generate() and chat() support structured output
via format parameter.test_connection() returns httr2::response
object by default, but also support returning a logical value. #29chat() supports tool calling via
tools parameter. Added get_tool_calls() helper
function to process tools. #30generate() and chat() accept multiple
images as prompts/messages.chat() function:
validate_message(), validate_messages().encode_images_in_messages() to encode images in
messages for chat() function.create_messages() to create messages easily....
parameter to pass additional options.endpoint
parameter.... parameter
to pass additional model options to the API.host parameter
to specify the host URL. Default is NULL, which uses the
default Ollama URL.req as an output format for generate()
and chat().create(),
show(), copy(), delete(),
push(), embed() (supercedes
embeddings()), ps().chat() function (or other APIs like OpenAI):
create_message(), append_message(),
prepend_message(), delete_message(),
insert_message().ohelp() function to chat with models in
real-time.model_avail(),
image_encode_base64(), check_option_valid(),
check_options(), search_options(),
validate_options()test_connection(logical = TRUE) function to
test connection to Ollama server.list_models() function to list available
models.pull() function to pull a model from Ollama
server.delete() function to delete a model from Ollama
server.chat() function to chat with a model.generate() function to generate text from a
model.embeddings() function to get embeddings from a
model.resp_process() function to process
httr2_response objects.
Need a high-speed mirror for your open-source project?
Contact our mirror admin team at info@clientvps.com.
This archive is provided as a free public service to the community.
Proudly supported by infrastructure from VPSPulse , RxServers , BuyNumber , UnitVPS , OffshoreName and secure payment technology by ArionPay.