improve langchain prompting using native messages #1194
Merged
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Outdated suggestions cannot be applied.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.
Currently when using LangChain chain as eval, the messages are serialized as json in the llm prompt, giving really bad results.
Instead langchain llm offers a method
predict_messages
that handles the prompt in a more performant way.Changes:
This directly impact all the builtin feedback functions
Summary:
Enhances LangChain prompting by using native
predict_messages
and a new helper function_convert_message
for message conversion.Key points:
_convert_message
to convert dict toBaseMessage
predict_messages
for better performanceGenerated with ❤️ by ellipsis.dev