, record_id: str):
         super().__init__(f"{record_name} with id {record_id} not found")
 

api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenizer.py

@@ -43,7 +43,7 @@ class GPT2Tokenizer:
                 except Exception:
                     from os.path import abspath, dirname, join
 
-                    from transformers import GPT2Tokenizer as TransformerGPT2Tokenizer  # type: ignore
+                    from transformers import GPT2Tokenizer as TransformerGPT2Tokenizer
 
                     base_path = abspath(__file__)
                     gpt2_tokenizer_path = join(dirname(base_path), "gpt2")

api/core/ops/ops_trace_manager.py

@@ -332,7 +332,7 @@ class OpsTraceManager:
             except KeyError:
                 raise ValueError(f"Invalid tracing provider: {tracing_provider}")
         else:
-            if tracing_provider is not None:
+            if tracing_provider is None:
                 raise ValueError(f"Invalid tracing provider: {tracing_provider}")
 
         app_config: Optional[App] = db.session.query(App).where(App.id == app_id).first()

api/core/plugin/backwards_invocation/model.py

@@ -375,16 +375,16 @@ Here is the extra instruction you need to follow:
 
         # merge lines into messages with max tokens
         messages: list[str] = []
-        for i in new_lines:  # type: ignore
+        for line in new_lines:
             if len(messages) == 0:
-                messages.append(i)  # type: ignore
+                messages.append(line)
             else:
-                if len(messages[-1]) + len(i) < max_tokens * 0.5:  # type: ignore
-                    messages[-1] += i  # type: ignore
-                if get_prompt_tokens(messages[-1] + i) > max_tokens * 0.7:  # type: ignore
-                    messages.append(i)  # type: ignore
+                if len(messages[-1]) + len(line) < max_tokens * 0.5:
+                    messages[-1] += line
+                if get_prompt_tokens(messages[-1] + line) > max_tokens * 0.7:
+                    messages.append(line)
                 else:
-                    messages[-1] += i  # type: ignore
+                    messages[-1] += line
 
         summaries = []
         for i in range(len(messages)):

api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py

@@ -3,8 +3,8 @@ import uuid
 from contextlib import contextmanager
 from typing import Any
 
-import psycopg2.extras  # type: ignore
-import psycopg2.pool  # type: ignore
+import psycopg2.extras
+import psycopg2.pool
 from pydantic import BaseModel, model_validator
 
 from core.rag.models.document import Document

api/core/rag/datasource/vdb/opengauss/opengauss.py

@@ -3,8 +3,8 @@ import uuid
 from contextlib import contextmanager
 from typing import Any
 
-import psycopg2.extras  # type: ignore
-import psycopg2.pool  # type: ignore
+import psycopg2.extras
+import psycopg2.pool
 from pydantic import BaseModel, model_validator
 
 from configs import dify_config

api/core/rag/datasource/vdb/opensearch/opensearch_vector.py

@@ -48,7 +48,7 @@ class OpenSearchConfig(BaseModel):
         return values
 
     def create_aws_managed_iam_auth(self) -> Urllib3AWSV4SignerAuth:
-        import boto3  # type: ignore
+        import boto3
 
         return Urllib3AWSV4SignerAuth(
             credentials=boto3.Session().get_credentials(),

api/core/rag/datasource/vdb/pgvector/pgvector.py

@@ -6,8 +6,8 @@ from contextlib import contextmanager
 from typing import Any
 
 import psycopg2.errors
-import psycopg2.extras  # type: ignore
-import psycopg2.pool  # type: ignore
+import psycopg2.extras
+import psycopg2.pool
 from pydantic import BaseModel, model_validator
 
 from configs import dify_config

api/core/rag/datasource/vdb/pyvastbase/vastbase_vector.py

@@ -3,8 +3,8 @@ import uuid
 from contextlib import contextmanager
 from typing import Any
 
-import psycopg2.extras  # type: ignore
-import psycopg2.pool  # type: ignore
+import psycopg2.extras
+import psycopg2.pool
 from pydantic import BaseModel, model_validator
 
 from configs import dify_config

api/core/rag/datasource/vdb/tidb_on_qdrant/tidb_on_qdrant_vector.py

@@ -3,7 +3,7 @@ import os
 import uuid
 from collections.abc import Generator, Iterable, Sequence
 from itertools import islice
-from typing import TYPE_CHECKING, Any, Optional, Union, cast
+from typing import TYPE_CHECKING, Any, Optional, Union
 
 import qdrant_client
 import requests
@@ -398,7 +398,6 @@ class TidbOnQdrantVector(BaseVector):
 
     def _reload_if_needed(self):
         if isinstance(self._client, QdrantLocal):
-            self._client = cast(QdrantLocal, self._client)
             self._client._load()
 
     @classmethod

api/core/rag/extractor/excel_extractor.py

@@ -4,7 +4,7 @@ import os
 from typing import Optional, cast
 
 import pandas as pd
-from openpyxl import load_workbook  # type: ignore
+from openpyxl import load_workbook
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document

api/core/rag/extractor/extract_processor.py

@@ -73,8 +73,8 @@ class ExtractProcessor:
                             suffix = "." + match.group(1)
                         else:
                             suffix = ""
-            # FIXME mypy: Cannot determine type of 'tempfile._get_candidate_names' better not use it here
-            file_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"  # type: ignore
+            # https://stackoverflow.com/questions/26541416/generate-temporary-file-names-without-creating-actual-file-in-python#comment90414256_26541521
+            file_path = f"{temp_dir}/{tempfile.gettempdir()}{suffix}"
             Path(file_path).write_bytes(response.content)
             extract_setting = ExtractSetting(datasource_type="upload_file", document_model="text_model")
             if return_text:

api/core/rag/extractor/html_extractor.py

@@ -1,6 +1,6 @@
 """Abstract interface for document loader implementations."""
 
-from bs4 import BeautifulSoup  # type: ignore
+from bs4 import BeautifulSoup
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document

api/core/rag/extractor/unstructured/unstructured_eml_extractor.py

@@ -3,7 +3,7 @@ import contextlib
 import logging
 from typing import Optional
 
-from bs4 import BeautifulSoup  # type: ignore
+from bs4 import BeautifulSoup
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document

api/core/rag/splitter/text_splitter.py

@@ -144,7 +144,7 @@ class TextSplitter(BaseDocumentTransformer, ABC):
     def from_huggingface_tokenizer(cls, tokenizer: Any, **kwargs: Any) -> TextSplitter:
         """Text splitter that uses HuggingFace tokenizer to count length."""
         try:
-            from transformers import PreTrainedTokenizerBase  # type: ignore
+            from transformers import PreTrainedTokenizerBase
 
             if not isinstance(tokenizer, PreTrainedTokenizerBase):
                 raise ValueError("Tokenizer received was not an instance of PreTrainedTokenizerBase")

api/core/tools/utils/parser.py

@@ -6,7 +6,7 @@ from typing import Optional
 
 from flask import request
 from requests import get
-from yaml import YAMLError, safe_load  # type: ignore
+from yaml import YAMLError, safe_load
 
 from core.tools.entities.common_entities import I18nObject
 from core.tools.entities.tool_bundle import ApiToolBundle

api/core/workflow/nodes/document_extractor/node.py

@@ -514,14 +514,14 @@ def _extract_text_from_excel(file_content: bytes) -> str:
                 df.dropna(how="all", inplace=True)
 
                 # Combine multi-line text in each cell into a single line
-                df = df.applymap(lambda x: " ".join(str(x).splitlines()) if isinstance(x, str) else x)  # type: ignore
+                df = df.map(lambda x: " ".join(str(x).splitlines()) if isinstance(x, str) else x)
 
                 # Combine multi-line text in column names into a single line
                 df.columns = pd.Index([" ".join(str(col).splitlines()) for col in df.columns])
 
                 # Manually construct the Markdown table
                 markdown_table += _construct_markdown_table(df) + "\n\n"
-            except Exception as e:
+            except Exception:
                 continue
         return markdown_table
     except Exception as e: