Multimodal Chat Completion with Google Vertex AI > Introduction to Multimodal Chat Completion with Google Vertex AI recipe
Introduction to Multimodal Chat Completion with Google Vertex AI recipe
The Multimodal Chat Completion with Google Vertex AI recipe is based on REST and SOAP APIs. You can ask questions to the Google Vertex AI Large Language Model (LLM) based on the contexts from uploaded files or specified the file URL.
The recipe allows you to upload files or provide a publicly accessible URL with context, provide a user prompt, read the file contexts, and answer the user's questions based on the file contexts with the Google Vertex AI LLM.
You can upload files of the following formats:
•application/pdf
•audio/mpeg
•audio/mp3
•audio/wav
•image/png
•image/jpeg
•image/webp
•text/plain
•video/mov
•video/mpeg
•video/mp4
•video/mpg
•video/avi
•video/wmv
•video/mpegps
•video/flv
You can upload up to 10 files with a combined maximum total size of 5 MB.
When you specify a file URL, you must also specify the IANA MIME type, that is, the Internet Assigned Numbers Authority (IANA) Multipurpose Internet Mail Extensions (MIME) type of data.