For users on our ChatGPT Enterprise platform, we are now offering ways to allow users to upload and work with different types of documents inside ChatGPT. This capability builds on our existing Advanced Data Analysis model (formerly known as Code Interpreter) to improve performance on text-rich documents like PDFs, word documents, and presentations.
What are the new capabilities of Advanced Data Analysis for ChatGPT Enterprise customers?
Advanced Data Analysis (ADA) has been upgraded to include three new capabilities aimed at enhancing the analysis of text-rich documents:
Synthesis - Analyze information from documents to generate new content or insights
Transformation - Alter the presentation of information without changing its underlying essence
Extraction - Identify and pull out specific pieces of information from a document\
What is the context window for Advanced Data Analysis?
This version will have a 32k context window.
What document types are supported?
Current supported file types include:
Comma-separated values (.csv)
We are continually working to expand the range of supported document types.
How many documents can we upload?
Up to 10 documents can be uploaded.
What are the file size limitations?
500 MB per file.
How are documents stored?
The file retention protocol for Advanced Data Analysis remains unchanged. Files are retained while the conversation is active and for three hours after the conversation is paused, after which they are deleted. The conversation itself is preserved in accordance with the general ChatGPT behavior. To resume the conversation at a later time, the documents will need to be re-uploaded. This limitation arises from the overall file storage capacity at this time.