{"id":31642252,"url":"https://github.com/joshyattridge/gptkeras","last_synced_at":"2026-04-18T00:03:12.775Z","repository":{"id":316709197,"uuid":"1061796015","full_name":"joshyattridge/GPTkeras","owner":"joshyattridge","description":"Automates Keras model design using GPT - generates architectures, tunes hyperparameters, and tracks experiments.","archived":false,"fork":false,"pushed_at":"2025-10-01T09:55:35.000Z","size":1136,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-01-14T11:21:53.582Z","etag":null,"topics":["chatgpt","gpt","keras","llm","tensorflow"],"latest_commit_sha":null,"homepage":"https://pypi.org/project/GPTkeras/","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/joshyattridge.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-22T11:52:59.000Z","updated_at":"2025-12-29T10:02:37.000Z","dependencies_parsed_at":null,"dependency_job_id":"1d0c7d21-fd4b-41ac-a7ba-db40ffd14f0a","html_url":"https://github.com/joshyattridge/GPTkeras","commit_stats":null,"previous_names":["joshyattridge/kerasgpt","joshyattridge/kerascraftergpt"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/joshyattridge/GPTkeras","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/joshyattridge%2FGPTkeras","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/joshyattridge%2FGPTkeras/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/joshyattridge%2FGPTkeras/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/joshyattridge%2FGPTkeras/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/joshyattridge","download_url":"https://codeload.github.com/joshyattridge/GPTkeras/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/joshyattridge%2FGPTkeras/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29705818,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-22T05:59:28.568Z","status":"ssl_error","status_checked_at":"2026-02-22T05:58:46.208Z","response_time":110,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["chatgpt","gpt","keras","llm","tensorflow"],"created_at":"2025-10-07T03:57:44.390Z","updated_at":"2026-02-22T06:00:46.685Z","avatar_url":"https://github.com/joshyattridge.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GPTkeras\n\nGPTkeras aims to solve the struggles of guessing model configurations and hyperparameters when developing machine learning projects. Instead of manually tuning architectures and settings, you simply provide your training data (`x` and `y`), and this library leverages large language models (LLMs) specifically ChatGPT to automatically generate suitable layers and hyperparameters for your dataset.\n\nThe workflow is as follows:\n\n- You provide your training data.\n- The library uses ChatGPT to draft a Keras model architecture and select hyperparameters tailored to your data.\n- It runs a training session and evaluates the results.\n- The training results are then passed back to the LLM, which attempts to further improve the model configuration in subsequent iterations.\n\nAnother major challenge in machine learning experimentation is tracking changes to models and understanding how those changes affect results. GPTkeras addresses this by using the LLM to log and manage conversational context, so you can see how each modification impacts performance over time.\n\nThis toolkit wraps the OpenAI Chat Completions API and provides helpers for drafting model architectures, managing experiments, and logging conversational context when iterating on training runs.\n\n## Installation\n\n```bash\npip install GPTkeras\n```\n\n## Quick start\n\n```python\nfrom GPTkeras import GPTkeras\n\nmodel = GPTkeras(train_x, train_y, api_key=\"sk-...\")\nmodel.fit(max_iterations=3)\n```\n\n## Documentation\n\n### GPTkeras Arguments\n\n```python\nGPTkeras(\n\ttrain_x,                      # Required. Training input data (numpy array or tensor)\n\ttrain_y,                      # Required. Training target data (numpy array or tensor)\n\tapi_key=None,                 # Required. OpenAI API key for LLM access\n\tmodel=\"gpt-4o-mini\",         # Optional. OpenAI model name (default: \"gpt-4o-mini\")\n\thistory_path=\"chat_history.jsonl\", # Optional. Path to log conversational/model history (default: \"chat_history.jsonl\")\n\tcontinue_from_history=False,  # Optional. If True, resumes conversation/model history from previous runs (default: False)\n)\n```\n\n## Contributing\n\nContributions, suggestions, and bug reports are welcome! Feel free to open issues or submit pull requests to help improve GPTkeras.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjoshyattridge%2Fgptkeras","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjoshyattridge%2Fgptkeras","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjoshyattridge%2Fgptkeras/lists"}