Google's AI offering is broken up into two parts: Gemini and Vertex AI. Most enterprises are likely to use Vertex AI, and individuals are likely to use Gemini.
chat_google_gemini() doesn't support structured output with Gemini 2.5
models, so upgrade to Gemini 3 or newer if you use chat_structured().
Use google_upload() to upload files (PDFs, images, video, audio, etc.)
Authentication
These functions try a number of authentication strategies, in this order:
An API key set in the
GOOGLE_API_KEYorGEMINI_API_KEYenv var (Gemini only).Viewer-based credentials on Posit Connect, if the connectcreds package is installed.
Google's default application credentials, if the gargle package is installed.
A browser-based OAuth flow, if you're in an interactive session (Gemini only). On a hosted session (e.g. Posit Workbench or Google Colab), the browser can't redirect back to R, so you'll be shown a code to paste into the console instead. Set the
ELLMER_GEMINI_OAUTH_CLIENTenv var to"desktop"or"web"to force one flow or the other.Browser sign-in doesn't give access to file uploads, so the
$file_upload()and related methods,google_upload(), andbatch_chat()won't work with it. Use an API key or application default credentials for those.
Usage
chat_google_gemini(
system_prompt = NULL,
base_url = "https://generativelanguage.googleapis.com/v1beta/",
api_key = NULL,
credentials = NULL,
model = NULL,
params = NULL,
api_args = list(),
api_headers = character(),
echo = NULL
)
chat_google_vertex(
location = Sys.getenv("GOOGLE_CLOUD_LOCATION"),
project_id = Sys.getenv("GOOGLE_CLOUD_PROJECT"),
system_prompt = NULL,
model = NULL,
params = NULL,
api_args = list(),
api_headers = character(),
echo = NULL
)
models_google_gemini(
base_url = "https://generativelanguage.googleapis.com/v1beta/",
api_key = NULL,
credentials = NULL
)
models_google_vertex(
location = Sys.getenv("GOOGLE_CLOUD_LOCATION"),
project_id = Sys.getenv("GOOGLE_CLOUD_PROJECT"),
credentials = NULL
)Arguments
- system_prompt
A system prompt to set the behavior of the assistant.
- base_url
The base URL to the API endpoint.
- api_key
- credentials
A function that returns a list of authentication headers or
NULL, the default, to use ambient credentials. See above for details.- model
The model to use for the chat (defaults to "gemini-3.8-flash"). We regularly update the default, so we strongly recommend explicitly specifying a model for anything other than casual use. Use
models_google_gemini()to see all options.- params
Common model parameters, usually created by
params().- api_args
Named list of arbitrary extra arguments appended to the body of every chat API call.
chat_google_gemini()uses the Interactions API andchat_google_vertex()the generateContent API, so use the field names from the matching request body.- api_headers
Named character vector of arbitrary extra headers appended to every chat API call.
- echo
One of the following options:
none: don't emit any output (default when running in a function).output: echo text and tool-calling output as it streams in (default when running at the console).all: echo all input and output.
Note this only affects the
chat()method.- location
Location, e.g.
us-east1,me-central1,africa-south1orglobal.- project_id
Project ID.
Value
A Chat object.
See also
Other chatbots:
chat_anthropic(),
chat_aws_bedrock(),
chat_azure_openai(),
chat_cloudflare(),
chat_databricks(),
chat_deepseek(),
chat_github(),
chat_groq(),
chat_huggingface(),
chat_lmstudio(),
chat_mistral(),
chat_ollama(),
chat_openai(),
chat_openai_compatible(),
chat_openrouter(),
chat_perplexity(),
chat_portkey(),
chat_posit()
