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Outdated suggestions cannot be applied.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.
If one were required to pass a custom cache_obj, it would necessitate passing the cache_obj during inference time, potentially leading to repetitive passes of the cache_obj. However, with this PR, such repetition will no longer be necessary:
Furthermore, the current limitation of not being able to pass cache_obj during the construction of
LangChainLLMs
prevents you from using a custom cache_obj in other sequential chains likeSQLDatabaseSequentialChain
, where only the global cache object can be used. This restriction arises because there is no provision to pass a custom cache_obj when SQLDatabaseSequentialChain calls the predict method.However, with the implementation of my update, you will have the ability to initialize LangChainLLMs with a custom cache_obj. As a result, when you pass this LangChainLLMs instance into the chain, custom cache_obj will function correctly:
I hope this clarfies the use case and why this will improve the usability of the package.