{"installed_packages":[{"package_name":"Core","package_description":"Built-in integrations that are always available.","endpoints":[{"name":"InvokeLLM","description":"\n    Generates a response from an LLM with a prompt.\n    Be elaborate and detailed in your prompt.\n    You can potentially ask the llm to output a json, in which case specify the json schema in response_json_schema.\n    If you need to use external knowledge, use add_context_from_internet=true. This will give the LLM context from google search, google maps, news, etc. That way you can fetch structured data from the web.\n    You can attach files (including images) for additional context to the LLM, using the `file_urls` parameter. This should be a list of urls after uploading them.\n    You can use both file_urls AND add_context_from_internet together - the system will use a model that supports both vision and web search.\n    You can optionally specify a `model` for this call. Options: 'automatic', 'gpt_5_mini', 'gemini_3_flash', 'gpt_5', 'gpt_5_4', 'gemini_3_1_pro', 'claude_sonnet_4_6', 'claude_opus_4_6'. Defaults to automatic (openai/gpt-4o-mini).\n    All models support file_urls. Only 'gemini_3_flash' and 'gemini_3_1_pro' support add_context_from_internet (web search). Using an incompatible model with add_context_from_internet will raise an error.\n    Non-default models cost more integration credits. Only use them when the task requires higher quality.\n    If response_json_schema is specified, returns a dict (so no need to parse it), otherwise returns a string.\n    IMPORTANT: If specified, response_json_schema root object must by of type object, not array. i.e. {\"type\": \"object\", ...}\n    ","schema":{"properties":{"app_id":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Id"},"app_owner":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Owner"},"prompt":{"title":"Prompt","type":"string"},"add_context_from_internet":{"default":false,"title":"Add Context From Internet","type":"boolean"},"response_json_schema":{"anyOf":[{"additionalProperties":true,"type":"object"},{"type":"null"}],"default":null,"title":"Response Json Schema"},"file_urls":{"anyOf":[{"format":"binary","type":"string"},{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"default":null,"title":"File Urls"},"model":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Model"}},"required":["prompt"],"title":"InvokeLLMModel","type":"object"}},{"name":"SendEmail","description":"Sends an email to the user. you can optionally specify the name of the sender, if not, the name of the app will be used.","schema":{"properties":{"app_id":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Id"},"app_owner":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Owner"},"from_name":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"From Name"},"to":{"title":"To","type":"string"},"subject":{"title":"Subject","type":"string"},"body":{"title":"Body","type":"string"}},"required":["to","subject","body"],"title":"SendEmailModel","type":"object"}},{"name":"UploadFile","description":"\n    Uploads a file to the user's files directory.\n    Returns a dict containing {\"file_url\": string}\n    You can use the url later for other inputs\n    ","schema":{"properties":{"app_id":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Id"},"app_owner":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Owner"},"file":{"format":"binary","title":"File","type":"string"}},"required":["file"],"title":"UploadFileModel","type":"object"}},{"name":"GenerateImage","description":"Generate an image using AI.\n    Takes about 5-10 seconds to generate an image.\n    Be detailed in the prompt, the better the prompt, the better the image.\n    Optionally provide existing_image_urls as reference - for editing, style inspiration, or visual context.\n    The integration returns a URL to the generated image: {url: str}","schema":{"properties":{"app_id":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Id"},"app_owner":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Owner"},"prompt":{"title":"Prompt","type":"string"},"existing_image_urls":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"null"}],"default":null,"title":"Existing Image Urls"}},"required":["prompt"],"title":"GenerateImageModel","type":"object"}},{"name":"ExtractDataFromUploadedFile","description":"\n    Extracts data from an uploaded file.\n    Use the UploadFile integration to get the file url first.\n    Supports csv, xlsx, json, html, png, jpg, jpeg, and pdf files.\n    Useful to extract data, and potential flow - upload file, extract data, bulk insert entities into database.\n    Only use this integration when you know the target JSON schema of the data you're trying to extract (if you just want the content of a file - fetch the file url).\n    returns the following object:\n    {\n        \"status\": \"success\" | \"error\",\n        \"details\": \"error details if error, otherwise null\",\n        \"output\": list[dict] | dict | None (exists if status is success)\n    }\n    ","schema":{"properties":{"app_id":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Id"},"app_owner":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Owner"},"file_url":{"title":"File Url","type":"string"},"json_schema":{"additionalProperties":true,"title":"Json Schema","type":"object"}},"required":["file_url","json_schema"],"title":"ExtractDataFromUploadedFileModel","type":"object"}},{"name":"CreateFileSignedUrl","description":"\n    Creates a signed URL for a private file that can be used to download the file.\n    The file must be uploaded to the private storage.\n    Returns a dict containing {\"signed_url\": string}\n    ","schema":{"properties":{"app_id":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Id"},"app_owner":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Owner"},"file_uri":{"title":"File Uri","type":"string"},"expires_in":{"default":300,"title":"Expires In","type":"integer"}},"required":["file_uri"],"title":"CreateFileSignedUrlModel","type":"object"}},{"name":"UploadPrivateFile","description":"\n    Uploads a file to the app's private filhes directory.\n    Returns a dict containing {\"file_uri\": string}\n    You can use the file_uri later to create a signed URL for the file using the CreateFileSignedUrl integration\n    The file is uploaded to the private storage.\n    ","schema":{"properties":{"app_id":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Id"},"app_owner":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"App Owner"},"file":{"format":"binary","title":"File","type":"string"}},"required":["file"],"title":"UploadPrivateFileModel","type":"object"}}]}],"missing_packages":[]}