Image & File Upload
Users can upload files during the conversation to enable document-based interaction with the AI Agent.
It supports .png, .jpg, .jpeg, .webp, and .pdf formats.
When you open the "Code Interpreter" tool from the Tools tab, it supports the following formats: .c, .cs, .cpp, .csv, .doc, .docx, .html, .java, .json, .md, .pdf, .php, .pptx, .py, .rb, .tex, .txt, .css, .js, .sh, .ts, .jpeg, .jpg, .gif, .pkl, .png, .tar, .xlsx, .xml, .zip.
Uploaded files are automatically analyzed by the AI Agent to generate intelligent, context-aware responses based on the document content.
The agent can reference specific excerpts from the file to provide more detailed and accurate answers.
For example, a user can upload their resume and receive tailored job suggestions or feedback.
A drag-and-drop interface is available, making it easy and intuitive for users to upload their documents directly into the chat window.

Last updated
Was this helpful?