View source: R/runCodeInResponse.R
runCodeInResponse | R Documentation |
The function extracts and executes the code in the response. If required it can try to correct errors in the code via different strategies.
runCodeInResponse(
response,
prompt = NULL,
agent = NULL,
context = NULL,
correction = c("none", "selfcorrect", "sampleMore", "sampleThenCorrect",
"correctThenSample"),
attempts = 3,
output.file = NULL,
...
)
response |
response to be parsed for code and executed |
prompt |
prompt for the response, if correction="none" it is not needed |
agent |
AI agent, if correction="none" it is not needed |
context |
context for the prompt, if correction="none" it is not needed |
correction |
"none" no code correction is needed. "selfcorrect" feedback the errors to LLM and ask for fix. "sampleMore" sample responses for the #prompt until an executable code is returned or number of attempts reached. "correctThenSample" first try self-correct "attempt" number of times. If no executable code is returned. It will sample new responses "attempt" number of times or until executable code |
attempts |
Numeric value denoting how many times the code should be sent back for fixing. |
output.file |
Optional output file created holding parsed code |
... |
arguments to sendPrompt() |
A list containing the following elements:
init.response |
A character vector representing the initial prompt response. |
init.blocks |
A list of initial blocks. |
final.blocks |
A list of final blocks. |
code.works |
A boolean value indicating whether the code works. |
exec.result |
A character string representing the execution results. |
tried.attempts |
An integer representing the number of attempts. |
selfcorrect
,sampleResponse
## Not run:
resp.list <- runCodeInResponse(agent,prompt,context=rbionfoExp,correction="sampleMore",attempt=2)
## End(Not run)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.