Returns diagnostic rows for calls whose success value is not TRUE
and, according to include, replies whose finish_reason is "length"
or "filter". Accepts results from call_llm_par() and llm_mutate().
Usage
llm_failures(x, prefix = NULL, include = c("all", "failed", "truncated"))Arguments
- x
A data frame from
call_llm_par()orllm_mutate().- prefix
For an
llm_mutate()result, the output column name whose diagnostics to summarize (e.g."answer"). Inferred automatically when a single diagnostic block is present; required when several are.- include
One of
"failed"(hard failures only),"truncated"(length/filter only), or"all"(default; both).
Value
A tibble (zero rows if nothing matched) with: row (index into x),
success, finish_reason, status_code, error_code, bad_param,
error_message, response_id. Columns absent from x are filled with
NA.
Details
Pass the original call_llm_par() result to llm_par_resume() to repeat
rows whose success value is not TRUE. Successful truncated or
filtered replies are retained. To repeat those requests, pass their
config and messages columns to call_llm_par(). A token-limit
truncation may require a larger max_tokens value in the configuration.
See also
llm_par_resume() to re-run failed rows, llm_usage().
