⚡️ Speed up create_prompt()
by 13% in libs/langchain/langchain/agents/mrkl/base.py
#36
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
📄
create_prompt()
inlibs/langchain/langchain/agents/mrkl/base.py
📈 Performance went up by
13%
(0.13x
faster)⏱️ Runtime went down from
240.60μs
to212.71μs
Explanation and details
(click to show)
In the original function, there are two list comprehensions where you're iterating over the same 'tools' object twice which can be costly if the 'tools' List is large.
Instead, you can combine these two list comprehensions into one loop on 'tools'. Also, we don't need to use join right away. We append the strings to lists and join only at the end, which should give performance improvement as string concatenation in Python creates a new string and is thus more expensive than list append.
Here is the optimized version.
Correctness verification
The new optimized code was tested for correctness. The results are listed below.
✅ 0 Passed − ⚙️ Existing Unit Tests
✅ 0 Passed − 🎨 Inspired Regression Tests
✅ 15 Passed − 🌀 Generated Regression Tests
(click to show generated tests)