📄️ Detect adult content.
Check if the content is appropriate for all audiences.
📄️ Detect text in an image.
Detects text in an image using the Azure Computer Vision API.
📄️ Text Entity Detection.
Identities Entities From Input Text.
📄️ Remove image background.
Remove background from image url or buffer.
📄️ Detect brand
Detect brand from given image.
📄️ Generate python code.
Generate python code based on provided prompt.
📄️ Detect color.
Detect color from given image.
📄️ Too Long To Read
Creates a summary of the given text.
📄️ Detect language.
Detect language of given text.
📄️ Transcribe audio.
Transcribe an audio file to text. This supports the following file types: `flac`, `m4a`, `mp3`, `mp4`, `mpeg`, `mpga`, `oga`, `ogg`, `wav`, `webm`. The maximum file size is 25MB.
📄️ Detect labels in an image.
Detects labels in an image using the OpenAI Vision model.
📄️ Generate an image.
Generate an image based on prompt.
📄️ Extract contact information.
Extract contact information from given prompt.
📄️ Generate JavaScript code.
Generate JavaScript code based on provided prompt.
📄️ Detect mood.
Detect mood from given text.
📄️ Detect face.
Detect face from given image.
📄️ PDF Optical Character Recognition.
PDF Optical Character Recognition.
📄️ Detect email type.
Detect email type from provided subject and body.ß
📄️ Check content policy.
Check if the content is appropriate to be posted on the internet.
📄️ Translate text to a specified language.
Translates the provided text into the specified target language using OpenAI.
📄️ Extract text from given image
Extracts text and specific data from documents, supporting OCR and specialized workflows.
📄️ Find the best match for a query string from a list of targets.
This function takes a query string and a list of target strings. It uses an LLM to find the best match(es), accounting for variations in the query string, and returns the closest match(es) based on the options provided.
📄️ Extract a custom object from a given text.
This function takes a text input, a context for added relevance, and a list of fields with their descriptions. It leverages an LLM to extract the specified information from the text and organizes it into a structured object.