RuntimeError: asyncio.run() cannot be called from a running event loop

[michelebon]

Hi everybody, i'm new to python and llm world. I'm following some tutorials online to improve my knowledge. Since two days this tutorial gives this error in the first stage of "Advanced Usage" step:

2024-01-17 21:17:17,191 - autollm - WARNING - use_async is only supported for SimpleVectorStore. Ignoring use_async.
Parsing nodes: 100%
1/1 [00:04<00:00, 4.53s/it]

RuntimeError Traceback (most recent call last)
in <cell line: 36>()
34 similarity_top_k = 3
35
---> 36 query_engine = AutoQueryEngine.from_defaults(
37 documents=documents,
38 llm_model=llm_model,

10 frames
/usr/lib/python3.10/asyncio/runners.py in run(main, debug)
31 """
32 if events._get_running_loop() is not None:
---> 33 raise RuntimeError(
34 "asyncio.run() cannot be called from a running event loop")
35

RuntimeError: asyncio.run() cannot be called from a running event loop

How can I solve it? Thanks for help.

[michelebon]

i'm sorry, I didn't link the tutorial.

https://colab.research.google.com/github/safevideo/autollm/blob/main/examples/quickstart.ipynb

[SeeknnDestroy]

Hi @michelebon ,

Thank you so much for exploring autollm and for bringing this issue to our attention! We're thrilled to have you in our community. To quickly resolve the error you're encountering, you can use the nest_asyncio package. This package allows for nesting the asyncio event loop, which should fix the RuntimeError you're experiencing.

Here's what you can do:

1. Right before the line where the error occurs, add the following code:

   import nest_asyncio
   nest_asyncio.apply()

2. Additionally, change the embed_model parameter to embed_model="text-embedding-ada-002",.

This should help you move past the error. Meanwhile, I will be working on fixing this and updating the quickstart Colab notebook to address this issue more permanently. Keep experimenting and let us know if you encounter any more challenges!