chore: release v0.1.15

* fix: auto-detect normalized embeddings and use cosine distance

- Add automatic detection for normalized embedding models (OpenAI, Voyage AI, Cohere)
- Automatically set distance_metric='cosine' for normalized embeddings
- Add warnings when using non-optimal distance metrics
- Implement manual L2 normalization in HNSW backend (custom Faiss build lacks normalize_L2)
- Fix DiskANN zmq_port compatibility with lazy loading strategy
- Add documentation for normalized embeddings feature

This fixes the low accuracy issue when using OpenAI text-embedding-3-small model with default MIPS metric.

* style: format

.pre-commit-config.yaml

@@ -9,15 +9,8 @@ repos:
       - id: check-merge-conflict
       - id: debug-statements
 
-  - repo: https://github.com/psf/black
-    rev: 24.1.1
-    hooks:
-      - id: black
-        language_version: python3
-
   - repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.2.1
     hooks:
       - id: ruff
-        args: [--fix]
       - id: ruff-format

README.md

@@ -33,12 +33,46 @@ LEANN achieves this through *graph-based selective recomputation* with *high-deg
 
 🪶 **Lightweight:** Graph-based recomputation eliminates heavy embedding storage, while smart graph pruning and CSR format minimize graph storage overhead. Always less storage, less memory usage!
 
+📦 **Portable:** Transfer your entire knowledge base between devices (even with others) with minimal cost - your personal AI memory travels with you.
+
 📈 **Scalability:** Handle messy personal data that would crash traditional vector DBs, easily managing your growing personalized data and agent generated memory!
 
 ✨ **No Accuracy Loss:** Maintain the same search quality as heavyweight solutions while using 97% less storage.
 
 ## Installation
-> `pip leann` coming soon!
+
+<details>
+<summary><strong>📦 Prerequisites: Install uv (if you don't have it)</strong></summary>
+
+Install uv first if you don't have it:
+
+```bash
+curl -LsSf https://astral.sh/uv/install.sh | sh
+```
+
+📖 [Detailed uv installation methods →](https://docs.astral.sh/uv/getting-started/installation/#installation-methods)
+
+</details>
+
+
+LEANN provides two installation methods: **pip install** (quick and easy) and **build from source** (recommended for development).
+
+
+
+### 🚀 Quick Install (Recommended for most users)
+
+Clone the repository to access all examples and install LEANN from [PyPI](https://pypi.org/project/leann/) to run them immediately:
+
+```bash
+git clone git@github.com:yichuan-w/LEANN.git leann
+cd leann
+uv venv
+source .venv/bin/activate
+uv pip install leann
+```
+
+### 🔧 Build from Source (Recommended for development)
+
 ```bash
 git clone git@github.com:yichuan-w/LEANN.git leann
 cd leann
@@ -48,27 +82,65 @@ git submodule update --init --recursive
 **macOS:**
 ```bash
 brew install llvm libomp boost protobuf zeromq pkgconf
-
-# Install with HNSW backend (default, recommended for most users)
-# Install uv first if you don't have it:
-# curl -LsSf https://astral.sh/uv/install.sh | sh
-# See: https://docs.astral.sh/uv/getting-started/installation/#installation-methods
 CC=$(brew --prefix llvm)/bin/clang CXX=$(brew --prefix llvm)/bin/clang++ uv sync
 ```
 
 **Linux:**
 ```bash
 sudo apt-get install libomp-dev libboost-all-dev protobuf-compiler libabsl-dev libmkl-full-dev libaio-dev libzmq3-dev
-
-# Install with HNSW backend (default, recommended for most users)
 uv sync
 ```
 
 
-**Ollama Setup (Recommended for full privacy):**
 
-> *You can skip this installation if you only want to use OpenAI API for generation.*
 
+## Quick Star
+
+Our declarative API makes RAG as easy as writing a config file.
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yichuan-w/LEANN/blob/main/demo.ipynb) [Try in this ipynb file →](demo.ipynb)
+
+```python
+from leann import LeannBuilder, LeannSearcher, LeannCha
+from pathlib import Path
+INDEX_PATH = str(Path("./").resolve() / "demo.leann")
+
+# Build an index
+builder = LeannBuilder(backend_name="hnsw")
+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)
+
+# Search
+searcher = LeannSearcher(INDEX_PATH)
+results = searcher.search("fantastical AI-generated creatures", top_k=1)
+
+# Chat with your data
+chat = LeannChat(INDEX_PATH, llm_config={"type": "hf", "model": "Qwen/Qwen3-0.6B"})
+response = chat.ask("How much storage does LEANN save?", top_k=1)
+```
+
+## RAG on Everything!
+
+LEANN supports RAG on various data sources including documents (.pdf, .txt, .md), Apple Mail, Google Search History, WeChat, and more.
+
+
+> **Generation Model Setup**
+> LEANN supports multiple LLM providers for text generation (OpenAI API, HuggingFace, Ollama).
+
+<details>
+<summary><strong>🔑 OpenAI API Setup (Default)</strong></summary>
+
+Set your OpenAI API key as an environment variable:
+
+```bash
+export OPENAI_API_KEY="your-api-key-here"
+```
+
+</details>
+
+<details>
+<summary><strong>🔧 Ollama Setup (Recommended for full privacy)</strong></summary>
 
 **macOS:**
 
@@ -80,6 +152,7 @@ ollama pull llama3.2:1b
 ```
 
 **Linux:**
+
 ```bash
 # Install Ollama
 curl -fsSL https://ollama.ai/install.sh | sh
@@ -91,43 +164,7 @@ ollama serve &
 ollama pull llama3.2:1b
 ```
 
-## Quick Start in 30s
+</details>
-
-Our declarative API makes RAG as easy as writing a config file.
-[Try in this ipynb file →](demo.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yichuan-w/LEANN/blob/main/demo.ipynb)
-
-```python
-from leann.api import LeannBuilder, LeannSearcher, LeannChat
-
-# 1. Build the index (no embeddings stored!)
-builder = LeannBuilder(backend_name="hnsw")
-builder.add_text("C# is a powerful programming language")
-builder.add_text("Python is a powerful programming language and it is very popular")
-builder.add_text("Machine learning transforms industries")
-builder.add_text("Neural networks process complex data")
-builder.add_text("Leann is a great storage saving engine for RAG on your MacBook")
-builder.build_index("knowledge.leann")
-
-# 2. Search with real-time embeddings
-searcher = LeannSearcher("knowledge.leann")
-results = searcher.search("programming languages", top_k=2)
-
-# 3. Chat with LEANN using retrieved results
-llm_config = {
-    "type": "ollama",
-    "model": "llama3.2:1b"
-}
-
-chat = LeannChat(index_path="knowledge.leann", llm_config=llm_config)
-response = chat.ask(
-    "Compare the two retrieved programming languages and say which one is more popular today.",
-    top_k=2,
-)
-```
-
-## RAG on Everything!
-
-LEANN supports RAG on various data sources including documents (.pdf, .txt, .md), Apple Mail, Google Search History, WeChat, and more.
 
 ### 📄 Personal Data Manager: Process Any Documents (.pdf, .txt, .md)!
 
@@ -139,11 +176,6 @@ Ask questions directly about your personal PDFs, documents, and any directory co
 
 The example below asks a question about summarizing two papers (uses default data in `examples/data`):
 
-```bash
-# Drop your PDFs, .txt, .md files into examples/data/
-uv run ./examples/main_cli_example.py
-```
-
 ```
 # Or use python directly
 source .venv/bin/activate
@@ -154,6 +186,9 @@ python ./examples/main_cli_example.py
 
 ### 📧 Your Personal Email Secretary: RAG on Apple Mail!
 
+> **Note:** The examples below currently support macOS only. Windows support coming soon.
+
+
 <p align="center">
   <img src="videos/mail_clear.gif" alt="LEANN Email Search Demo" width="600">
 </p>
@@ -233,7 +268,7 @@ The default Chrome profile path is configured for a typical macOS setup. If you
 1. Open Terminal
 2. Run: `ls ~/Library/Application\ Support/Google/Chrome/`
 3. Look for folders like "Default", "Profile 1", "Profile 2", etc.
-4. Use the full path as your `--chrome-profile` argument
+4. Use the full path as your `--chrome-profile` argumen
 
 **Common Chrome profile locations:**
 - macOS: `~/Library/Application Support/Google/Chrome/Default`
@@ -276,7 +311,7 @@ sudo packages/wechat-exporter/wechattweak-cli install
 
 **Troubleshooting:**
 - **Installation issues**: Check the [WeChatTweak-CLI issues page](https://github.com/sunnyyoung/WeChatTweak-CLI/issues/41)
-- **Export errors**: If you encounter the error below, try restarting WeChat
+- **Export errors**: If you encounter the error below, try restarting WeCha
 ```
 Failed to export WeChat data. Please ensure WeChat is running and WeChatTweak is installed.
 Failed to find or export WeChat data. Exiting.
@@ -331,7 +366,7 @@ leann search my-docs "machine learning concepts"
 leann ask my-docs --interactive
 
 # List all your indexes
-leann list
+leann lis
 ```
 
 **Key CLI features:**
@@ -416,7 +451,7 @@ Options:
 
 ```bash
 uv pip install -e ".[dev]"  # Install dev dependencies
-python examples/run_evaluation.py data/indices/dpr/dpr_diskann      # DPR dataset
+python examples/run_evaluation.py data/indices/dpr/dpr_diskann      # DPR datase
 python examples/run_evaluation.py data/indices/rpj_wiki/rpj_wiki.index  # Wikipedia
 ```
 
@@ -441,10 +476,10 @@ If you find Leann useful, please cite:
 
 ## ✨ [Detailed Features →](docs/features.md)
 
-## 🤝 [Contributing →](docs/contributing.md)
+## 🤝 [CONTRIBUTING →](docs/CONTRIBUTING.md)
 
 
-## [FAQ →](docs/faq.md)
+## ❓ [FAQ →](docs/faq.md)
 
 
 ## 📈 [Roadmap →](docs/roadmap.md)
@@ -465,4 +500,3 @@ This work is done at [**Berkeley Sky Computing Lab**](https://sky.cs.berkeley.e
 <p align="center">
   Made with ❤️ by the Leann team
 </p>
-

demo.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Quick Start in 30s\n",
+    "# Quick Start \n",
     "\n",
     "**Home GitHub Repository:** [LEANN on GitHub](https://github.com/yichuan-w/LEANN)\n",
     "\n",
@@ -49,68 +49,7 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [
+   "outputs": [],
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Writing passages: 100%|██████████| 5/5 [00:00<00:00, 17077.79chunk/s]\n",
-      "Batches: 100%|██████████| 1/1 [00:00<00:00, 36.43it/s]\n",
-      "WARNING:leann_backend_hnsw.hnsw_backend:Converting data to float32, shape: (5, 768)\n",
-      "INFO:leann_backend_hnsw.hnsw_backend:INFO: Converting HNSW index to CSR-pruned format...\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "M: 64 for level: 0\n",
-      "Starting conversion: index.index -> index.csr.tmp\n",
-      "[0.00s] Reading Index HNSW header...\n",
-      "[0.00s]   Header read: d=768, ntotal=5\n",
-      "[0.00s] Reading HNSW struct vectors...\n",
-      "  Reading vector (dtype=<class 'numpy.float64'>, fmt='d')... Count=6, Bytes=48\n",
-      "[0.00s]   Read assign_probas (6)\n",
-      "  Reading vector (dtype=<class 'numpy.int32'>, fmt='i')... Count=7, Bytes=28\n",
-      "[0.14s]   Read cum_nneighbor_per_level (7)\n",
-      "  Reading vector (dtype=<class 'numpy.int32'>, fmt='i')... Count=5, Bytes=20\n",
-      "[0.24s]   Read levels (5)\n",
-      "[0.33s]   Probing for compact storage flag...\n",
-      "[0.33s]   Found compact flag: False\n",
-      "[0.33s]   Compact flag is False, reading original format...\n",
-      "[0.33s]   Probing for potential extra byte before non-compact offsets...\n",
-      "[0.33s]   Found and consumed an unexpected 0x00 byte.\n",
-      "  Reading vector (dtype=<class 'numpy.uint64'>, fmt='Q')... Count=6, Bytes=48\n",
-      "[0.33s]   Read offsets (6)\n",
-      "[0.41s]   Attempting to read neighbors vector...\n",
-      "  Reading vector (dtype=<class 'numpy.int32'>, fmt='i')... Count=320, Bytes=1280\n",
-      "[0.41s]   Read neighbors (320)\n",
-      "[0.54s]   Read scalar params (ep=4, max_lvl=0)\n",
-      "[0.54s] Checking for storage data...\n",
-      "[0.54s]   Found storage fourcc: 49467849.\n",
-      "[0.54s] Converting to CSR format...\n",
-      "[0.54s]   Conversion loop finished.                        \n",
-      "[0.54s] Running validation checks...\n",
-      "    Checking total valid neighbor count...\n",
-      "    OK: Total valid neighbors = 20\n",
-      "    Checking final pointer indices...\n",
-      "    OK: Final pointers match data size.\n",
-      "[0.54s] Deleting original neighbors and offsets arrays...\n",
-      "    CSR Stats: |data|=20, |level_ptr|=10\n",
-      "[0.63s] Writing CSR HNSW graph data in FAISS-compatible order...\n",
-      "   Pruning embeddings: Writing NULL storage marker.\n",
-      "[0.71s] Conversion complete.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "INFO:leann_backend_hnsw.hnsw_backend:✅ CSR conversion successful.\n",
-      "INFO:leann_backend_hnsw.hnsw_backend:INFO: Replaced original index with CSR-pruned version at 'index.index'\n"
-     ]
-    }
-   ],
    "source": [
     "from leann.api import LeannBuilder\n",
     "\n",
@@ -136,81 +75,7 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [
+   "outputs": [],
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "INFO:leann.api:🔍 LeannSearcher.search() called:\n",
-      "INFO:leann.api:  Query: 'programming languages'\n",
-      "INFO:leann.api:  Top_k: 2\n",
-      "INFO:leann.api:  Additional kwargs: {}\n",
-      "INFO:leann.embedding_server_manager:Port 5557 has incompatible server, trying next port...\n",
-      "INFO:leann.embedding_server_manager:Port 5558 has incompatible server, trying next port...\n",
-      "INFO:leann.embedding_server_manager:Port 5559 has incompatible server, trying next port...\n",
-      "INFO:leann.embedding_server_manager:Port 5560 has incompatible server, trying next port...\n",
-      "INFO:leann.embedding_server_manager:Port 5561 has incompatible server, trying next port...\n",
-      "INFO:leann.embedding_server_manager:Port 5562 has incompatible server, trying next port...\n",
-      "INFO:leann.embedding_server_manager:Starting embedding server on port 5563...\n",
-      "INFO:leann.embedding_server_manager:Command: /Users/yichuan/Desktop/code/test_leann_pip/LEANN/.venv/bin/python -m leann_backend_hnsw.hnsw_embedding_server --zmq-port 5563 --model-name facebook/contriever --passages-file /Users/yichuan/Desktop/code/test_leann_pip/LEANN/content/index.meta.json\n",
-      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
-      "To disable this warning, you can either:\n",
-      "\t- Avoid using `tokenizers` before the fork if possible\n",
-      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
-      "INFO:leann.embedding_server_manager:Server process started with PID: 31699\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[read_HNSW - CSR NL v4] Reading metadata & CSR indices (manual offset)...\n",
-      "[read_HNSW NL v4] Read levels vector, size: 5\n",
-      "[read_HNSW NL v4] Reading Compact Storage format indices...\n",
-      "[read_HNSW NL v4] Read compact_level_ptr, size: 10\n",
-      "[read_HNSW NL v4] Read compact_node_offsets, size: 6\n",
-      "[read_HNSW NL v4] Read entry_point: 4, max_level: 0\n",
-      "[read_HNSW NL v4] Read storage fourcc: 0x6c6c756e\n",
-      "[read_HNSW NL v4 FIX] Detected FileIOReader. Neighbors size field offset: 326\n",
-      "[read_HNSW NL v4] Reading neighbors data into memory.\n",
-      "[read_HNSW NL v4] Read neighbors data, size: 20\n",
-      "[read_HNSW NL v4] Finished reading metadata and CSR indices.\n",
-      "INFO: Skipping external storage loading, since is_recompute is true.\n",
-      "INFO: Registering backend 'hnsw'\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Traceback (most recent call last):\n",
-      "  File \"<frozen runpy>\", line 198, in _run_module_as_main\n",
-      "  File \"<frozen runpy>\", line 88, in _run_code\n",
-      "  File \"/Users/yichuan/Desktop/code/test_leann_pip/LEANN/.venv/lib/python3.11/site-packages/leann_backend_hnsw/hnsw_embedding_server.py\", line 323, in <module>\n",
-      "    create_hnsw_embedding_server(\n",
-      "  File \"/Users/yichuan/Desktop/code/test_leann_pip/LEANN/.venv/lib/python3.11/site-packages/leann_backend_hnsw/hnsw_embedding_server.py\", line 98, in create_hnsw_embedding_server\n",
-      "    passages = PassageManager(passage_sources)\n",
-      "               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"/Users/yichuan/Desktop/code/test_leann_pip/LEANN/.venv/lib/python3.11/site-packages/leann/api.py\", line 127, in __init__\n",
-      "    raise FileNotFoundError(f\"Passage index file not found: {index_file}\")\n",
-      "FileNotFoundError: Passage index file not found: /Users/yichuan/Desktop/code/test_leann_pip/LEANN/index.passages.idx\n",
-      "ERROR:leann.embedding_server_manager:Server terminated during startup.\n"
-     ]
-    },
-    {
-     "ename": "RuntimeError",
-     "evalue": "Failed to start embedding server on port 5563",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
-      "\u001b[31mRuntimeError\u001b[39m                              Traceback (most recent call last)",
-      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[4]\u001b[39m\u001b[32m, line 4\u001b[39m\n\u001b[32m      1\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mleann\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mapi\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m LeannSearcher\n\u001b[32m      3\u001b[39m searcher = LeannSearcher(\u001b[33m\"\u001b[39m\u001b[33mindex\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m----> \u001b[39m\u001b[32m4\u001b[39m results = \u001b[43msearcher\u001b[49m\u001b[43m.\u001b[49m\u001b[43msearch\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mprogramming languages\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_k\u001b[49m\u001b[43m=\u001b[49m\u001b[32;43m2\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[32m      5\u001b[39m results\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m~/Desktop/code/test_leann_pip/LEANN/.venv/lib/python3.11/site-packages/leann/api.py:439\u001b[39m, in \u001b[36mLeannSearcher.search\u001b[39m\u001b[34m(self, query, top_k, complexity, beam_width, prune_ratio, recompute_embeddings, pruning_strategy, expected_zmq_port, **kwargs)\u001b[39m\n\u001b[32m    437\u001b[39m start_time = time.time()\n\u001b[32m    438\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m recompute_embeddings:\n\u001b[32m--> \u001b[39m\u001b[32m439\u001b[39m     zmq_port = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mbackend_impl\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_ensure_server_running\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    440\u001b[39m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mmeta_path_str\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    441\u001b[39m \u001b[43m        \u001b[49m\u001b[43mport\u001b[49m\u001b[43m=\u001b[49m\u001b[43mexpected_zmq_port\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    442\u001b[39m \u001b[43m        \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    443\u001b[39m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    444\u001b[39m     \u001b[38;5;28;01mdel\u001b[39;00m expected_zmq_port\n\u001b[32m    445\u001b[39m zmq_time = time.time() - start_time\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m~/Desktop/code/test_leann_pip/LEANN/.venv/lib/python3.11/site-packages/leann/searcher_base.py:81\u001b[39m, in \u001b[36mBaseSearcher._ensure_server_running\u001b[39m\u001b[34m(self, passages_source_file, port, **kwargs)\u001b[39m\n\u001b[32m     72\u001b[39m server_started, actual_port = \u001b[38;5;28mself\u001b[39m.embedding_server_manager.start_server(\n\u001b[32m     73\u001b[39m     port=port,\n\u001b[32m     74\u001b[39m     model_name=\u001b[38;5;28mself\u001b[39m.embedding_model,\n\u001b[32m   (...)\u001b[39m\u001b[32m     78\u001b[39m     enable_warmup=kwargs.get(\u001b[33m\"\u001b[39m\u001b[33menable_warmup\u001b[39m\u001b[33m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m),\n\u001b[32m     79\u001b[39m )\n\u001b[32m     80\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m server_started:\n\u001b[32m---> \u001b[39m\u001b[32m81\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\n\u001b[32m     82\u001b[39m         \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mFailed to start embedding server on port \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mactual_port\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\n\u001b[32m     83\u001b[39m     )\n\u001b[32m     85\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m actual_port\n",
-      "\u001b[31mRuntimeError\u001b[39m: Failed to start embedding server on port 5563"
-     ]
-    }
-   ],
    "source": [
     "from leann.api import LeannSearcher\n",
     "\n",

docs/CONTRIBUTING.md

@@ -0,0 +1,220 @@
+# 🤝 Contributing
+
+We welcome contributions! Leann is built by the community, for the community.
+
+## Ways to Contribute
+
+- 🐛 **Bug Reports**: Found an issue? Let us know!
+- 💡 **Feature Requests**: Have an idea? We'd love to hear it!
+- 🔧 **Code Contributions**: PRs welcome for all skill levels
+- 📖 **Documentation**: Help make Leann more accessible
+- 🧪 **Benchmarks**: Share your performance results
+
+## 🚀 Development Setup
+
+### Prerequisites
+
+1. **Install uv** (fast Python package installer):
+   ```bash
+   curl -LsSf https://astral.sh/uv/install.sh | sh
+   ```
+
+2. **Clone the repository**:
+   ```bash
+   git clone https://github.com/LEANN-RAG/LEANN-RAG.git
+   cd LEANN-RAG
+   ```
+
+3. **Install system dependencies**:
+
+   **macOS:**
+   ```bash
+   brew install llvm libomp boost protobuf zeromq pkgconf
+   ```
+
+   **Ubuntu/Debian:**
+   ```bash
+   sudo apt-get install libomp-dev libboost-all-dev protobuf-compiler \
+                        libabsl-dev libmkl-full-dev libaio-dev libzmq3-dev
+   ```
+
+4. **Build from source**:
+   ```bash
+   # macOS
+   CC=$(brew --prefix llvm)/bin/clang CXX=$(brew --prefix llvm)/bin/clang++ uv sync
+
+   # Ubuntu/Debian
+   uv sync
+   ```
+
+## 🔨 Pre-commit Hooks
+
+We use pre-commit hooks to ensure code quality and consistency. This runs automatically before each commit.
+
+### Setup Pre-commit
+
+1. **Install pre-commit** (already included when you run `uv sync`):
+   ```bash
+   uv pip install pre-commit
+   ```
+
+2. **Install the git hooks**:
+   ```bash
+   pre-commit install
+   ```
+
+3. **Run pre-commit manually** (optional):
+   ```bash
+   pre-commit run --all-files
+   ```
+
+### Pre-commit Checks
+
+Our pre-commit configuration includes:
+- **Trailing whitespace removal**
+- **End-of-file fixing**
+- **YAML validation**
+- **Large file prevention**
+- **Merge conflict detection**
+- **Debug statement detection**
+- **Code formatting with ruff**
+- **Code linting with ruff**
+
+## 🧪 Testing
+
+### Running Tests
+
+```bash
+# Run all tests
+uv run pytest
+
+# Run specific test file
+uv run pytest test/test_filename.py
+
+# Run with coverage
+uv run pytest --cov=leann
+```
+
+### Writing Tests
+
+- Place tests in the `test/` directory
+- Follow the naming convention `test_*.py`
+- Use descriptive test names that explain what's being tested
+- Include both positive and negative test cases
+
+## 📝 Code Style
+
+We use `ruff` for both linting and formatting to ensure consistent code style.
+
+### Format Your Code
+
+```bash
+# Format all files
+ruff format
+
+# Check formatting without changing files
+ruff format --check
+```
+
+### Lint Your Code
+
+```bash
+# Run linter with auto-fix
+ruff check --fix
+
+# Just check without fixing
+ruff check
+```
+
+### Style Guidelines
+
+- Follow PEP 8 conventions
+- Use descriptive variable names
+- Add type hints where appropriate
+- Write docstrings for all public functions and classes
+- Keep functions focused and single-purpose
+
+## 🚦 CI/CD
+
+Our CI pipeline runs automatically on all pull requests. It includes:
+
+1. **Linting and Formatting**: Ensures code follows our style guidelines
+2. **Multi-platform builds**: Tests on Ubuntu and macOS
+3. **Python version matrix**: Tests on Python 3.9-3.13
+4. **Wheel building**: Ensures packages can be built and distributed
+
+### CI Commands
+
+The CI uses the same commands as pre-commit to ensure consistency:
+```bash
+# Linting
+ruff check .
+
+# Format checking
+ruff format --check .
+```
+
+Make sure your code passes these checks locally before pushing!
+
+## 🔄 Pull Request Process
+
+1. **Fork the repository** and create your branch from `main`:
+   ```bash
+   git checkout -b feature/your-feature-name
+   ```
+
+2. **Make your changes**:
+   - Write clean, documented code
+   - Add tests for new functionality
+   - Update documentation as needed
+
+3. **Run pre-commit checks**:
+   ```bash
+   pre-commit run --all-files
+   ```
+
+4. **Test your changes**:
+   ```bash
+   uv run pytest
+   ```
+
+5. **Commit with descriptive messages**:
+   ```bash
+   git commit -m "feat: add new search algorithm"
+   ```
+
+   Follow [Conventional Commits](https://www.conventionalcommits.org/):
+   - `feat:` for new features
+   - `fix:` for bug fixes
+   - `docs:` for documentation changes
+   - `test:` for test additions/changes
+   - `refactor:` for code refactoring
+   - `perf:` for performance improvements
+
+6. **Push and create a pull request**:
+   - Provide a clear description of your changes
+   - Reference any related issues
+   - Include examples or screenshots if applicable
+
+## 📚 Documentation
+
+When adding new features or making significant changes:
+
+1. Update relevant documentation in `/docs`
+2. Add docstrings to new functions/classes
+3. Update README.md if needed
+4. Include usage examples
+
+## 🤔 Getting Help
+
+- **Discord**: Join our community for discussions
+- **Issues**: Check existing issues or create a new one
+- **Discussions**: For general questions and ideas
+
+## 📄 License
+
+By contributing, you agree that your contributions will be licensed under the same license as the project (MIT).
+
+---
+
+Thank you for contributing to LEANN! Every contribution, no matter how small, helps make the project better for everyone. 🌟

docs/contributing.md

@@ -1,11 +0,0 @@
-# 🤝 Contributing
-
-We welcome contributions! Leann is built by the community, for the community.
-
-## Ways to Contribute
-
-- 🐛 **Bug Reports**: Found an issue? Let us know!
-- 💡 **Feature Requests**: Have an idea? We'd love to hear it!
-- 🔧 **Code Contributions**: PRs welcome for all skill levels
-- 📖 **Documentation**: Help make Leann more accessible
-- 🧪 **Benchmarks**: Share your performance results 

docs/normalized_embeddings.md

@@ -0,0 +1,75 @@
+# Normalized Embeddings Support in LEANN
+
+LEANN now automatically detects normalized embedding models and sets the appropriate distance metric for optimal performance.
+
+## What are Normalized Embeddings?
+
+Normalized embeddings are vectors with L2 norm = 1 (unit vectors). These embeddings are optimized for cosine similarity rather than Maximum Inner Product Search (MIPS).
+
+## Automatic Detection
+
+When you create a `LeannBuilder` instance with a normalized embedding model, LEANN will:
+
+1. **Automatically set `distance_metric="cosine"`** if not specified
+2. **Show a warning** if you manually specify a different distance metric
+3. **Provide optimal search performance** with the correct metric
+
+## Supported Normalized Embedding Models
+
+### OpenAI
+All OpenAI text embedding models are normalized:
+- `text-embedding-ada-002`
+- `text-embedding-3-small`
+- `text-embedding-3-large`
+
+### Voyage AI
+All Voyage AI embedding models are normalized:
+- `voyage-2`
+- `voyage-3`
+- `voyage-large-2`
+- `voyage-multilingual-2`
+- `voyage-code-2`
+
+### Cohere
+All Cohere embedding models are normalized:
+- `embed-english-v3.0`
+- `embed-multilingual-v3.0`
+- `embed-english-light-v3.0`
+- `embed-multilingual-light-v3.0`
+
+## Example Usage
+
+```python
+from leann.api import LeannBuilder
+
+# Automatic detection - will use cosine distance
+builder = LeannBuilder(
+    backend_name="hnsw",
+    embedding_model="text-embedding-3-small",
+    embedding_mode="openai"
+)
+# Warning: Detected normalized embeddings model 'text-embedding-3-small'...
+# Automatically setting distance_metric='cosine'
+
+# Manual override (not recommended)
+builder = LeannBuilder(
+    backend_name="hnsw",
+    embedding_model="text-embedding-3-small",
+    embedding_mode="openai",
+    distance_metric="mips"  # Will show warning
+)
+# Warning: Using 'mips' distance metric with normalized embeddings...
+```
+
+## Non-Normalized Embeddings
+
+Models like `facebook/contriever` and other sentence-transformers models that are not normalized will continue to use MIPS by default, which is optimal for them.
+
+## Why This Matters
+
+Using the wrong distance metric with normalized embeddings can lead to:
+- **Poor search quality** due to HNSW's early termination with narrow score ranges
+- **Incorrect ranking** of search results
+- **Suboptimal performance** compared to using the correct metric
+
+For more details on why this happens, see our analysis of [OpenAI embeddings with MIPS](../examples/main_cli_example.py).

examples/data/PrideandPrejudice.txt

@@ -14903,5 +14903,3 @@ This website includes information about Project Gutenberg™,
 including how to make donations to the Project Gutenberg Literary
 Archive Foundation, how to help produce our new eBooks, and how to
 subscribe to our email newsletter to hear about new eBooks.
-
-

examples/document_search.py

@@ -27,7 +27,10 @@ def load_sample_documents():
             "title": "Intro to Python",
             "content": "Python is a high-level, interpreted language known for simplicity.",
         },
-        {"title": "ML Basics", "content": "Machine learning builds systems that learn from data."},
+        {
+            "title": "ML Basics",
+            "content": "Machine learning builds systems that learn from data.",
+        },
         {
             "title": "Data Structures",
             "content": "Data structures like arrays, lists, and graphs organize data.",

examples/google_history_reader_leann.py

@@ -21,7 +21,9 @@ DEFAULT_CHROME_PROFILE = os.path.expanduser("~/Library/Application Support/Googl
 
 
 def create_leann_index_from_multiple_chrome_profiles(
-    profile_dirs: list[Path], index_path: str = "chrome_history_index.leann", max_count: int = -1
+    profile_dirs: list[Path],
+    index_path: str = "chrome_history_index.leann",
+    max_count: int = -1,
 ):
     """
     Create LEANN index from multiple Chrome profile data sources.

examples/history_data/wechat_history.py

@@ -474,7 +474,8 @@ Messages ({len(messages)} messages, {message_group["total_length"]} chars):
                                 message_group, contact_name
                             )
                             doc = Document(
-                                text=doc_content, metadata={"contact_name": contact_name}
+                                text=doc_content,
+                                metadata={"contact_name": contact_name},
                             )
                             docs.append(doc)
                             count += 1

examples/mail_reader_leann.py

@@ -315,7 +315,11 @@ async def main():
 
     # Create or load the LEANN index from all sources
     index_path = create_leann_index_from_multiple_sources(
-        messages_dirs, INDEX_PATH, args.max_emails, args.include_html, args.embedding_model
+        messages_dirs,
+        INDEX_PATH,
+        args.max_emails,
+        args.include_html,
+        args.embedding_model,
     )
 
     if index_path:

examples/mail_reader_llamaindex.py

@@ -92,7 +92,10 @@ def main():
         help="Directory to store the index (default: mail_index_embedded)",
     )
     parser.add_argument(
-        "--max-emails", type=int, default=10000, help="Maximum number of emails to process"
+        "--max-emails",
+        type=int,
+        default=10000,
+        help="Maximum number of emails to process",
     )
     parser.add_argument(
         "--include-html",
@@ -112,7 +115,10 @@ def main():
     else:
         print("Creating new index...")
         index = create_and_save_index(
-            mail_path, save_dir, max_count=args.max_emails, include_html=args.include_html
+            mail_path,
+            save_dir,
+            max_count=args.max_emails,
+            include_html=args.include_html,
         )
     if index:
         queries = [

examples/main_cli_example.py

@@ -30,17 +30,22 @@ async def main(args):
         all_texts = []
         for doc in documents:
             nodes = node_parser.get_nodes_from_documents([doc])
-            for node in nodes:
+            if nodes:
-                all_texts.append(node.get_content())
+                all_texts.extend(node.get_content() for node in nodes)
 
         print("--- Index directory not found, building new index ---")
 
         print("\n[PHASE 1] Building Leann index...")
 
+        # LeannBuilder now automatically detects normalized embeddings and sets appropriate distance metric
+        print(f"Using {args.embedding_model} with {args.embedding_mode} mode")
+
         # Use HNSW backend for better macOS compatibility
         builder = LeannBuilder(
             backend_name="hnsw",
-            embedding_model="facebook/contriever",
+            embedding_model=args.embedding_model,
+            embedding_mode=args.embedding_mode,
+            # distance_metric is automatically set based on embedding model
             graph_degree=32,
             complexity=64,
             is_compact=True,
@@ -89,6 +94,19 @@ if __name__ == "__main__":
         default="Qwen/Qwen3-0.6B",
         help="The model name to use (e.g., 'llama3:8b' for ollama, 'deepseek-ai/deepseek-llm-7b-chat' for hf, 'gpt-4o' for openai).",
     )
+    parser.add_argument(
+        "--embedding-model",
+        type=str,
+        default="facebook/contriever",
+        help="The embedding model to use (e.g., 'facebook/contriever', 'text-embedding-3-small').",
+    )
+    parser.add_argument(
+        "--embedding-mode",
+        type=str,
+        default="sentence-transformers",
+        choices=["sentence-transformers", "openai", "mlx"],
+        help="The embedding backend mode.",
+    )
     parser.add_argument(
         "--host",
         type=str,

examples/multi_vector_aggregator.py

@@ -347,7 +347,9 @@ def demo_aggregation():
         print(f"\n{'=' * 20} {method.upper()} AGGREGATION {'=' * 20}")
 
         aggregator = MultiVectorAggregator(
-            aggregation_method=method, spatial_clustering=True, cluster_distance_threshold=100.0
+            aggregation_method=method,
+            spatial_clustering=True,
+            cluster_distance_threshold=100.0,
         )
 
         aggregated = aggregator.aggregate_results(mock_results, top_k=5)

packages/__init__.py

@@ -1 +0,0 @@
-

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

@@ -163,18 +163,44 @@ class DiskannSearcher(BaseSearcher):
 
             self.num_threads = kwargs.get("num_threads", 8)
 
-            fake_zmq_port = 6666
+            # For DiskANN, we need to reinitialize the index when zmq_port changes
+            # Store the initialization parameters for later use
             full_index_prefix = str(self.index_dir / self.index_path.stem)
-            self._index = diskannpy.StaticDiskFloatIndex(
+            self._init_params = {
-                metric_enum,
+                "metric_enum": metric_enum,
-                full_index_prefix,
+                "full_index_prefix": full_index_prefix,
-                self.num_threads,
+                "num_threads": self.num_threads,
-                kwargs.get("num_nodes_to_cache", 0),
+                "num_nodes_to_cache": kwargs.get("num_nodes_to_cache", 0),
-                1,
+                "cache_mechanism": 1,
-                fake_zmq_port,  # Initial port, can be updated at runtime
+                "pq_prefix": "",
-                "",
+                "partition_prefix": "",
-                "",
+            }
-            )
+            self._diskannpy = diskannpy
+            self._current_zmq_port = None
+            self._index = None
+            logger.debug("DiskANN searcher initialized (index will be loaded on first search)")
+
+    def _ensure_index_loaded(self, zmq_port: int):
+        """Ensure the index is loaded with the correct zmq_port."""
+        if self._index is None or self._current_zmq_port != zmq_port:
+            # Need to (re)load the index with the correct zmq_port
+            with suppress_cpp_output_if_needed():
+                if self._index is not None:
+                    logger.debug(f"Reloading DiskANN index with new zmq_port: {zmq_port}")
+                else:
+                    logger.debug(f"Loading DiskANN index with zmq_port: {zmq_port}")
+
+                self._index = self._diskannpy.StaticDiskFloatIndex(
+                    self._init_params["metric_enum"],
+                    self._init_params["full_index_prefix"],
+                    self._init_params["num_threads"],
+                    self._init_params["num_nodes_to_cache"],
+                    self._init_params["cache_mechanism"],
+                    zmq_port,
+                    self._init_params["pq_prefix"],
+                    self._init_params["partition_prefix"],
+                )
+                self._current_zmq_port = zmq_port
 
     def search(
         self,
@@ -212,14 +238,15 @@ class DiskannSearcher(BaseSearcher):
         Returns:
             Dict with 'labels' (list of lists) and 'distances' (ndarray)
         """
-        # Handle zmq_port compatibility: DiskANN can now update port at runtime
+        # Handle zmq_port compatibility: Ensure index is loaded with correct port
         if recompute_embeddings:
             if zmq_port is None:
                 raise ValueError("zmq_port must be provided if recompute_embeddings is True")
-            current_port = self._index.get_zmq_port()
+            self._ensure_index_loaded(zmq_port)
-            if zmq_port != current_port:
+        else:
-                logger.debug(f"Updating DiskANN zmq_port from {current_port} to {zmq_port}")
+            # If not recomputing, we still need an index, use a default port
-                self._index.set_zmq_port(zmq_port)
+            if self._index is None:
+                self._ensure_index_loaded(6666)  # Default port when not recomputing
 
         # DiskANN doesn't support "proportional" strategy
         if pruning_strategy == "proportional":

packages/leann-backend-diskann/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-diskann"
-version = "0.1.14"
+version = "0.1.15"
-dependencies = ["leann-core==0.1.14", "numpy", "protobuf>=3.19.0"]
+dependencies = ["leann-core==0.1.15", "numpy", "protobuf>=3.19.0"]
 
 [tool.scikit-build]
 # Key: simplified CMake path

packages/leann-backend-hnsw/leann_backend_hnsw/convert_to_csr.py

@@ -72,7 +72,11 @@ def read_vector_raw(f, element_fmt_char):
 def read_numpy_vector(f, np_dtype, struct_fmt_char):
     """Reads a vector into a NumPy array."""
     count = -1  # Initialize count for robust error handling
-    print(f"  Reading vector (dtype={np_dtype}, fmt='{struct_fmt_char}')... ", end="", flush=True)
+    print(
+        f"  Reading vector (dtype={np_dtype}, fmt='{struct_fmt_char}')... ",
+        end="",
+        flush=True,
+    )
     try:
         count, data_bytes = read_vector_raw(f, struct_fmt_char)
         print(f"Count={count}, Bytes={len(data_bytes)}")
@@ -647,7 +651,10 @@ def convert_hnsw_graph_to_csr(input_filename, output_filename, prune_embeddings=
         print(f"Error: Input file not found: {input_filename}", file=sys.stderr)
         return False
     except MemoryError as e:
-        print(f"\nFatal MemoryError during conversion: {e}. Insufficient RAM.", file=sys.stderr)
+        print(
+            f"\nFatal MemoryError during conversion: {e}. Insufficient RAM.",
+            file=sys.stderr,
+        )
         # Clean up potentially partially written output file?
         try:
             os.remove(output_filename)

packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py

@@ -28,6 +28,12 @@ def get_metric_map():
     }
 
 
+def normalize_l2(data: np.ndarray) -> np.ndarray:
+    norms = np.linalg.norm(data, axis=1, keepdims=True)
+    norms[norms == 0] = 1  # Avoid division by zero
+    return data / norms
+
+
 @register_backend("hnsw")
 class HNSWBackend(LeannBackendFactoryInterface):
     @staticmethod
@@ -76,7 +82,7 @@ class HNSWBuilder(LeannBackendBuilderInterface):
         index.hnsw.efConstruction = self.efConstruction
 
         if self.distance_metric.lower() == "cosine":
-            faiss.normalize_L2(data)
+            data = normalize_l2(data)
 
         index.add(data.shape[0], faiss.swig_ptr(data))
         index_file = index_dir / f"{index_prefix}.index"
@@ -186,7 +192,7 @@ class HNSWSearcher(BaseSearcher):
         if query.dtype != np.float32:
             query = query.astype(np.float32)
         if self.distance_metric == "cosine":
-            faiss.normalize_L2(query)
+            query = normalize_l2(query)
 
         params = faiss.SearchParametersHNSW()
         if zmq_port is not None:

packages/leann-backend-hnsw/pyproject.toml

@@ -6,10 +6,10 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-hnsw"
-version = "0.1.14"
+version = "0.1.15"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.1.14", 
+    "leann-core==0.1.15",
     "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 = "0.1.14"
+version = "0.1.15"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"

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

@@ -7,6 +7,7 @@ import json
 import logging
 import pickle
 import time
+import warnings
 from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Any, Literal
@@ -163,6 +164,76 @@ class LeannBuilder:
         self.embedding_model = embedding_model
         self.dimensions = dimensions
         self.embedding_mode = embedding_mode
+
+        # Check if we need to use cosine distance for normalized embeddings
+        normalized_embeddings_models = {
+            # OpenAI models
+            ("openai", "text-embedding-ada-002"),
+            ("openai", "text-embedding-3-small"),
+            ("openai", "text-embedding-3-large"),
+            # Voyage AI models
+            ("voyage", "voyage-2"),
+            ("voyage", "voyage-3"),
+            ("voyage", "voyage-large-2"),
+            ("voyage", "voyage-multilingual-2"),
+            ("voyage", "voyage-code-2"),
+            # Cohere models
+            ("cohere", "embed-english-v3.0"),
+            ("cohere", "embed-multilingual-v3.0"),
+            ("cohere", "embed-english-light-v3.0"),
+            ("cohere", "embed-multilingual-light-v3.0"),
+        }
+
+        # Also check for patterns in model names
+        is_normalized = False
+        current_model_lower = embedding_model.lower()
+        current_mode_lower = embedding_mode.lower()
+
+        # Check exact matches
+        for mode, model in normalized_embeddings_models:
+            if (current_mode_lower == mode and current_model_lower == model) or (
+                mode in current_mode_lower and model in current_model_lower
+            ):
+                is_normalized = True
+                break
+
+        # Check patterns
+        if not is_normalized:
+            # OpenAI patterns
+            if "openai" in current_mode_lower or "openai" in current_model_lower:
+                if any(
+                    pattern in current_model_lower
+                    for pattern in ["text-embedding", "ada", "3-small", "3-large"]
+                ):
+                    is_normalized = True
+            # Voyage patterns
+            elif "voyage" in current_mode_lower or "voyage" in current_model_lower:
+                is_normalized = True
+            # Cohere patterns
+            elif "cohere" in current_mode_lower or "cohere" in current_model_lower:
+                if "embed" in current_model_lower:
+                    is_normalized = True
+
+        # Handle distance metric
+        if is_normalized and "distance_metric" not in backend_kwargs:
+            backend_kwargs["distance_metric"] = "cosine"
+            warnings.warn(
+                f"Detected normalized embeddings model '{embedding_model}' with mode '{embedding_mode}'. "
+                f"Automatically setting distance_metric='cosine' for optimal performance. "
+                f"Normalized embeddings (L2 norm = 1) should use cosine similarity instead of MIPS.",
+                UserWarning,
+                stacklevel=2,
+            )
+        elif is_normalized and backend_kwargs.get("distance_metric", "").lower() != "cosine":
+            current_metric = backend_kwargs.get("distance_metric", "mips")
+            warnings.warn(
+                f"Warning: Using '{current_metric}' distance metric with normalized embeddings model "
+                f"'{embedding_model}' may lead to suboptimal search results. "
+                f"Consider using 'cosine' distance metric for better performance.",
+                UserWarning,
+                stacklevel=2,
+            )
+
         self.backend_kwargs = backend_kwargs
         self.chunks: list[dict[str, Any]] = []
 

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

@@ -245,7 +245,11 @@ def search_hf_models_fuzzy(query: str, limit: int = 10) -> list[str]:
 
         # HF Hub's search is already fuzzy! It handles typos and partial matches
         models = list_models(
-            search=query, filter="text-generation", sort="downloads", direction=-1, limit=limit
+            search=query,
+            filter="text-generation",
+            sort="downloads",
+            direction=-1,
+            limit=limit,
         )
 
         model_names = [model.id if hasattr(model, "id") else str(model) for model in models]
@@ -582,7 +586,11 @@ class HFChat(LLMInterface):
 
         # Tokenize input
         inputs = self.tokenizer(
-            formatted_prompt, return_tensors="pt", padding=True, truncation=True, max_length=2048
+            formatted_prompt,
+            return_tensors="pt",
+            padding=True,
+            truncation=True,
+            max_length=2048,
         )
 
         # Move inputs to device

packages/leann/README.md

@@ -16,25 +16,24 @@ uv pip install leann[diskann]
 
 ```python
 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")
 builder.add_text("LEANN saves 97% storage compared to traditional vector databases.")
-builder.build_index("my_index.leann")
+builder.add_text("Tung Tung Tung Sahur called—they need their banana‑crocodile hybrid back")
+builder.build_index(INDEX_PATH)
 
 # Search
-searcher = LeannSearcher("my_index.leann")
+searcher = LeannSearcher(INDEX_PATH)
-results = searcher.search("storage savings", top_k=3)
+results = searcher.search("fantastical AI-generated creatures", top_k=1)
 
 # Chat with your data
-chat = LeannChat("my_index.leann", llm_config={"type": "ollama", "model": "llama3.2:1b"})
+chat = LeannChat(INDEX_PATH, llm_config={"type": "hf", "model": "Qwen/Qwen3-0.6B"})
-response = chat.ask("How much storage does LEANN save?")
+response = chat.ask("How much storage does LEANN save?", top_k=1)
 ```
 
-## Documentation
-
-For full documentation, visit [https://leann.readthedocs.io](https://leann.readthedocs.io)
-
 ## License
 
 MIT License

packages/leann/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann"
-version = "0.1.14"
+version = "0.1.15"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -36,7 +36,5 @@ diskann = [
 ]
 
 [project.urls]
-Homepage = "https://github.com/yourusername/leann"
+Repository = "https://github.com/yichuan-w/LEANN"
-Documentation = "https://leann.readthedocs.io"
+Issues = "https://github.com/yichuan-w/LEANN/issues"
-Repository = "https://github.com/yourusername/leann"
-Issues = "https://github.com/yourusername/leann/issues" 

packages/wechat-exporter/main.py

@@ -1,6 +1,6 @@
 import json
 import sqlite3
-import xml.etree.ElementTree as ET
+import xml.etree.ElementTree as ElementTree
 from pathlib import Path
 from typing import Annotated
 
@@ -26,7 +26,7 @@ def get_safe_path(s: str) -> str:
 def process_history(history: str):
     if history.startswith("<?xml") or history.startswith("<msg>"):
         try:
-            root = ET.fromstring(history)
+            root = ElementTree.fromstring(history)
             title = root.find(".//title").text if root.find(".//title") is not None else None
             quoted = (
                 root.find(".//refermsg/content").text
@@ -52,7 +52,8 @@ def get_message(history: dict | str):
 
 def export_chathistory(user_id: str):
     res = requests.get(
-        "http://localhost:48065/wechat/chatlog", params={"userId": user_id, "count": 100000}
+        "http://localhost:48065/wechat/chatlog",
+        params={"userId": user_id, "count": 100000},
     ).json()
     for i in range(len(res["chatLogs"])):
         res["chatLogs"][i]["content"] = process_history(res["chatLogs"][i]["content"])
@@ -116,7 +117,8 @@ def export_sqlite(
     all_users = requests.get("http://localhost:48065/wechat/allcontacts").json()
     for user in tqdm(all_users):
         cursor.execute(
-            "INSERT OR IGNORE INTO users (id, name) VALUES (?, ?)", (user["arg"], user["title"])
+            "INSERT OR IGNORE INTO users (id, name) VALUES (?, ?)",
+            (user["arg"], user["title"]),
         )
         usr_chatlog = export_chathistory(user["arg"])
         for msg in usr_chatlog:

pyproject.toml

@@ -53,6 +53,7 @@ dev = [
     "ruff>=0.1.0",
     "matplotlib",
     "huggingface-hub>=0.20.0",
+    "pre-commit>=3.5.0",
 ]
 
 diskann = [

test/micro_tpt.py

@@ -58,7 +58,8 @@ class GraphWrapper:
             self.graph = torch.cuda.CUDAGraph()
             with torch.cuda.graph(self.graph):
                 self.static_output = self.model(
-                    input_ids=self.static_input, attention_mask=self.static_attention_mask
+                    input_ids=self.static_input,
+                    attention_mask=self.static_attention_mask,
                 )
             self.use_cuda_graph = True
         else:
@@ -82,7 +83,10 @@ class GraphWrapper:
     def _warmup(self, num_warmup: int = 3):
         with torch.no_grad():
             for _ in range(num_warmup):
-                self.model(input_ids=self.static_input, attention_mask=self.static_attention_mask)
+                self.model(
+                    input_ids=self.static_input,
+                    attention_mask=self.static_attention_mask,
+                )
 
     def __call__(self, input_ids: torch.Tensor, attention_mask: torch.Tensor) -> torch.Tensor:
         if self.use_cuda_graph:
@@ -261,7 +265,10 @@ class Benchmark:
                                 # print size
                                 print(f"in_features: {in_features}, out_features: {out_features}")
                                 new_module = bnb.nn.Linear8bitLt(
-                                    in_features, out_features, bias=bias, has_fp16_weights=False
+                                    in_features,
+                                    out_features,
+                                    bias=bias,
+                                    has_fp16_weights=False,
                                 )
 
                                 # Copy weights and bias
@@ -350,8 +357,6 @@ class Benchmark:
                 # Try xformers if available (only on CUDA)
                 if torch.cuda.is_available():
                     try:
-                        from xformers.ops import memory_efficient_attention  # noqa: F401
-
                         if hasattr(model, "enable_xformers_memory_efficient_attention"):
                             model.enable_xformers_memory_efficient_attention()
                             print("- Enabled xformers memory efficient attention")
@@ -427,7 +432,11 @@ class Benchmark:
             else "cpu"
         )
         return torch.randint(
-            0, 1000, (batch_size, self.config.seq_length), device=device, dtype=torch.long
+            0,
+            1000,
+            (batch_size, self.config.seq_length),
+            device=device,
+            dtype=torch.long,
         )
 
     def _run_inference(

test/sanity_checks/benchmark_embeddings.py

@@ -115,7 +115,13 @@ def main():
     # --- Plotting ---
     print("\n--- Generating Plot ---")
     plt.figure(figsize=(10, 6))
-    plt.plot(BATCH_SIZES, results_torch, marker="o", linestyle="-", label=f"PyTorch ({device})")
+    plt.plot(
+        BATCH_SIZES,
+        results_torch,
+        marker="o",
+        linestyle="-",
+        label=f"PyTorch ({device})",
+    )
     plt.plot(BATCH_SIZES, results_mlx, marker="s", linestyle="-", label="MLX")
 
     plt.title(f"Embedding Performance: MLX vs PyTorch\nModel: {MODEL_NAME_TORCH}")

test/simple_mac_tpt_test.py

@@ -170,7 +170,11 @@ class Benchmark:
 
     def _create_random_batch(self, batch_size: int) -> torch.Tensor:
         return torch.randint(
-            0, 1000, (batch_size, self.config.seq_length), device=self.device, dtype=torch.long
+            0,
+            1000,
+            (batch_size, self.config.seq_length),
+            device=self.device,
+            dtype=torch.long,
         )
 
     def _run_inference(self, input_ids: torch.Tensor) -> float:
@@ -256,7 +260,11 @@ def run_mlx_benchmark():
     """Run MLX-specific benchmark"""
     if not MLX_AVAILABLE:
         print("MLX not available, skipping MLX benchmark")
-        return {"max_throughput": 0.0, "avg_throughput": 0.0, "error": "MLX not available"}
+        return {
+            "max_throughput": 0.0,
+            "avg_throughput": 0.0,
+            "error": "MLX not available",
+        }
 
     config = BenchmarkConfig(model_path="mlx-community/all-MiniLM-L6-v2-4bit", use_mlx=True)
 
@@ -265,7 +273,11 @@ def run_mlx_benchmark():
         results = benchmark.run()
 
         if not results:
-            return {"max_throughput": 0.0, "avg_throughput": 0.0, "error": "No valid results"}
+            return {
+                "max_throughput": 0.0,
+                "avg_throughput": 0.0,
+                "error": "No valid results",
+            }
 
         max_throughput = max(results[batch_size]["throughput"] for batch_size in results)
         avg_throughput = np.mean([results[batch_size]["throughput"] for batch_size in results])

uv.lock

@@ -1847,7 +1847,7 @@ wheels = [
 
 [[package]]
 name = "leann-backend-diskann"
-version = "0.1.13"
+version = "0.1.14"
 source = { editable = "packages/leann-backend-diskann" }
 dependencies = [
     { name = "leann-core" },
@@ -1858,14 +1858,14 @@ dependencies = [
 
 [package.metadata]
 requires-dist = [
-    { name = "leann-core", specifier = "==0.1.13" },
+    { name = "leann-core", specifier = "==0.1.14" },
     { name = "numpy" },
     { name = "protobuf", specifier = ">=3.19.0" },
 ]
 
 [[package]]
 name = "leann-backend-hnsw"
-version = "0.1.13"
+version = "0.1.14"
 source = { editable = "packages/leann-backend-hnsw" }
 dependencies = [
     { name = "leann-core" },
@@ -1877,7 +1877,7 @@ dependencies = [
 
 [package.metadata]
 requires-dist = [
-    { name = "leann-core", specifier = "==0.1.13" },
+    { name = "leann-core", specifier = "==0.1.14" },
     { name = "msgpack", specifier = ">=1.0.0" },
     { name = "numpy" },
     { name = "pyzmq", specifier = ">=23.0.0" },
@@ -1885,7 +1885,7 @@ requires-dist = [
 
 [[package]]
 name = "leann-core"
-version = "0.1.13"
+version = "0.1.14"
 source = { editable = "packages/leann-core" }
 dependencies = [
     { name = "accelerate" },