Skip to main content

Combining output parsers

Output parsers can be combined using CombiningOutputParser. This output parser takes in a list of output parsers, and will ask for (and parse) a combined output that contains all the fields of all the parsers.

npm install @langchain/openai
import { OpenAI } from "@langchain/openai";
import {
} from "langchain/output_parsers";
import { PromptTemplate } from "@langchain/core/prompts";
import { RunnableSequence } from "@langchain/core/runnables";

const answerParser = StructuredOutputParser.fromNamesAndDescriptions({
answer: "answer to the user's question",
source: "source used to answer the user's question, should be a website.",

const confidenceParser = new RegexParser(
/Confidence: (A|B|C), Explanation: (.*)/,
["confidence", "explanation"],

const parser = new CombiningOutputParser(answerParser, confidenceParser);

const chain = RunnableSequence.from([
"Answer the users question as best as possible.\n{format_instructions}\n{question}"
new OpenAI({ temperature: 0 }),

Answer the users question as best as possible.
Return the following outputs, each formatted as described below:

Output 1:
The output should be formatted as a JSON instance that conforms to the JSON schema below.

As an example, for the schema {{"properties": {{"foo": {{"title": "Foo", "description": "a list of strings", "type": "array", "items": {{"type": "string"}}}}}}, "required": ["foo"]}}}}
the object {{"foo": ["bar", "baz"]}} is a well-formatted instance of the schema. The object {{"properties": {{"foo": ["bar", "baz"]}}}} is not well-formatted.

Here is the output schema:
{"type":"object","properties":{"answer":{"type":"string","description":"answer to the user's question"},"source":{"type":"string","description":"source used to answer the user's question, should be a website."}},"required":["answer","source"],"additionalProperties":false,"$schema":""}

Output 2:
Your response should match the following regex: /Confidence: (A|B|C), Explanation: (.*)/

What is the capital of France?

const response = await chain.invoke({
question: "What is the capital of France?",
format_instructions: parser.getFormatInstructions(),

answer: 'Paris',
source: '',
confidence: 'A',
explanation: 'The capital of France is Paris.'

API Reference:

Help us out by providing feedback on this documentation page: