Find answers from the community

Updated 7 months ago

I am trying to make some queries against

I am trying to make some queries against my custom query engine in parallel. I have tried to use both concurrent futures and multiprocessing and both are throwing me random errors. My pipeline works just fine when I simply use a for loop but I want to speed up the processing time as waiting for my response is ineffective. If anyone has used a query engine in parallel with no problems please let me know!

6 comments

LLogan M

you used query_engine.aquery() ?

LLogan M

It should work tbh

LLogan M

Plain Text

tasks = []
for query_str in queries:
  tasks.append(query_engine.aquery(query_str)

responses = asyncio.gather(*tasks)

dddashed

ya know i didnt do that. makes a lotta sense. gonna try it

dddashed

@Logan M also i am looking to setup error tracking with llamaIndex. Is there a list of errors I could recieve from llamaindex or would the errors be from the underlying llm chosen? Is there any examples of it?

LLogan M

Oh man, it really could be anything 😅 api errors, http errors, value errors, etc.

Add a reply