{"id":27311713,"url":"https://github.com/aadya940/numpyai","last_synced_at":"2025-04-12T06:33:39.243Z","repository":{"id":285627323,"uuid":"958791563","full_name":"aadya940/numpyai","owner":"aadya940","description":"A Natural Language Interface to the Numpy Library using LLMs.","archived":false,"fork":false,"pushed_at":"2025-04-09T12:59:26.000Z","size":141,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-09T13:44:43.423Z","etag":null,"topics":["ai","data-analysis","data-science","library","llm","machine-learning","numpy","python"],"latest_commit_sha":null,"homepage":"https://numpyai.readthedocs.io/en/latest/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aadya940.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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}},"created_at":"2025-04-01T19:10:50.000Z","updated_at":"2025-04-09T12:59:30.000Z","dependencies_parsed_at":null,"dependency_job_id":"2b890681-9539-4d48-8085-980a7efeb985","html_url":"https://github.com/aadya940/numpyai","commit_stats":null,"previous_names":["aadya940/numpyai"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aadya940%2Fnumpyai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aadya940%2Fnumpyai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aadya940%2Fnumpyai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aadya940%2Fnumpyai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aadya940","download_url":"https://codeload.github.com/aadya940/numpyai/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248529840,"owners_count":21119580,"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","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","data-analysis","data-science","library","llm","machine-learning","numpy","python"],"created_at":"2025-04-12T06:32:21.652Z","updated_at":"2025-04-12T06:33:39.191Z","avatar_url":"https://github.com/aadya940.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://github.com/user-attachments/assets/7d6244d2-2a94-42c7-99e1-ba2953c21781\" alt=\"logo\" width=\"500\"\u003e\n\u003c/p\u003e\n\n\n### NumpyAI\nA Natural Language Interface for NumPy powered by LLMs. Empowering mindful data analysis using Generative AI.\n\n### About NumpyAI\nNumpyAI enables seamless interaction with NumPy using natural language queries, making numerical computing more intuitive and efficient.\n\n#### Key Features:\n- **Natural Language Processing**: Convert plain language instructions into executable NumPy code.\n- **Validation \u0026 Safety**: Automatically validates and tests generated code for correctness and security.\n- **Transparency**: Logs all generated code and applies checks to ensure accuracy before execution.\n- **Control**: We don't allow AI to reassign or change the internal arrays passed to `numpyai.array` or `numpyai.NumpyAISession`. We believe they need to be intentional decisions by the user.\n\n\n### Installation\n```sh\npip install numpyai\n```\n\nWindows\n```sh\nset GOOGLE_API_KEY=...\n```\n\nLinux\n```sh\nexport GOOGLE_API_KEY=...\n```\n\n### Usage Example\n\n#### Single Array\n```python\nimport numpyai as npi\nimport numpy as np\n\n# Ensure GOOGLE_API_KEY environment variable is set.\n\n# Create an array instance\ndata = [[1, 2, 3, 4, 5, np.nan], [np.nan, 3, 5, 3.1415, 2, 2]]\narr = npi.array(data)\n\n# Query NumPyAI with natural language\nprint(arr.chat(\"Compute the height and width of the image using NumPy.\"))  # Expected output: (2, 6)\n```\n\n#### Multiple Arrays\n```python\nimport numpyai as npi\nimport numpy as np\n\narr1 = np.array([[1, 2, 3], [4, 5, 6]])\narr2 = np.random.random((2, 3))\n\nsess = npi.NumpyAISession([arr1, arr2])\nimputed_array = sess.chat(\"Impute the first array with the mean of the second array.\")\n```\n\n### Supported LLM Vendors\n- Google Gemini\n\n### Future Enhancements\n- Support for additional LLM providers (OpenAI, Anthropic, etc.)\n- Interactive debugging and visualization tools\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faadya940%2Fnumpyai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faadya940%2Fnumpyai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faadya940%2Fnumpyai/lists"}