Frequently Asked Questions
FAQ
Provides speed and efficiency for high-volume, quality, cost-effective apps.
The best-performing image and video understanding model to handle a broad range of applications.
Supports text or chat prompts for a text or code response. Supports long-context understanding up to the maximum input token limit.
Anthropics’s Claude 3.5 Sonnet
The upgraded Claude 3.5 Sonnet is a state-of-the-art model for real-world software engineering tasks and agentic capabilities. Claude 3.5 Sonnet delivers these advancements at the same price and speed as its predecessor.
Meta's LLama 3.2
A medium-sized 90B multimodal model that can support image reasoning, such as chart and graph analysis, as well as image captioning.
The main difference between a chat and a query engine is the number of documents you can reference as part of your query. While the chat interface allows for a single document upload or web reference, once a query engine is created, it can then reference all documents at a defined location. Similar to chat, you have the option of choosing the model that responds to your prompt.
To upload a file or reference a URL when using New Chat, begin by selecting the plus sign to the right of the prompt, which will open an interface allowing you to either upload a file from your device or reference a URL in the Document URL window.
The ability for the models to reference images and video is dependent on the functionality of the particular one you select. At this time, however, the interface does not allow any images rendered by the models to be displayed in its output.
Google Cloud AI platform is structured so that your queries and uploaded data will not be used to train the available models and stay contained within the platform.