{"id":26504763,"url":"https://github.com/topoteretes/cognee-starter","last_synced_at":"2025-10-15T14:40:49.549Z","repository":{"id":276400157,"uuid":"929179016","full_name":"topoteretes/cognee-starter","owner":"topoteretes","description":"Cognee starter repo with examples","archived":false,"fork":false,"pushed_at":"2025-05-10T14:34:52.000Z","size":250,"stargazers_count":37,"open_issues_count":1,"forks_count":13,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-06-12T19:05:50.699Z","etag":null,"topics":["ai","graphrag","llm","semantic-memory"],"latest_commit_sha":null,"homepage":"https://www.cognee.ai/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/topoteretes.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-02-08T00:32:50.000Z","updated_at":"2025-06-09T09:48:28.000Z","dependencies_parsed_at":"2025-04-22T10:58:02.486Z","dependency_job_id":"0fe54f1c-92a3-415d-bf6f-3486fd47a6aa","html_url":"https://github.com/topoteretes/cognee-starter","commit_stats":null,"previous_names":["topoteretes/cognee-starter"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/topoteretes/cognee-starter","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/topoteretes%2Fcognee-starter","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/topoteretes%2Fcognee-starter/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/topoteretes%2Fcognee-starter/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/topoteretes%2Fcognee-starter/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/topoteretes","download_url":"https://codeload.github.com/topoteretes/cognee-starter/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/topoteretes%2Fcognee-starter/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279085602,"owners_count":26100017,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-15T02:00:07.814Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","graphrag","llm","semantic-memory"],"created_at":"2025-03-20T20:38:23.227Z","updated_at":"2025-10-15T14:40:49.539Z","avatar_url":"https://github.com/topoteretes.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Cognee Starter Kit\nWelcome to the \u003ca href=\"https://github.com/topoteretes/cognee\"\u003ecognee\u003c/a\u003e Starter Repo! This repository is designed to help you get started quickly by providing a structured dataset and pre-built data pipelines using cognee to build powerful knowledge graphs.\n\nYou can use this repo to ingest, process, and visualize data in minutes.\n\nBy following this guide, you will:\n\n- Load structured company and employee data\n- Utilize pre-built pipelines for data processing\n- Perform graph-based search and query operations\n- Visualize entity relationships effortlessly on a graph\n\n# How to Use This Repo 🛠\n\n## Install uv if you don't have it on your system\n```\npip install uv\n```\n## Install dependencies\n```\nuv sync\n```\n\n## Setup LLM\nAdd environment variables to `.env` file.\nIn case you choose to use OpenAI provider, add just the model and api_key.\n```\nLLM_PROVIDER=\"\"\nLLM_MODEL=\"\"\nLLM_ENDPOINT=\"\"\nLLM_API_KEY=\"\"\nLLM_API_VERSION=\"\"\n\nEMBEDDING_PROVIDER=\"\"\nEMBEDDING_MODEL=\"\"\nEMBEDDING_ENDPOINT=\"\"\nEMBEDDING_API_KEY=\"\"\nEMBEDDING_API_VERSION=\"\"\n```\n\nActivate the Python environment:\n```\nsource .venv/bin/activate\n```\n\n## Run the Default Pipeline\n\nThis script runs the cognify pipeline with default settings. It ingests text data, builds a knowledge graph, and allows you to run search queries.\n\n```\npython src/pipelines/default.py\n```\n\n## Run the Low-Level Pipeline\n\nThis script implements its own pipeline with custom ingestion task. It processes the given JSON data about companies and employees, making it searchable via a graph.\n\n```\npython src/pipelines/low_level.py\n```\n\n## Run the Custom Model Pipeline\n\nCustom model uses custom pydantic model for graph extraction. This script categorizes programming languages as an example and visualizes relationships.\n\n```\npython src/pipelines/custom-model.py\n```\n\n## Graph preview\n\ncognee provides a visualize_graph function that will render the graph for you.\n\n```\n    graph_file_path = str(\n        pathlib.Path(\n            os.path.join(pathlib.Path(__file__).parent, \".artifacts/graph_visualization.html\")\n        ).resolve()\n    )\n    await visualize_graph(graph_file_path)\n```\nIf you want to use tools like Graphistry for graph visualization:\n- create an account and API key from https://www.graphistry.com\n- add the following environment variables to `.env` file:\n```\nGRAPHISTRY_USERNAME=\"\"\nGRAPHISTRY_PASSWORD=\"\"\n```\nNote: `GRAPHISTRY_PASSWORD` is API key.\n\n## Trace\n\nCognee supports Langfuse tracing to help you monitor and debug your workflows.\n\nTo enable tracing:\n\n1. Create an account and obtain your API keys at [Langfuse](https://langfuse.com/).\n   *(Alternatively, you can self-host Langfuse by following the instructions at [Langfuse Self-Hosting](https://langfuse.com/self-hosting))*\n\n2. Add the following environment variables to your `.env` file:\n\n    ```env\n    LANGFUSE_PUBLIC_KEY=\"\"\n    LANGFUSE_SECRET_KEY=\"\"\n    LANGFUSE_HOST=\"\"\n    ```\n\nMake sure to replace the empty strings with your actual Langfuse credentials.\n\n\n# What will you build with cognee?\n\n- Expand the dataset by adding more structured/unstructured data\n- Customize the data model to fit your use case\n- Use the search API to build an intelligent assistant\n- Visualize knowledge graphs for better insights\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftopoteretes%2Fcognee-starter","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftopoteretes%2Fcognee-starter","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftopoteretes%2Fcognee-starter/lists"}