private-gpt
private-gpt copied to clipboard
Ingest.py running forever
Note: if you'd like to ask a question or open a discussion, head over to the Discussions section and post it there.
Describe the bug and how to reproduce it I've transferred three PDF files (each containing 2 to a maximum of 5 pages, and less than 1 MB in size) into the 'source_documents' directory and executed the 'ingest.py' script. It's been running for over an hour. The console output appears to be consistently displaying similar content as follows:
llama_print_timings: load time = 4069.87 ms
llama_print_timings: sample time = 0.00 ms / 1 runs ( 0.00 ms per run)
llama_print_timings: prompt eval time = 37650.26 ms / 79 tokens ( 476.59 ms per token)
llama_print_timings: eval time = 0.00 ms / 1 runs ( 0.00 ms per run)
llama_print_timings: total time = 37680.04 ms
llama_print_timings: load time = 4069.87 ms
llama_print_timings: sample time = 0.00 ms / 1 runs ( 0.00 ms per run)
llama_print_timings: prompt eval time = 39766.47 ms / 84 tokens ( 473.41 ms per token)
llama_print_timings: eval time = 0.00 ms / 1 runs ( 0.00 ms per run)
llama_print_timings: total time = 39798.69 ms
llama_print_timings: load time = 4069.87 ms
llama_print_timings: sample time = 0.00 ms / 1 runs ( 0.00 ms per run)
llama_print_timings: prompt eval time = 53641.43 ms / 114 tokens ( 470.54 ms per token)
llama_print_timings: eval time = 0.00 ms / 1 runs ( 0.00 ms per run)
llama_print_timings: total time = 53685.67 ms
Expected behavior Expected to complete in few minutes,
Environment (please complete the following information):
- OS / hardware: macOS 13.4 / M2
- Python version 3.11.3
Additional context Add any other context about the problem here.