The list of previous messages between the user and the model. The chat history gives the model context for responding to the user's inputs.
Inline citations for the generated response.
The documents that the model can refer to when generating a response. Each document is a JSON string that represents the field and values of the document.
Example: '[ { \"id\": \"doc_0\", \"snippet\": \"Emperor penguins are the tallest.\", \"title\": \"Tall penguins\" }, { \"id\": \"doc_1\", \"snippet\": \"Emperor penguins only live in Antarctica.\", \"title\": \"Penguin habitats\" } ]'
If there is an error during the streaming scenario, then the {@code errorMessage} parameter contains details for the error.
Why the generation stopped.
If set to true, a search for documents is required.
The full prompt that was sent to the model if isEcho is true when request.
The generated search queries.
Contents of the response that the model generates.
A list of tool calls generated by the model.
The response to the chat conversation.