feat: implement smart memory configuration for DiskANN (#16)

- Add intelligent memory calculation based on data size and system specs
- search_memory_maximum: 1/10 of embedding size (controls PQ compression)
- build_memory_maximum: 50% of available RAM (controls sharding)
- Provides optimal balance between performance and memory usage
- Automatic fallback to default values if parameters are explicitly provided

apps/document_rag.py

@@ -99,7 +99,9 @@ if __name__ == "__main__":
     print("- 'What are the main techniques LEANN uses?'")
     print("- 'What is the technique DLPM?'")
     print("- 'Who does Elizabeth Bennet marry?'")
-    print("- 'What is the problem of developing pan gu model? (盘古大模型开发中遇到什么问题?)'")
+    print(
+        "- 'What is the problem of developing pan gu model Huawei meets? (盘古大模型开发中遇到什么问题?)'"
+    )
     print("\nOr run without --query for interactive mode\n")
 
     rag = DocumentRAG()

packages/leann-backend-diskann/leann_backend_diskann/diskann_backend.py

@@ -7,6 +7,7 @@ from pathlib import Path
 from typing import Any, Literal
 
 import numpy as np
+import psutil
 from leann.interface import (
     LeannBackendBuilderInterface,
     LeannBackendFactoryInterface,
@@ -84,6 +85,43 @@ def _write_vectors_to_bin(data: np.ndarray, file_path: Path):
         f.write(data.tobytes())
 
 
+def _calculate_smart_memory_config(data: np.ndarray) -> tuple[float, float]:
+    """
+    Calculate smart memory configuration for DiskANN based on data size and system specs.
+
+    Args:
+        data: The embedding data array
+
+    Returns:
+        tuple: (search_memory_maximum, build_memory_maximum) in GB
+    """
+    num_vectors, dim = data.shape
+
+    # Calculate embedding storage size
+    embedding_size_bytes = num_vectors * dim * 4  # float32 = 4 bytes
+    embedding_size_gb = embedding_size_bytes / (1024**3)
+
+    # search_memory_maximum: 1/10 of embedding size for optimal PQ compression
+    # This controls Product Quantization size - smaller means more compression
+    search_memory_gb = max(0.1, embedding_size_gb / 10)  # At least 100MB
+
+    # build_memory_maximum: Based on available system RAM for sharding control
+    # This controls how much memory DiskANN uses during index construction
+    available_memory_gb = psutil.virtual_memory().available / (1024**3)
+    total_memory_gb = psutil.virtual_memory().total / (1024**3)
+
+    # Use 50% of available memory, but at least 2GB and at most 75% of total
+    build_memory_gb = max(2.0, min(available_memory_gb * 0.5, total_memory_gb * 0.75))
+
+    logger.info(
+        f"Smart memory config - Data: {embedding_size_gb:.2f}GB, "
+        f"Search mem: {search_memory_gb:.2f}GB (PQ control), "
+        f"Build mem: {build_memory_gb:.2f}GB (sharding control)"
+    )
+
+    return search_memory_gb, build_memory_gb
+
+
 @register_backend("diskann")
 class DiskannBackend(LeannBackendFactoryInterface):
     @staticmethod
@@ -121,6 +159,16 @@ class DiskannBuilder(LeannBackendBuilderInterface):
                 f"Unsupported distance_metric '{build_kwargs.get('distance_metric', 'unknown')}'."
             )
 
+        # Calculate smart memory configuration if not explicitly provided
+        if (
+            "search_memory_maximum" not in build_kwargs
+            or "build_memory_maximum" not in build_kwargs
+        ):
+            smart_search_mem, smart_build_mem = _calculate_smart_memory_config(data)
+        else:
+            smart_search_mem = build_kwargs.get("search_memory_maximum", 4.0)
+            smart_build_mem = build_kwargs.get("build_memory_maximum", 8.0)
+
         try:
             from . import _diskannpy as diskannpy  # type: ignore
 
@@ -131,8 +179,8 @@ class DiskannBuilder(LeannBackendBuilderInterface):
                     index_prefix,
                     build_kwargs.get("complexity", 64),
                     build_kwargs.get("graph_degree", 32),
-                    build_kwargs.get("search_memory_maximum", 4.0),
-                    build_kwargs.get("build_memory_maximum", 8.0),
+                    build_kwargs.get("search_memory_maximum", smart_search_mem),
+                    build_kwargs.get("build_memory_maximum", smart_build_mem),
                     build_kwargs.get("num_threads", 8),
                     build_kwargs.get("pq_disk_bytes", 0),
                     "",

packages/leann-backend-diskann/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-diskann"
-version = "0.1.16"
-dependencies = ["leann-core==0.1.16", "numpy", "protobuf>=3.19.0"]
+version = "0.2.0"
+dependencies = ["leann-core==0.2.0", "numpy", "protobuf>=3.19.0"]
 
 [tool.scikit-build]
 # Key: simplified CMake path

packages/leann-backend-hnsw/pyproject.toml

@@ -6,10 +6,10 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-hnsw"
-version = "0.1.16"
+version = "0.2.0"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.1.16",
+    "leann-core==0.2.0",
     "numpy",
     "pyzmq>=23.0.0",
     "msgpack>=1.0.0",

packages/leann-core/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann-core"
-version = "0.1.16"
+version = "0.2.0"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"

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

@@ -636,7 +636,10 @@ class LeannChat:
             "Please provide the best answer you can based on this context and your knowledge."
         )
 
+        ask_time = time.time()
         ans = self.llm.ask(prompt, **llm_kwargs)
+        ask_time = time.time() - ask_time
+        logger.info(f"  Ask time: {ask_time} seconds")
         return ans
 
     def start_interactive(self):

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

@@ -358,7 +358,11 @@ def validate_model_and_suggest(model_name: str, llm_type: str) -> str | None:
                 error_msg += f"\n\nModel '{model_name}' was not found in Ollama's library."
 
                 if suggestions:
-                    error_msg += "\n\nDid you mean one of these installed models?\n"
+                    error_msg += (
+                        "\n\nDid you mean one of these installed models?\n"
+                        + "\nTry to use ollama pull to install the model you need\n"
+                    )
+
                     for i, suggestion in enumerate(suggestions, 1):
                         error_msg += f"  {i}. {suggestion}\n"
                 else:
@@ -542,14 +546,41 @@ class HFChat(LLMInterface):
             self.device = "cpu"
             logger.info("No GPU detected. Using CPU.")
 
-        # Load tokenizer and model
-        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
-        self.model = AutoModelForCausalLM.from_pretrained(
-            model_name,
-            torch_dtype=torch.float16 if self.device != "cpu" else torch.float32,
-            device_map="auto" if self.device != "cpu" else None,
-            trust_remote_code=True,
-        )
+        # Load tokenizer and model with timeout protection
+        try:
+            import signal
+
+            def timeout_handler(signum, frame):
+                raise TimeoutError("Model download/loading timed out")
+
+            # Set timeout for model loading (60 seconds)
+            old_handler = signal.signal(signal.SIGALRM, timeout_handler)
+            signal.alarm(60)
+
+            try:
+                logger.info(f"Loading tokenizer for {model_name}...")
+                self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+                logger.info(f"Loading model {model_name}...")
+                self.model = AutoModelForCausalLM.from_pretrained(
+                    model_name,
+                    torch_dtype=torch.float16 if self.device != "cpu" else torch.float32,
+                    device_map="auto" if self.device != "cpu" else None,
+                    trust_remote_code=True,
+                )
+                logger.info(f"Successfully loaded {model_name}")
+            finally:
+                signal.alarm(0)  # Cancel the alarm
+                signal.signal(signal.SIGALRM, old_handler)  # Restore old handler
+
+        except TimeoutError:
+            logger.error(f"Model loading timed out for {model_name}")
+            raise RuntimeError(
+                f"Model loading timed out for {model_name}. Please check your internet connection or try a smaller model."
+            )
+        except Exception as e:
+            logger.error(f"Failed to load model {model_name}: {e}")
+            raise
 
         # Move model to device if not using device_map
         if self.device != "cpu" and "device_map" not in str(self.model):

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

@@ -354,13 +354,21 @@ class EmbeddingServerManager:
         self.server_process.terminate()
 
         try:
-            self.server_process.wait(timeout=5)
+            self.server_process.wait(timeout=3)
             logger.info(f"Server process {self.server_process.pid} terminated.")
         except subprocess.TimeoutExpired:
             logger.warning(
-                f"Server process {self.server_process.pid} did not terminate gracefully, killing it."
+                f"Server process {self.server_process.pid} did not terminate gracefully within 3 seconds, killing it."
             )
             self.server_process.kill()
+            try:
+                self.server_process.wait(timeout=2)
+                logger.info(f"Server process {self.server_process.pid} killed successfully.")
+            except subprocess.TimeoutExpired:
+                logger.error(
+                    f"Failed to kill server process {self.server_process.pid} - it may be hung"
+                )
+                # Don't hang indefinitely
 
         # Clean up process resources to prevent resource tracker warnings
         try:

packages/leann/README.md

@@ -5,11 +5,8 @@ LEANN is a revolutionary vector database that democratizes personal AI. Transfor
 ## Installation
 
 ```bash
-# Default installation (HNSW backend, recommended)
+# Default installation (includes both HNSW and DiskANN backends)
 uv pip install leann
-
-# With DiskANN backend (for large-scale deployments)
-uv pip install leann[diskann]
 ```
 
 ## Quick Start
@@ -19,8 +16,8 @@ from leann import LeannBuilder, LeannSearcher, LeannChat
 from pathlib import Path
 INDEX_PATH = str(Path("./").resolve() / "demo.leann")
 
-# Build an index
-builder = LeannBuilder(backend_name="hnsw")
+# Build an index (choose backend: "hnsw" or "diskann")
+builder = LeannBuilder(backend_name="hnsw")  # or "diskann" for large-scale deployments
 builder.add_text("LEANN saves 97% storage compared to traditional vector databases.")
 builder.add_text("Tung Tung Tung Sahur called—they need their banana‑crocodile hybrid back")
 builder.build_index(INDEX_PATH)

packages/leann/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann"
-version = "0.1.16"
+version = "0.2.0"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -24,16 +24,15 @@ classifiers = [
     "Programming Language :: Python :: 3.12",
 ]
 
-# Default installation: core + hnsw
+# Default installation: core + hnsw + diskann
 dependencies = [
     "leann-core>=0.1.0",
     "leann-backend-hnsw>=0.1.0",
+    "leann-backend-diskann>=0.1.0",
 ]
 
 [project.optional-dependencies]
-diskann = [
-    "leann-backend-diskann>=0.1.0",
-]
+# All backends now included by default
 
 [project.urls]
 Repository = "https://github.com/yichuan-w/LEANN"