call_llm.gemini_embedding {LLMR} | R Documentation |
Call LLM API for Gemini Embedding Models
Description
This function handles embedding requests specifically for Gemini embedding models. It processes text inputs and returns embedding vectors using Google's Generative Language API.
Usage
## S3 method for class 'gemini_embedding'
call_llm(config, messages, verbose = FALSE, json = FALSE)
Arguments
config |
A configuration object created by llm_config() with provider="gemini" |
messages |
Character vector of texts to embed, or list of message objects |
verbose |
Logical indicating whether to print request details (default: FALSE) |
json |
Logical indicating whether to return raw JSON response (default: FALSE) |
Value
List containing embedding data in standard LLMR format
[Package LLMR version 0.3.0 Index]