Hi @ruthseki ,
Appreciate your response on this. please find my finding below.
Before making the batch requests, create a lookup table (e.g., in a database, data store) that maps a sequential ID to the actual request payload. Use these sequential IDs in the prompt. You then use the ID to query the lookup table for original requests.
This is not true as per my finding, Below is some id ordering in the input and output verification I have done. E.g. take a example of output for a particular keyword the line is present at 19 but in input it was present at 193.
grep -n -Eo SF1430633518SIK demoCliRuns_prediction-model-2024-12-27T16_15_53.115021Z_predictions.jsonl GeminaiBatchInput_prod_automated_v1_2024-12-27_7e9a1e3a-a9f2-408d-bae7-7559164a4ef8.jsonl
demoCliRuns_prediction-model-2024-12-27T16_15_53.115021Z_predictions.jsonl:19:SF1430633518SIK
GeminaiBatchInput_prod_automated_v1_2024-12-27_7e9a1e3a-a9f2-408d-bae7-7559164a4ef8.jsonl:193:SF1430633518SIK
Questions:
- Do I need to pass any options to make sure the output are in sequential order ?
It will also be gr8 if this information is officially updated in the documentation . I have also double verified to be sure that i am not mixing the files :).