How To Continue After Rate Limit

[TH (tinghao-ai)]

The Error is 0 <graphml xmlns="http://graphml.graphdrawing.or... ❌ create_summarized_entities None ⠙ GraphRAG Indexer ├── Loading Input (InputFileType.text) - 113 files loaded (2 filtered) ━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00 0:00:00 ├── create_base_text_units ├── create_base_extracted_entities └── create_summarized_entities ❌ Errors occurred during the pipeline run, see logs for more details.

because of the OpenAI API Rate Limit. What should I do to continue the previous thread. It's really expensive to start all over again and always have this kind of rate limit porblem.

[Alonso Guevara (AlonsoGuevara)]

There's a --resume command whe you run an index job, you just need to provide the folder name (the timestamp).
For example python -m graphrag.index --root path/to/ --resume 20241506-0123

This will pick up where your run ended.

[TH (tinghao-ai)]

Thanks for the answer. But the path should be like this /Users/Avernus/graphRagTest/output/20240707-023656 or? If I run this command it would just start like empty input output for this folder instead of continue the thread before.