Add ty type checker to CI and fix type errors (fixes bug from PR #157) (#192)

* Add ty type checker to CI and fix type errors

- Add ty (Astral's fast Python type checker) to GitHub CI workflow
- Fix type annotations across all RAG apps:
  - Update load_data return types from list[str] to list[dict[str, Any]]
  - Fix base_rag_example.py to properly handle dict format from create_text_chunks
- Fix type errors in leann-core:
  - chunking_utils.py: Add explicit type annotations
  - cli.py: Fix return type annotations for PDF extraction functions
  - interactive_utils.py: Fix readline import type handling
- Fix type errors in apps:
  - wechat_history.py: Fix return type annotations
  - document_rag.py, code_rag.py: Replace **kwargs with explicit arguments
- Add ty configuration to pyproject.toml

This resolves the bug introduced in PR #157 where create_text_chunks()
changed to return list[dict] but callers were not updated.

* 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

* Fix multimodal benchmark scripts type errors

- Fix undefined LeannRetriever -> LeannMultiVector
- Add proper type casts for HuggingFace Dataset iteration
- Cast task config values to correct types
- Add type annotations for dataset row dicts

* Enable ty check for multimodal scripts in CI

All type errors in multimodal scripts have been fixed, so we can now
include them in the CI type checking.

* Fix all test type errors and enable ty check on tests

- Fix test_basic.py: search() takes str not list
- Fix test_cli_prompt_template.py: add type: ignore for Mock assignments
- Fix test_prompt_template_persistence.py: match BaseSearcher.search signature
- Fix test_prompt_template_e2e.py: add type narrowing asserts after skip
- Fix test_readme_examples.py: use explicit kwargs instead of **model_args
- Fix metadata_filter.py: allow Optional[MetadataFilters]
- Update CI to run ty check on tests

* Format code with ruff

* Format searcher_base.py

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

@@ -239,11 +239,11 @@ def create_ast_chunks(
 
             chunks = chunk_builder.chunkify(code_content)
             for chunk in chunks:
-                chunk_text = None
-                astchunk_metadata = {}
+                chunk_text: str | None = None
+                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/cli.py

@@ -19,7 +19,7 @@ from .settings import (
 )
 
 
-def extract_pdf_text_with_pymupdf(file_path: str) -> str:
+def extract_pdf_text_with_pymupdf(file_path: str) -> str | None:
     """Extract text from PDF using PyMuPDF for better quality."""
     try:
         import fitz  # PyMuPDF
@@ -35,7 +35,7 @@ def extract_pdf_text_with_pymupdf(file_path: str) -> str:
         return None
 
 
-def extract_pdf_text_with_pdfplumber(file_path: str) -> str:
+def extract_pdf_text_with_pdfplumber(file_path: str) -> str | None:
     """Extract text from PDF using pdfplumber for better quality."""
     try:
         import pdfplumber

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/interactive_utils.py

@@ -11,14 +11,15 @@ from pathlib import Path
 from typing import Callable, Optional
 
 # Try to import readline with fallback for Windows
+HAS_READLINE = False
+readline = None  # type: ignore[assignment]
 try:
-    import readline
+    import readline  # type: ignore[no-redef]
 
     HAS_READLINE = True
 except ImportError:
     # Windows doesn't have readline by default
-    HAS_READLINE = False
-    readline = None
+    pass
 
 
 class InteractiveSession:

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

@@ -7,7 +7,7 @@ operators for different data types including numbers, strings, booleans, and lis
 """
 
 import logging
-from typing import Any, Union
+from typing import Any, Optional, Union
 
 logger = logging.getLogger(__name__)
 
@@ -47,7 +47,7 @@ class MetadataFilterEngine:
         }
 
     def apply_filters(
-        self, search_results: list[dict[str, Any]], metadata_filters: MetadataFilters
+        self, search_results: list[dict[str, Any]], metadata_filters: Optional[MetadataFilters]
     ) -> list[dict[str, Any]]:
         """
         Apply metadata filters to a list of search results.

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

@@ -56,7 +56,9 @@ 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 +83,7 @@ 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 +100,7 @@ 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:
         """