Closed eyast closed 2 months ago
it seems this problem only occurs for llm.tokens_per_minutes
but not for embeddings.llm.tokens_per_minutes
- the setting of the latter is properly reflected in the indexlog.
It seems that no matter what I enter, the value that is leveraged by the index engine is the hardcoded one in configs\defaults.py
in LLM_TOKENS_PER_MINUTE
.
To prove so, I commented this line - Pydantic would complain that tokens_per_minute
is not int
, because it's None
.
https://github.com/microsoft/graphrag/blob/daca75ff7925b93cd8b282ff067c6bdc76484e94/graphrag/config/create_graphrag_config.py#L122
I find update it to tpm and rpm in setting.yaml will work.
thanks for the tip - but it seemed strange because the same key is used for llm.embeddings.tokens_per_minute
and that seems to be working fine.
Hi folks!
Thanks for following up on this and providing workarounds. This has been fixed in #373 Will include it a part of the next version release, in the meantime, if you use the source directly please pull from latest main to address this.
Will leave the issue open until we release the next version.
0.2.0 is now live
The configuration of
tokens_per_minutes
insettings.yaml
seems not to be adapted by the indexing engine. I've tried setting it to both50000
and50_000
(as per the commented example) but I see the same outcome inindex-engine.log
= 0. I repeatedly hit 429s, no matter what I do.The content of
settings.yaml
:contents of
{run_id}\reports\index-engine.log
: