Merge remote-tracking branch 'origin/main' into feat/queue-based-graph-engine

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")