Actions from other AI providers.
Transforms images with Hugging Face models. Inputs: in, model, provider, num inference steps, guidance scale, strength, image, prompt, negativePrompt. Outputs: out, on error, error, url (the resulting image).
Loads a document from a given URL with Langchain. Inputs: in, type. Outputs: out, on error, error, result (the loaded document).
Splits the given documents into coherent chunks with Langchain. Inputs: in, documents, chunkSize, chunkOverlap. Outputs: out, on error, error, result (the resulting chunks).
Analyzes one or several images with a vision-capable model (Pixtral-12b) in the Mistral AI integration. Inputs: in, type, multipleImages, streaming. Outputs: error, result (the analysis).
image text to text (Hugging Face) generates text descriptions from images using Hugging Face models. Inputs: in, model, provider, prompt, image. Outputs: out, on error, error, text. It is a Hugging Face action block of the Voltask connector catalog.
text to image (Hugging Face) generates images using Hugging Face models. Inputs: in, model, provider, num inference steps, guidance scale, prompt, negativePrompt. Outputs: out, on error, error, url (the address of the generated image).
Generate embeddings (Mistral AI) generates embeddings from plain text using Mistral AI. Inputs: in, model, text. Outputs: out, on error, error, result (the embedding). It belongs to the Mistral AI connector.
