The Problem:
The user is attempting to measure the performance difference between apply
and aapply
methods of langchain.chains.LLMChain
. However, aapply
method is not working as expected, resulting in a coroutine object instead of a list of results. User seeks assistance in identifying and resolving the issue to successfully execute aapply
and compare its performance with apply
.
The Solutions:
Solution 1: Using await to run async methods
The issue here is that `chain.aapply` returns a coroutine object, which is not awaited in the code. To run the coroutine and get the result, one needs to use the `await` keyword. The corrected code should look like this:
start = time()
res_aa = await chain.aapply(texts)
print(res_aa)
print(f"aapply time taken: {time() - start:.2f} seconds")
Q&A
Why res_aa not showing the output of the code?
To get the output of the async chain.aapply()
method, it needs to be awaited.
How to fix res_aa = chain.aapply(texts)
?
Change res_aa = chain.aapply(texts)
to res_aa = await chain.aapply(texts)
.
Video Explanation:
The following video, titled "Langchain Async explained. Make multiple OpenAI chatgpt API calls ...", provides additional insights and in-depth exploration related to the topics discussed in this post.
Learn about how you can use async support in langchain to make multiple parallel OpenAI gpt 3 or gpt-3.5-turbo(chat ...
The following video, titled "Langchain Async explained. Make multiple OpenAI chatgpt API calls ...", provides additional insights and in-depth exploration related to the topics discussed in this post.
Learn about how you can use async support in langchain to make multiple parallel OpenAI gpt 3 or gpt-3.5-turbo(chat ...