{"id":20627425,"url":"https://github.com/florianmgs/gpt4-image-api","last_synced_at":"2025-04-15T15:21:59.076Z","repository":{"id":197988793,"uuid":"699818782","full_name":"FlorianMgs/gpt4-image-api","owner":"FlorianMgs","description":"Small tool using selenium to get a temporary API endpoint for the ChatGPT Image Input / image recognition feature. Very quickly made, you should not rely on this on prod. ","archived":false,"fork":false,"pushed_at":"2023-10-09T15:13:57.000Z","size":6,"stargazers_count":31,"open_issues_count":4,"forks_count":10,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-28T21:51:07.210Z","etag":null,"topics":["api","chatgpt","fastapi","gpt4","gpt4-api","image","openai","python","selenium"],"latest_commit_sha":null,"homepage":"","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/FlorianMgs.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}},"created_at":"2023-10-03T12:04:54.000Z","updated_at":"2025-01-10T06:35:07.000Z","dependencies_parsed_at":"2023-11-10T11:44:22.724Z","dependency_job_id":null,"html_url":"https://github.com/FlorianMgs/gpt4-image-api","commit_stats":null,"previous_names":["florianmgs/gpt4-image-api"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FlorianMgs%2Fgpt4-image-api","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FlorianMgs%2Fgpt4-image-api/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FlorianMgs%2Fgpt4-image-api/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FlorianMgs%2Fgpt4-image-api/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FlorianMgs","download_url":"https://codeload.github.com/FlorianMgs/gpt4-image-api/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249095115,"owners_count":21211866,"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":["api","chatgpt","fastapi","gpt4","gpt4-api","image","openai","python","selenium"],"created_at":"2024-11-16T13:16:45.768Z","updated_at":"2025-04-15T15:21:59.050Z","avatar_url":"https://github.com/FlorianMgs.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GPT4 Image Recognition API\nSmall tool using selenium to get a temporary API endpoint for the ChatGPT Image Input / image recognition feature.  \nVery quickly made, you should not rely on this on prod.  \nShould be deprecated as soon as we have access to official OpenAI endpoints.  \nWorks with google authentification. If you use a different login method, please modify the code for your usecase.  \n\n# Installation\n- Create venv, then clone the repo  \n- Install requirements:  \n`pip install -r requirements.txt`\n- Define a `.env` file with your OpenAI Google credentials (or whatever but make sure to modiy the code appropriately)\n- Run FastAPI server:\n`python main.py`\n\n# Endpoints\n\n## GET\n`https://0.0.0.0:8000/start`  \nStart a new session. Complete manually the login steps and press enter when asked.  \nWait for the OpenAI popup to display before pressing enter.  \n\n`https://0.0.0.0:8000/stop`  \nStop the current session.  \n\n## POST\n`https://0.0.0.0:8000/action/`  \nPost an image URL with a prompt. Example:  \n```\nRequest:\n{\n    \"image_url\": \"https://www.reuters.com/resizer/NLk9k89J1tfmH-B7XKd598-6j_Y=/960x0/filters:quality(80)/cloudfront-us-east-2.images.arcpublishing.com/reuters/AHF2FYISNJO55J6N35YJBZ2JYY.jpg\",\n    \"prompt\": \"Describe this image precisely.\"\n}\n\nResponse:\n{\n    \"status\": \"Success\",\n    \"result\": {\n        \"answer\": \"A night view of the Eiffel Tower illuminated, with its reflection visible in calm water in the foreground. The sky is dark blue, and there are two streetlights on either side of the scene.\"\n    }\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflorianmgs%2Fgpt4-image-api","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fflorianmgs%2Fgpt4-image-api","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflorianmgs%2Fgpt4-image-api/lists"}