feat: Add chunk-size parameters and improve file type filtering

- Add --chunk-size and --chunk-overlap parameters to all RAG examples
- Preserve original default values for each data source:
  - Document: 256/128 (optimized for general documents)
  - Email: 256/25 (smaller overlap for email threads)
  - Browser: 256/128 (standard for web content)
  - WeChat: 192/64 (smaller chunks for chat messages)
- Make --file-types optional filter instead of restriction in document_rag
- Update README to clarify interactive mode and parameter usage
- Fix LLM default model documentation (gpt-4o, not gpt-4o-mini)

examples/browser_rag.py

@@ -39,6 +39,12 @@ class BrowserRAG(BaseRAGExample):
             default=True,
             help="Automatically find all Chrome profiles (default: True)",
         )
+        browser_group.add_argument(
+            "--chunk-size", type=int, default=256, help="Text chunk size (default: 256)"
+        )
+        browser_group.add_argument(
+            "--chunk-overlap", type=int, default=128, help="Text chunk overlap (default: 128)"
+        )
 
     def _get_chrome_base_path(self) -> Path:
         """Get the base Chrome profile path based on OS."""
@@ -134,7 +140,9 @@ class BrowserRAG(BaseRAGExample):
         print(f"\nTotal history entries processed: {len(all_documents)}")
 
         # Convert to text chunks
-        all_texts = create_text_chunks(all_documents)
+        all_texts = create_text_chunks(
+            all_documents, chunk_size=args.chunk_size, chunk_overlap=args.chunk_overlap
+        )
 
         return all_texts
 

examples/document_rag.py

@@ -35,8 +35,8 @@ class DocumentRAG(BaseRAGExample):
         doc_group.add_argument(
             "--file-types",
             nargs="+",
-            default=[".pdf", ".txt", ".md"],
-            help="File types to process (default: .pdf .txt .md)",
+            default=None,
+            help="Filter by file types (e.g., .pdf .txt .md). If not specified, all supported types are processed",
         )
         doc_group.add_argument(
             "--chunk-size", type=int, default=256, help="Text chunk size (default: 256)"
@@ -48,7 +48,10 @@ class DocumentRAG(BaseRAGExample):
     async def load_data(self, args) -> list[str]:
         """Load documents and convert to text chunks."""
         print(f"Loading documents from: {args.data_dir}")
-        print(f"File types: {args.file_types}")
+        if args.file_types:
+            print(f"Filtering by file types: {args.file_types}")
+        else:
+            print("Processing all supported file types")
 
         # Check if data directory exists
         data_path = Path(args.data_dir)
@@ -56,12 +59,16 @@ class DocumentRAG(BaseRAGExample):
             raise ValueError(f"Data directory not found: {args.data_dir}")
 
         # Load documents
-        documents = SimpleDirectoryReader(
-            args.data_dir,
-            recursive=True,
-            encoding="utf-8",
-            required_exts=args.file_types,
-        ).load_data(show_progress=True)
+        reader_kwargs = {
+            "recursive": True,
+            "encoding": "utf-8",
+        }
+        if args.file_types:
+            reader_kwargs["required_exts"] = args.file_types
+
+        documents = SimpleDirectoryReader(args.data_dir, **reader_kwargs).load_data(
+            show_progress=True
+        )
 
         if not documents:
             print(f"No documents found in {args.data_dir} with extensions {args.file_types}")

examples/email_rag.py

@@ -35,6 +35,12 @@ class EmailRAG(BaseRAGExample):
         email_group.add_argument(
             "--include-html", action="store_true", help="Include HTML content in email processing"
         )
+        email_group.add_argument(
+            "--chunk-size", type=int, default=256, help="Text chunk size (default: 256)"
+        )
+        email_group.add_argument(
+            "--chunk-overlap", type=int, default=25, help="Text chunk overlap (default: 25)"
+        )
 
     def _find_mail_directories(self) -> list[Path]:
         """Auto-detect all Apple Mail directories."""
@@ -113,7 +119,9 @@ class EmailRAG(BaseRAGExample):
 
         # Convert to text chunks
         # Email reader uses chunk_overlap=25 as in original
-        all_texts = create_text_chunks(all_documents, chunk_overlap=25)
+        all_texts = create_text_chunks(
+            all_documents, chunk_size=args.chunk_size, chunk_overlap=args.chunk_overlap
+        )
 
         return all_texts
 

examples/wechat_rag.py

@@ -42,6 +42,12 @@ class WeChatRAG(BaseRAGExample):
             action="store_true",
             help="Force re-export of WeChat data even if exports exist",
         )
+        wechat_group.add_argument(
+            "--chunk-size", type=int, default=192, help="Text chunk size (default: 192)"
+        )
+        wechat_group.add_argument(
+            "--chunk-overlap", type=int, default=64, help="Text chunk overlap (default: 64)"
+        )
 
     def _export_wechat_data(self, export_dir: Path) -> bool:
         """Export WeChat data using wechattweak-cli."""
@@ -120,7 +126,9 @@ class WeChatRAG(BaseRAGExample):
             print(f"Loaded {len(documents)} chat entries")
 
             # Convert to text chunks
-            all_texts = create_text_chunks(documents)
+            all_texts = create_text_chunks(
+                documents, chunk_size=args.chunk_size, chunk_overlap=args.chunk_overlap
+            )
 
             return all_texts