Package com.hw.langchain.schema

Class BaseOutputParser<T>

java.lang.Object

com.hw.langchain.schema.BaseLLMOutputParser<T>

com.hw.langchain.schema.BaseOutputParser<T>

All Implemented Interfaces:

Serializable

Direct Known Subclasses:

AgentOutputParser, ListOutputParser, NoOpOutputParser, StructuredOutputParser, StructuredQueryOutputParser

public abstract class BaseOutputParser<T>
extends BaseLLMOutputParser<T>

Class to parse the output of an LLM call. Output parsers help structure language model responses.

Author:

HamaWhite

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
BaseOutputParser()

Method Summary

Modifier and Type	Method	Description
String	getFormatInstructions()	Instructions on how the LLM output should be formatted.
abstract T	parse(String text)	Parse the output of an LLM call.
T	parseResult(List<? extends Generation> result)	Parse LLM Result.
Object	parseWithPrompt(String completion, PromptValue prompt)	Optional method to parse the output of an LLM call with a prompt.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

BaseOutputParser

public BaseOutputParser()

Method Details

parseResult

public T parseResult(List<? extends Generation> result)

Description copied from class: BaseLLMOutputParser

Parse LLM Result.

Specified by:

parseResult in class BaseLLMOutputParser<T>

parse

public abstract T parse(String text)

Parse the output of an LLM call. A method which takes in a string (assumed output of a language model) and parses it into some structure.

Parameters:

text - output of language model

Returns:

structured output

parseWithPrompt

public Object parseWithPrompt(String completion,
 PromptValue prompt)

Optional method to parse the output of an LLM call with a prompt. The prompt is largely provided in the event the OutputParser wants to retry or fix the output in some way, and needs information from the prompt to do so.

Parameters:

completion - output of language model

prompt - prompt value

Returns:

structured output

getFormatInstructions

public String getFormatInstructions()

Instructions on how the LLM output should be formatted.

Returns:

format instructions