cognee-mcp

{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## Cognee GraphRAG with Multimedia files" ] }, { "cell_type": "markdown", "metadata": { "vscode": { "languageId": "plaintext" } }, "source": [ "## Load Data\n", "\n", "We will use a few sample multimedia files which we have on GitHub for easy access." ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "ExecuteTime": { "end_time": "2025-06-30T11:54:44.613431Z", "start_time": "2025-06-30T11:54:44.606687Z" } }, "outputs": [], "source": [ "import os\n", "import pathlib\n", "\n", "# cognee knowledge graph will be created based on the text\n", "# and description of these files\n", "mp3_file_path = os.path.join(\n", " os.path.abspath(\"\"),\n", " \"../\",\n", " \"examples/data/multimedia/text_to_speech.mp3\",\n", ")\n", "png_file_path = os.path.join(\n", " os.path.abspath(\"\"),\n", " \"../\",\n", " \"examples/data/multimedia/example.png\",\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Set environment variables" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "ExecuteTime": { "end_time": "2025-06-30T11:54:46.739157Z", "start_time": "2025-06-30T11:54:46.734808Z" } }, "outputs": [], "source": [ "import os\n", "\n", "if \"LLM_API_KEY\" not in os.environ:\n", " os.environ[\"LLM_API_KEY\"] = \"\"\n", "\n", "# \"neo4j\" or \"networkx\"\n", "os.environ[\"GRAPH_DATABASE_PROVIDER\"] = \"kuzu\"\n", "# Not needed if using networkx\n", "# os.environ[\"GRAPH_DATABASE_URL\"]=\"\"\n", "# os.environ[\"GRAPH_DATABASE_USERNAME\"]=\"\"\n", "# os.environ[\"GRAPH_DATABASE_PASSWORD\"]=\"\"\n", "\n", "# \"pgvector\", \"qdrant\", \"weaviate\" or \"lancedb\"\n", "os.environ[\"VECTOR_DB_PROVIDER\"] = \"lancedb\"\n", "# Not needed if using \"lancedb\" or \"pgvector\"\n", "# os.environ[\"VECTOR_DB_URL\"]=\"\"\n", "# os.environ[\"VECTOR_DB_KEY\"]=\"\"\n", "\n", "# Relational Database provider \"sqlite\" or \"postgres\"\n", "os.environ[\"DB_PROVIDER\"] = \"sqlite\"\n", "\n", "# Database name\n", "os.environ[\"DB_NAME\"] = \"cognee_db\"\n", "\n", "# Postgres specific parameters (Only if Postgres or PGVector is used)\n", "# os.environ[\"DB_HOST\"]=\"127.0.0.1\"\n", "# os.environ[\"DB_PORT\"]=\"5432\"\n", "# os.environ[\"DB_USERNAME\"]=\"cognee\"\n", "# os.environ[\"DB_PASSWORD\"]=\"cognee\"" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "\n", "\u001b[2m2025-10-22T17:58:21.914432\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mDeleted old log file: /Users/daulet/Desktop/dev/cognee-claude/logs/2025-10-22_18-20-40.log\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:22.759223\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mLogging initialized \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m \u001b[36mcognee_version\u001b[0m=\u001b[35m0.3.6-local\u001b[0m \u001b[36mdatabase_path\u001b[0m=\u001b[35m/Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m \u001b[36mgraph_database_name\u001b[0m=\u001b[35m\u001b[0m \u001b[36mos_info\u001b[0m=\u001b[35m'Darwin 24.5.0 (Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132)'\u001b[0m \u001b[36mpython_version\u001b[0m=\u001b[35m3.10.11\u001b[0m \u001b[36mrelational_config\u001b[0m=\u001b[35mcognee_db\u001b[0m \u001b[36mstructlog_version\u001b[0m=\u001b[35m25.4.0\u001b[0m \u001b[36mvector_config\u001b[0m=\u001b[35mlancedb\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:22.759643\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mDatabase storage: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "0.3.6-local\n" ] } ], "source": [ "import cognee\n", "print(cognee.__version__)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Run Cognee with multimedia files" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "\n", "\u001b[2m2025-10-22T17:58:24.045051\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mLoaded JSON extension \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:24.081025\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mDeleted Kuzu database files at /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases/cognee_graph_kuzu\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:26.937024\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mDatabase deleted successfully.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n", "\n", "\u001b[1mStorage manager absolute path: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_cache\u001b[0m\n", "\n", "\u001b[1mDeleting cache... \u001b[0m\n", "\n", "\u001b[1m✓ Cache deleted successfully! \u001b[0m\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "User 5c6da0e1-4bda-4b32-a6e3-ca70b884fb9a has registered.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n", "\u001b[2m2025-10-22T17:58:28.397580\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run started: `981301fd-9699-5cd2-9746-577c0076b844`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.398001\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.398362\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.399412\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run started: `981301fd-9699-5cd2-9746-577c0076b844`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.399724\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.400149\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.414674\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: pypdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.415122\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: text_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.415472\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: image_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.415781\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: audio_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.416132\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: unstructured_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.416494\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: advanced_pdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:28.416861\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: beautiful_soup_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.666583\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.667605\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.668153\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run completed: `981301fd-9699-5cd2-9746-577c0076b844`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.673512\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.673986\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.674429\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run completed: `981301fd-9699-5cd2-9746-577c0076b844`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.686749\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.707284\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run started: `eea87f6e-3943-552c-b2fe-904ac1e367f0`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.707716\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.708080\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.708748\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run started: `eea87f6e-3943-552c-b2fe-904ac1e367f0`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.709019\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.709373\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.716846\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.720657\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.725864\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:32.731948\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:36.077494\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mReconnecting to Kuzu database...\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:36.126562\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mLoaded JSON extension \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:36.161293\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'object' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:36.161962\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'light bulb' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:36.162356\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'profession' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:36.162703\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'programmer' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:36.163116\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:36.163438\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'hardware problem' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:37.300377\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:38.621515\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:39.290034\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'profession' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:39.291121\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'programmers' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:39.292185\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'object' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:39.293038\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'light bulb' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:39.293777\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:39.294485\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'hardware problem' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:39.295087\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'joke' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:39.295651\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'humor' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:40.433350\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:40.434081\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:40.434611\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:40.435199\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:40.435629\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:40.435958\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:40.436247\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run completed: `eea87f6e-3943-552c-b2fe-904ac1e367f0`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:40.697594\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:42.368373\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:43.185789\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:43.186535\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:43.186875\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:43.187279\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:43.187623\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:43.187953\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:43.188254\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run completed: `eea87f6e-3943-552c-b2fe-904ac1e367f0`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n" ] }, { "data": { "text/plain": [ "{UUID('849137b0-173d-5a0f-9462-403398a3b1e2'): PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('8f4e8447-24c9-5d2a-afb2-f86256ca4f34'), dataset_id=UUID('849137b0-173d-5a0f-9462-403398a3b1e2'), dataset_name='main_dataset', payload=None, data_ingestion_info=[{'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('8f4e8447-24c9-5d2a-afb2-f86256ca4f34'), dataset_id=UUID('849137b0-173d-5a0f-9462-403398a3b1e2'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('cc1ec4a6-2621-5143-ad19-ae7703db040b')}, {'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('8f4e8447-24c9-5d2a-afb2-f86256ca4f34'), dataset_id=UUID('849137b0-173d-5a0f-9462-403398a3b1e2'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('f3d53fbe-2a29-57e4-9e55-d87a49890ecc')}])}" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import cognee\n", "\n", "# Create a clean slate for cognee -- reset data and system state\n", "await cognee.prune.prune_data()\n", "await cognee.prune.prune_system(metadata=True)\n", "\n", "# Add multimedia files and make them available for cognify\n", "await cognee.add([mp3_file_path, png_file_path])\n", "\n", "# Create knowledge graph with cognee\n", "await cognee.cognify()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Query Cognee for summaries related to multimedia files" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "ExecuteTime": { "end_time": "2025-06-30T11:44:56.372628Z", "start_time": "2025-06-30T11:44:55.978258Z" } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "\n", "\u001b[2m2025-10-22T17:58:43.213961\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mStarting summary retrieval for query: 'What is in the multimedia files?'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:43.495466\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mFound 2 summaries from vector search\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:43.496119\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mReturning 2 summary payloads \u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:43.496456\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mStarting completion generation for query: 'What is in the multimedia files?'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n", "\n", "\u001b[2m2025-10-22T17:58:43.496815\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mReturning context with 2 item(s)\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'id': 'b4da8f65-1ab7-5816-b6ca-c3b7e16d7ea9', 'created_at': 1761155918667, 'updated_at': 1761155918667, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Changing a light bulb is a hardware issue for programmers.'}\n", "{'id': '875f97da-6b05-52af-973d-54939a229a21', 'created_at': 1761155922404, 'updated_at': 1761155922404, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'How many coders are needed to replace a light bulb? Zero. That’s an issue for hardware.'}\n" ] } ], "source": [ "from cognee.api.v1.search import SearchType\n", "\n", "# Query cognee for summaries of the data in the multimedia files\n", "search_results = await cognee.search(\n", " query_type=SearchType.SUMMARIES,\n", " query_text=\"What is in the multimedia files?\",\n", ")\n", "\n", "# Display search results\n", "for result_text in search_results:\n", " print(result_text)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "ename": "", "evalue": "", "output_type": "error", "traceback": [ "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n", "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n", "\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n", "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details." ] } ], "source": [ "# Only exit in interactive mode, not during GitHub Actions\n", "import os\n", "\n", "# Skip exit if we're running in GitHub Actions\n", "if not os.environ.get('GITHUB_ACTIONS'):\n", " print(\"Exiting kernel to clean up resources...\")\n", " os._exit(0)\n", "else:\n", " print(\"Skipping kernel exit - running in GitHub Actions\")" ] } ], "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": "3.10.11" } }, "nbformat": 4, "nbformat_minor": 2 }