library(mall)
llm_use("ollama", "llama3.2")
#>
#> ── mall session object
#> Backend: ollama
#> LLM session: model:llama3.2
#> R session:
#> cache_folder:/var/folders/y_/f_0cx_291nl0s8h26t4jg6ch0000gp/T//RtmpLQHzPj/_mall_cache3a375fa49927
# Additional arguments will be passed 'as-is' to the
# downstream R function in this example, to ollama::chat()
llm_use("ollama", "llama3.2", seed = 100, temperature = 0.1)
#>
#> ── mall session object
#> Backend: ollamaLLM session: model:llama3.2
#> seed:100
#> temperature:0.1
#> R session:
#> cache_folder:/var/folders/y_/f_0cx_291nl0s8h26t4jg6ch0000gp/T//RtmpLQHzPj/_mall_cache3a375fa49927
# During the R session, you can change any argument
# individually and it will retain all of previous
# arguments used
llm_use(temperature = 0.3)
#>
#> ── mall session object
#> Backend: ollamaLLM session: model:llama3.2
#> seed:100
#> temperature:0.3
#> R session:
#> cache_folder:/var/folders/y_/f_0cx_291nl0s8h26t4jg6ch0000gp/T//RtmpLQHzPj/_mall_cache3a375fa49927
# Use .cache to modify the target folder for caching
llm_use(.cache = "_my_cache")
#>
#> ── mall session object
#> Backend: ollamaLLM session: model:llama3.2
#> seed:100
#> temperature:0.3
#> R session: cache_folder:_my_cache
# Leave .cache empty to turn off this functionality
llm_use(.cache = "")
#>
#> ── mall session object
#> Backend: ollamaLLM session: model:llama3.2
#> seed:100
#> temperature:0.3
# Use .silent to avoid the print out
llm_use(.silent = TRUE)
# Use an `ellmer` object
library(ellmer)
chat <- chat_openai(model = "gpt-4o")
llm_use(chat)
#>
#> ── mall session object
#> Backend: ellmerLLM session: model:gpt-4o
#> seed:100
#> temperature:0.3Specify the model to use
llm_use
Description
Allows us to specify the back-end provider, model to use during the current R session
Usage
llm_use(
backend = NULL,
model = NULL,
...,
.silent = FALSE,
.cache = NULL,
.force = FALSE
)Arguments
| Arguments | Description |
|---|---|
| backend | “ollama” or an ellmer Chat object. If using “ollama”, mall will use is out-of-the-box integration with that back-end. Defaults to “ollama”. |
| model | The name of model supported by the back-end provider |
| … | Additional arguments that this function will pass down to the integrating function. In the case of Ollama, it will pass those arguments to ollamar::chat(). |
| .silent | Avoids console output |
| .cache | The path to save model results, so they can be re-used if the same operation is ran again. To turn off, set this argument to an empty character: "". It defaults to a temp folder. If this argument is left NULL when calling this function, no changes to the path will be made. |
| .force | Flag that tell the function to reset all of the settings in the R session |
Value
A mall_session object