UCSF Versa, Assistants, and API

Take the required UCSF Versa AI training

Request access to UCSF Versa (including API) now

Versa Assistants — Learn more about and/or request your own Versa Assistant on the UCSF Wiki. For IT help accessing UCSF Wiki.

Versa API pricing — UCSF Versa and Versa Assistants are free for UCSF users; API is subsidized by UCSF IT.

Launch Versa Chat

Launched in August 2023, the UCSF Versa platform is approved for use with all UCSF data while offering a safe and protected environment for faculty, staff, and learners to leverage generative AI technologies. Versa keeps the data inside UCSF and complies with HIPAA requirements. The UCSF Versa platform consists of three products – a general purpose chatbot interface (Versa Chat and UCSF Versa for iOS/Android), API, and then Versa Assistants built upon the Versa APIs and provided for free in Versa Chat based upon access groups determined by Versa Assistant owners.

UCSF Versa is a chat interface that allows users to engage in interactive conversations with large language models such as Azure OpenAI’s GPT-4o and GPT-4, and o1. Upon completion of this required online training course, the tool is free by request to anyone at UCSF. The web application requires VPN for remote users. The mobile app requires Okta SSO login. See our wiki for model details.

Users can input prompts and engage with the GPT model within their browser, including incorporating protected health information (P4) and de-identified clinical data (P3).

Complete the custom training on UCSF Versa (required for access), request access, or get support. 

Versa Assistants are hybrid collections of UCSF-curated documents or data available via AI Search to interact conversationally in Versa Chat powered by the Large Language Model (LLM) of choice (e.g., GPT-4o).

To learn more about the available Assistants, visit the Versa Assistants Wiki page. Note the currently available set of Assistants are provided as exemplars to inspire you or your team to create on the Versa Assistant platform. Please reach out to the team if you are interested in making a Versa Assistant or proceed directly to the Assistant Request Form if you are ready to begin. Remember, AI responses may contain inaccurate information—always verify answers independently.

API extends UCSF Versa's capabilities by providing programmers and researchers with tools to automate tasks and process large datasets. UCSF IT partially subsidizes the use of this API, and detailed pricing information can be found at Versa pricing.

With software endpoints designed to facilitate model training and inference in a secure environment, the API programmatically calls the Azure OpenAI GPT models (e.g., using Python or R in a Jupyter notebook), enabling incorporation of generative AI capabilities into your data pipeline.

API is approved for use with UCSF’s protected institutional and clinical data (P2, de-identified P3, and identified P4). See the Versa wiki for the API endpoint details features supported, such as Chat Completion and Embeddings.

The API gateway can be accessed from a RAE (Research Analysis Environment) virtual workstation with high level of support from the UCSF ARS (Academic Research Services) team or from other UCSF secure P4-approved environments with limited support (recommended for highly technical users).

Complete the custom training on Versa (required for access), request access, or get support. 

UCSF Versa products are cleared for use with UCSF protected data, including P2, P3, and P4 data. This is inclusive of being HIPAA compliant for UCSF data as well. Versa is not approved for PHI from ZSFG, SFDPH, or the VA, and sensitive data from these entities, including electronic health records, cannot be entered into Versa without IRB approval. 

The AI Tiger Team built UCSF Versa to be as minimally retentive of data as possible. Users prompts and responses to Versa are transmitted securely to the model vendors (e.g., Microsoft Azure) but are not retained beyond that user-session (aka a single conversation in the web application or after the response is returned in the API). This intentional lack of data retention is intentional and intended to help Versa users be excellent stewards of UCSF data. 

Prior to making any model available in Versa, the AI Tiger Team has taken steps with the model vendors to set up every model offered (e.g., GPT-4) in Versa so that no data is retained by the model vendor beyond that session. This means the model vendors are explicitly not allowed to use any Versa data in future model training, refinement, fine-tuning, or any similar activity. UCSF data is thus kept secure in Versa and not saved by any third party.