From baf70dc411bde4eac7e51673a89d06783fdfc482 Mon Sep 17 00:00:00 2001
From: yichuan520030910320 <yichuan_wang@berkeley.edu>
Date: Sun, 3 Aug 2025 20:54:52 -0700
Subject: [PATCH] change rebuild logic

---
 README.md                    | 2 +-
 examples/base_rag_example.py | 9 ++++-----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/README.md b/README.md
index 2dcc775..114912c 100755
--- a/README.md
+++ b/README.md
@@ -179,7 +179,7 @@ All RAG examples share these common parameters. **Interactive mode** is availabl
 # Core Parameters (General preprocessing for all examples)
 --index-dir DIR          # Directory to store the index (default: current directory)
 --query "YOUR QUESTION"  # Single query mode. Omit for interactive chat (type 'quit' to exit)
---max-items N           # Limit data preprocessing (default: 1000 items, use -1 to process all data)
+--max-items N           # Limit data preprocessing (default: -1, process all data)
 --force-rebuild         # Force rebuild index even if it exists
 
 # Embedding Parameters
diff --git a/examples/base_rag_example.py b/examples/base_rag_example.py
index 69a91ae..a164b3c 100644
--- a/examples/base_rag_example.py
+++ b/examples/base_rag_example.py
@@ -50,12 +50,12 @@ class BaseRAGExample(ABC):
             help="Query to run (if not provided, will run in interactive mode)",
         )
         # Allow subclasses to override default max_items
-        max_items_default = getattr(self, "max_items_default", 1000)
+        max_items_default = getattr(self, "max_items_default", -1)
         core_group.add_argument(
             "--max-items",
             type=int,
             default=max_items_default,
-            help=f"Maximum number of items to process (default: {max_items_default}, -1 for all)",
+            help="Maximum number of items to process  -1 for all, means index all documents, and you should set it to a reasonable number if you have a large dataset and try at the first time)",
         )
         core_group.add_argument(
             "--force-rebuild", action="store_true", help="Force rebuild index even if it exists"
@@ -256,7 +256,7 @@ class BaseRAGExample(ABC):
 
         # Check if index exists
         index_path = str(Path(args.index_dir) / f"{self.default_index_name}.leann")
-        index_exists = Path(index_path).exists()
+        index_exists = Path(args.index_dir).exists()
 
         if not index_exists or args.force_rebuild:
             # Load data and build index
@@ -268,9 +268,8 @@ class BaseRAGExample(ABC):
                 return
 
             index_path = await self.build_index(args, texts)
-            print(f"Index saved to: {index_path}")
         else:
-            print(f"\nUsing existing index: {index_path}")
+            print(f"\nUsing existing index in {args.index_dir}")
 
         # Run query or interactive mode
         if args.query: