Fix remaining ty type errors

- Fix slack_mcp_reader.py channel parameter can be None
- Fix embedding_compute.py ContextProp type issue
- Fix searcher_base.py method override signatures
- Fix chunking_utils.py chunk_text assignment
- Fix slack_rag.py and twitter_rag.py return types
- Fix email.py and image_rag.py method overrides

apps/email_data/email.py

@@ -127,11 +127,12 @@ class EmlxMboxReader(MboxReader):
 
     def load_data(
         self,
-        directory: Path,
+        file: Path,  # Note: for EmlxMboxReader, this is actually a directory
         extra_info: dict | None = None,
         fs: AbstractFileSystem | None = None,
     ) -> list[Document]:
         """Parse .emlx files from directory into strings using MboxReader logic."""
+        directory = file  # Rename for clarity - this is a directory of .emlx files
         import os
         import tempfile
 

apps/image_rag.py

@@ -169,7 +169,7 @@ class ImageRAG(BaseRAGExample):
         print(f"✅ Processed {len(image_data)} images")
         return image_data
 
-    async def build_index(self, args, texts: list[str]) -> str:
+    async def build_index(self, args, texts: list[dict[str, Any]]) -> str:
         """Build index using pre-computed CLIP embeddings."""
         from leann.api import LeannBuilder
 

apps/slack_data/slack_mcp_reader.py

@@ -177,7 +177,9 @@ class SlackMCPReader:
                     break
 
         # If we get here, all retries failed or it's not a retryable error
-        raise last_exception
+        if last_exception is not None:
+            raise last_exception
+        raise RuntimeError("Unexpected error: no exception captured during retry loop")
 
     async def fetch_slack_messages(
         self, channel: Optional[str] = None, limit: int = 100
@@ -267,7 +269,10 @@ class SlackMCPReader:
                     messages = json.loads(content["text"])
                 except json.JSONDecodeError:
                     # If not JSON, try to parse as CSV format (Slack MCP server format)
-                    messages = self._parse_csv_messages(content["text"], channel)
+                    text_content = content.get("text", "")
+                    messages = self._parse_csv_messages(
+                        text_content if text_content else "", channel or "unknown"
+                    )
             else:
                 messages = result["content"]
         else:

apps/slack_rag.py

@@ -189,7 +189,8 @@ class SlackMCPRAG(BaseRAGExample):
                 print(sample_text)
                 print("-" * 40)
 
-            return texts
+            # Convert strings to dict format expected by base class
+            return [{"text": text, "metadata": {"source": "slack"}} for text in texts]
 
         except Exception as e:
             print(f"Error loading Slack data: {e}")

apps/twitter_rag.py

@@ -157,7 +157,8 @@ class TwitterMCPRAG(BaseRAGExample):
                 print(sample_text)
                 print("-" * 50)
 
-            return texts
+            # Convert strings to dict format expected by base class
+            return [{"text": text, "metadata": {"source": "twitter"}} for text in texts]
 
         except Exception as e:
             print(f"❌ Error loading Twitter bookmarks: {e}")

packages/leann-core/src/leann/chunking_utils.py

@@ -243,7 +243,7 @@ def create_ast_chunks(
                 astchunk_metadata: dict[str, Any] = {}
 
                 if hasattr(chunk, "text"):
-                    chunk_text = chunk.text
+                    chunk_text = str(chunk.text) if chunk.text else None
                 elif isinstance(chunk, str):
                     chunk_text = chunk
                 elif isinstance(chunk, dict):

packages/leann-core/src/leann/embedding_compute.py

@@ -451,7 +451,8 @@ def compute_embeddings_sentence_transformers(
             # TODO: Haven't tested this yet
             torch.set_num_threads(min(8, os.cpu_count() or 4))
             try:
-                torch.backends.mkldnn.enabled = True
+                # PyTorch's ContextProp type is complex; cast for type checker
+                torch.backends.mkldnn.enabled = True  # type: ignore[assignment]
             except AttributeError:
                 pass
 

packages/leann-core/src/leann/searcher_base.py

@@ -56,7 +56,7 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
         with open(meta_path, encoding="utf-8") as f:
             return json.load(f)
 
-    def _ensure_server_running(self, passages_source_file: str, port: int, **kwargs) -> int:
+    def _ensure_server_running(self, passages_source_file: str, port: Optional[int], **kwargs) -> int:
         """
         Ensures the embedding server is running if recompute is needed.
         This is a helper for subclasses.
@@ -81,7 +81,7 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
         }
 
         server_started, actual_port = self.embedding_server_manager.start_server(
-            port=port,
+            port=port if port is not None else 5557,
             model_name=self.embedding_model,
             embedding_mode=self.embedding_mode,
             passages_file=passages_source_file,
@@ -98,7 +98,7 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
         self,
         query: str,
         use_server_if_available: bool = True,
-        zmq_port: int = 5557,
+        zmq_port: Optional[int] = None,
         query_template: Optional[str] = None,
     ) -> np.ndarray:
         """