Struct JsonOutputParser 

pub struct JsonOutputParser { /* private fields */ }

JSON output parser

Parses the LLM’s JSON string output into a serde_json::Value. Supports:

• standard JSON parsing
• extracting JSON from a Markdown code block
• optional partial-JSON parsing (for streaming scenarios)

Equivalent to Python LangChain’s JsonOutputParser.

Example

use langchainrust::output_parsers::JsonOutputParser;
use serde_json::json;

let parser = JsonOutputParser::new();
let result = parser.parse(r#"{"name": "Rust", "year": 2015}"#).await?;
assert_eq!(result["name"], "Rust");

Implementations

impl JsonOutputParser

pub fn new() -> Self

Creates a standard JSON output parser.

pub fn new_partial() -> Self

Creates a parser that supports partial-JSON parsing

In streaming scenarios the LLM may emit incomplete JSON; with this option enabled it tries to parse as much data out as possible.

Trait Implementations

impl BaseOutputParser<Value> for JsonOutputParser

fn parse<'life0, 'life1, 'async_trait>( &'life0 self, text: &'life1 str, ) -> Pin<Box<dyn Future<Output = OutputParserResult<Value>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Parses raw LLM output text into the target type

fn get_format_instructions(&self) -> String

Returns format instructions (to prompt the LLM to output in the expected format)

fn parse_with_retry<'life0, 'life1, 'async_trait>( &'life0 self, text: &'life1 str, max_retries: usize, ) -> Pin<Box<dyn Future<Output = OutputParserResult<Output>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Parsing with retry (default: genuinely retries max_retries times)

impl Default for JsonOutputParser

fn default() -> Self

Returns the “default value” for a type.

impl Runnable<LLMResult, Value> for JsonOutputParser

type Error = OutputParserError

Error type.

fn invoke<'life0, 'async_trait>( &'life0 self, input: LLMResult, _config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<Value, Self::Error>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Transforms single input to output.

fn stream<'life0, 'async_trait>( &'life0 self, input: LLMResult, _config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<Pin<Box<dyn Stream<Item = Result<Value, Self::Error>> + Send>>, Self::Error>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Streaming output - for real-time responses (LLM, etc).

fn batch<'life0, 'async_trait>( &'life0 self, inputs: Vec<Input>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<Vec<Output>, Self::Error>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Batch processing - transforms multiple inputs to outputs.

fn batch_as_completed<'life0, 'async_trait>( &'life0 self, inputs: Vec<Input>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<Vec<(usize, Output)>, Self::Error>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Batch processing that returns results in completion order.

fn transform<'life0, 'async_trait>( &'life0 self, input: Pin<Box<dyn Stream<Item = Result<Input, Self::Error>> + Send>>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<Pin<Box<dyn Stream<Item = Result<Output, Self::Error>> + Send + '_>>, Self::Error>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Stream-to-stream transformation - the core of LCEL streaming.