Skip to main content

Output Parser Types

This is a list of the most popular output parsers LangChain supports. The table below has various pieces of information:

Name: The name of the output parser

Supports Streaming: Whether the output parser supports streaming.

Has Format Instructions: Whether the output parser has format instructions. This is generally available except when (a) the desired schema is not specified in the prompt but rather in other parameters (like OpenAI function calling), or (b) when the OutputParser wraps another OutputParser.

Calls LLM: Whether this output parser itself calls an LLM. This is usually only done by output parsers that attempt to correct misformatted output.

Input Type: Expected input type. Most output parsers work on both strings and messages, but some (like OpenAI Functions) need a message with specific kwargs.

Output Type: The output type of the object returned by the parser.

Description: Our commentary on this output parser and when to use it.

NameSupports StreamingHas Format InstructionsCalls LLMInput TypeOutput TypeDescription
Stringstring or MessagestringTakes language model output (either an entire response or as a stream) and converts it into a string. This is useful for standardizing chat model and LLM output and makes working with chat model outputs much more convenient.
HTTPResponsestring or MessagebinaryAllows you to stream LLM output properly formatted bytes a web HTTP response for a variety of content types.
OpenAIFunctions(Passes functions to model)Message (with function_call)JSON objectAllows you to use OpenAI function calling to structure the return output. If you are using a model that supports function calling, this is generally the most reliable method.
CSVstring or Messagestring[]Returns a list of comma separated values.
OutputFixingstring or MessageWraps another output parser. If that output parser errors, then this will pass the error message and the bad output to an LLM and ask it to fix the output.
Structuredstring or MessageRecord<string, string>An output parser that returns structured information. It is less powerful than other output parsers since it only allows for fields to be strings. This can be useful when you are working with smaller LLMs.
Datetimestring or MessageDateParses response into a JavaScript date.

Help us out by providing feedback on this documentation page: