{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Quick Start in 30s\n", "\n", "**Home GitHub Repository:** [LEANN on GitHub](https://github.com/yichuan-w/LEANN)\n", "\n", "**Important for Colab users:** Set your runtime type to T4 GPU for optimal performance. Go to Runtime → Change runtime type → Hardware accelerator → T4 GPU." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# install this if you are using colab\n", "! uv pip install leann-core leann-backend-hnsw --no-deps\n", "! uv pip install leann --no-deps\n", "# For Colab environment, we need to set some environment variables\n", "import os\n", "\n", "os.environ[\"LEANN_LOG_LEVEL\"] = \"INFO\" # Enable more detailed logging" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from pathlib import Path\n", "\n", "INDEX_DIR = Path(\"./\").resolve()\n", "INDEX_PATH = str(INDEX_DIR / \"demo.leann\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Build the index" ] }, { "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=, fmt='d')... Count=6, Bytes=48\n", "[0.00s] Read assign_probas (6)\n", " Reading vector (dtype=, fmt='i')... Count=7, Bytes=28\n", "[0.14s] Read cum_nneighbor_per_level (7)\n", " Reading vector (dtype=, 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=, fmt='Q')... Count=6, Bytes=48\n", "[0.33s] Read offsets (6)\n", "[0.41s] Attempting to read neighbors vector...\n", " Reading vector (dtype=, 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", "builder = LeannBuilder(backend_name=\"hnsw\")\n", "builder.add_text(\"C# is a powerful programming language and it is good at game development\")\n", "builder.add_text(\n", " \"Python is a powerful programming language and it is good at machine learning tasks\"\n", ")\n", "builder.add_text(\"Machine learning transforms industries\")\n", "builder.add_text(\"Neural networks process complex data\")\n", "builder.add_text(\"Leann is a great storage saving engine for RAG on your MacBook\")\n", "builder.build_index(INDEX_PATH)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Search with real-time embeddings" ] }, { "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 \"\", line 198, in _run_module_as_main\n", " File \"\", 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 \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", "searcher = LeannSearcher(INDEX_PATH)\n", "results = searcher.search(\"programming languages\", top_k=2)\n", "results" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Chat with LEANN using retrieved results" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from leann.api import LeannChat\n", "\n", "llm_config = {\n", " \"type\": \"hf\",\n", " \"model\": \"Qwen/Qwen3-0.6B\",\n", "}\n", "\n", "chat = LeannChat(index_path=INDEX_PATH, llm_config=llm_config)\n", "response = chat.ask(\n", " \"Compare the two retrieved programming languages and tell me their advantages.\",\n", " top_k=2,\n", " llm_kwargs={\"max_tokens\": 128},\n", ")\n", "response" ] } ], "metadata": { "kernelspec": { "display_name": ".venv", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.12" } }, "nbformat": 4, "nbformat_minor": 2 }