refactor!: Simplify Output Parsers #367
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Outdated suggestions cannot be applied.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.
Relates to #266
The
BaseOutputParser
class has been reworked. Before it was strongly coupled to LLMs/ChatModels and they could not be used with other types ofRunnables
. You couldn't pass options to the parser either.Now the
BaseOutputParser
takes 3 generic parameters:ParserInput
(extends Object?
): the type of the input to the parser.CallOptions
(extends OutputParserOptions
): the type of the options to pass to the parser.ParserOutput
(extends Object?
): the type of the output of the parser.Migration guide
StringOutputParser
You now have to specify in input type in the generic parameter of
StringOutputParser
.If you were using a
StringOutputParser
with an llm (e.g.OpenAI
):Before:
After:
If you were using a
StringOutputParser
with a Chat Model (e.g.ChatOpenAI
):Before:
After:
If you were using a
StringOutputParser
defined inside the chain, the generic type will still be inferred automatically: