[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Python aifaissgpt-osslangchainllama-indexllmlocalstorageoffline-firstollamaprivacypythonragretrieval-augmented-generationvector-databasevector-searchvectors
fix emaple and add pypi example
yichuan520030910320455f93fb7c12
diff --git a/README.md b/README.mdindex 6bdebfc..f4af89a 100755--- a/README.md+++ b/README.md@@ -114,32 +114,23 @@ Our declarative API makes RAG as easy as writing a config file.[Try in this ipynb file →](demo.ipynb) [](https://colab.research.google.com/github/yichuan-w/LEANN/blob/main/demo.ipynb)```python-from leann.api import LeannBuilder, LeannSearcher, LeannChat+from leann import LeannBuilder, LeannSearcher, LeannChat+from pathlib import Path+INDEX_PATH = str(Path("./").resolve() / "demo.leann")-# 1. Build the index (no embeddings stored!)+# Build an indexbuilder = 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"-}+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 = 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,-)+# 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!diff --git a/demo.ipynb b/demo.ipynbindex 016302c..e91ec01 100644--- a/demo.ipynb+++ b/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": [- {- "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"- ]- }- ],+ "outputs": [],"source": ["from leann.api import LeannBuilder\n","\n",@@ -136,81 +75,7 @@"cell_type": "code","execution_count": null,"metadata": {},- "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"- ]- }- ],+ "outputs": [],"source": ["from leann.api import LeannSearcher\n","\n",diff --git a/packages/leann/README.md b/packages/leann/README.mdindex 0488c3d..4281ef1 100644--- a/packages/leann/README.md+++ b/packages/leann/README.md@@ -16,25 +16,24 @@ uv pip install leann[diskann]```pythonfrom leann import LeannBuilder, LeannSearcher, LeannChat+from pathlib import Path+INDEX_PATH = str(Path("./").resolve() / "demo.leann")# Build an indexbuilder = 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")-results = searcher.search("storage savings", top_k=3)+searcher = LeannSearcher(INDEX_PATH)+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"})-response = chat.ask("How much storage does LEANN save?")+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)```-## Documentation--For full documentation, visit [https://leann.readthedocs.io](https://leann.readthedocs.io)-## LicenseMIT Licensediff --git a/packages/leann/pyproject.toml b/packages/leann/pyproject.tomlindex a6db993..74ab903 100644--- a/packages/leann/pyproject.toml+++ b/packages/leann/pyproject.toml@@ -36,7 +36,5 @@ diskann = [][project.urls]-Homepage = "https://github.com/yourusername/leann"-Documentation = "https://leann.readthedocs.io"-Repository = "https://github.com/yourusername/leann"-Issues = "https://github.com/yourusername/leann/issues"+Repository = "https://github.com/yichuan-w/LEANN"+Issues = "https://github.com/yichuan-w/LEANN/issues"