Removed --prompt-source and now genai-perf infers the prompt source:
--input-dataset -> dataset
--input-file -> file
else synthetic
Added error checking when multiple flags lead to unclear prompt source.
This maintains the default behavior of synthetic as the default.
Going forward, Genai-perf will move to infer more details and improve the UX.
Great work 👍 This seems like a useful feature for the users. One thing I would add is a small test that checks if the prompt gets properly set to the input json.
Added a new option --input-file
Removed --prompt-source and now genai-perf infers the prompt source: --input-dataset -> dataset --input-file -> file else synthetic
Added error checking when multiple flags lead to unclear prompt source. This maintains the default behavior of synthetic as the default. Going forward, Genai-perf will move to infer more details and improve the UX.
Inform user the source via a info command![Screenshot 2024-05-03 at 16 02 29](https://github.com/triton-inference-server/client/assets/6505145/9657e32b-06b8-4f8f-840f-052af9f70e42)
sample prompt file:![Screenshot 2024-05-03 at 16 03 05](https://github.com/triton-inference-server/client/assets/6505145/8d5e5c4a-bb1c-423e-a098-4168d64d2101)
llm_inputs.json when using an input file:![Screenshot 2024-05-03 at 16 03 20](https://github.com/triton-inference-server/client/assets/6505145/5d17dd97-9642-4683-a17f-929e1f0300a7)