Download Gemini Batch results to a JSONL file

For inline batch requests, Gemini returns results under response$inlinedResponses$inlinedResponses. In the v1beta REST API this often comes back as a data frame with one row per request and a "response" column, where each "response" is itself a data frame of GenerateContentResponse objects.

Usage

gemini_download_batch_results(
  batch,
  requests_tbl,
  output_path,
  api_key = Sys.getenv("GEMINI_API_KEY"),
  api_version = "v1beta"
)

Arguments

batch

Either a parsed batch object (as returned by gemini_get_batch()) or a character batch name such as "batches/123...".

requests_tbl

Tibble/data frame with a custom_id column in the same order as the submitted requests.

output_path

Path to the JSONL file to create.

api_key

Optional Gemini API key (used only when batch is a name).

api_version

API version (default "v1beta").

Value

Invisibly returns output_path.

Details

This helper writes those results to a local .jsonl file where each line is a JSON object of the form:

{"custom_id": "<GEM_ID1_vs_ID2>",
 "result": {
   "type": "succeeded",
   "response": { ... GenerateContentResponse ... }
 }}

or, when an error occurred:

{"custom_id": "<GEM_ID1_vs_ID2>",
 "result": {
   "type": "errored",
   "error": { ... }
 }}

Retrieval retries

Batch metadata and result-file GET requests retry HTTP 408, 429, all 5xx responses, and transport failures, with at most three total HTTP attempts per GET. Valid Retry-After seconds or HTTP dates take precedence; otherwise retries use exponential backoff starting at 0.5 seconds plus up to 0.25 seconds of jitter, capped at 30 seconds. Other HTTP errors fail immediately. Exhaustion raises the original error with the additional class pairwiseLLM_batch_retry_exhausted. These retries retrieve the same batch; they do not resubmit comparisons or create scientific failed-attempt rows.

See also

llm_submit_pairs_batch(), llm_download_batch_results()

Other batch backends: anthropic_create_batch(), anthropic_download_batch_results(), anthropic_get_batch(), anthropic_poll_batch_until_complete(), build_anthropic_batch_requests(), build_gemini_batch_requests(), build_openai_batch_requests(), gemini_create_batch(), gemini_get_batch(), gemini_poll_batch_until_complete(), llm_download_batch_results(), llm_resume_multi_batches(), llm_submit_pairs_batch(), llm_submit_pairs_multi_batch(), openai_create_batch(), openai_download_batch_errors(), openai_download_batch_output(), openai_get_batch(), openai_poll_batch_until_complete(), openai_upload_batch_file(), run_anthropic_batch_pipeline(), run_gemini_batch_pipeline(), run_openai_batch_pipeline(), write_openai_batch_file()

Examples

# This example requires a Gemini API key and network access.
# It assumes you have already created and run a Gemini batch job.
if (FALSE) { # \dontrun{
# Name of an existing Gemini batch
batch_name <- "batches/123456"

# Requests table used to create the batch (must include custom_id)
requests_tbl <- tibble::tibble(
  custom_id = c("GEM_S01_vs_S02", "GEM_S03_vs_S04")
)

# Download inline batch results to a local JSONL file
out_file <- tempfile(fileext = ".jsonl")

gemini_download_batch_results(
  batch        = batch_name,
  requests_tbl = requests_tbl,
  output_path  = out_file
)

# Inspect the downloaded JSONL
readLines(out_file, warn = FALSE)
} # }