Class: Langchain::OutputParsers::StructuredOutputParser

Inherits:
Base
  • Object
show all
Defined in:
lib/langchain/output_parsers/structured_output_parser.rb

Overview

Structured Output Parser

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(schema:) ⇒ StructuredOutputParser

Initializes a new instance of the class.

Parameters:

  • schema (JSON::Schema) —

    The json schema



13
14
15
 
# File 'lib/langchain/output_parsers/structured_output_parser.rb', line 13

def initialize(schema:)
  @schema = validate_schema!(schema)
end

Instance Attribute Details

#schema ⇒ Object (readonly)

Returns the value of attribute schema.



8
9
10
 
# File 'lib/langchain/output_parsers/structured_output_parser.rb', line 8

def schema
  @schema
end

Class Method Details

.from_json_schema(schema) ⇒ Object

Creates a new instance of the class using the given JSON::Schema.

Parameters:

  • schema (JSON::Schema) —

    The JSON::Schema to use

Returns:

  • (Object) —

    A new instance of the class



29
30
31
 
# File 'lib/langchain/output_parsers/structured_output_parser.rb', line 29

def self.from_json_schema(schema)
  new(schema: schema)
end

Instance Method Details

#get_format_instructions ⇒ String

Returns a string containing instructions for how the output of a language model should be formatted according to the @schema.

according to the @schema.

Returns:

  • (String) —

    Instructions for how the output of a language model should be formatted



38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
 
# File 'lib/langchain/output_parsers/structured_output_parser.rb', line 38

def get_format_instructions
  <<~INSTRUCTIONS
    You must format your output as a JSON value that adheres to a given "JSON Schema" instance.

    "JSON Schema" is a declarative language that allows you to annotate and validate JSON documents.

    For example, the example "JSON Schema" instance {"properties": {"foo": {"description": "a list of test words", "type": "array", "items": {"type": "string"}}}, "required": ["foo"]}}
    would match an object with one required property, "foo". The "type" property specifies "foo" must be an "array", and the "description" property semantically describes it as "a list of test words". The items within "foo" must be strings.
    Thus, the object {"foo": ["bar", "baz"]} is a well-formatted instance of this example "JSON Schema". The object {"properties": {"foo": ["bar", "baz"]}}} is not well-formatted.

    Your output will be parsed and type-checked according to the provided schema instance, so make sure all fields in your output match the schema exactly and there are no trailing commas!

    Here is the JSON Schema instance your output must adhere to. Include the enclosing markdown codeblock:
    ```json
    #{schema.to_json}
    ```
  INSTRUCTIONS
end

#parse(text) ⇒ Object

Parse the output of an LLM call extracting an object that abides by the @schema

Parameters:

  • text (String) —

    Text output from the LLM call

Returns:

  • (Object) —

    object that abides by the @schema



61
62
63
64
65
66
67
68
 
# File 'lib/langchain/output_parsers/structured_output_parser.rb', line 61

def parse(text)
  json = text.include?("```") ? text.strip.split(/```(?:json)?/)[1] : text.strip
  parsed = JSON.parse(json)
  JSON::Validator.validate!(schema, parsed)
  parsed
rescue => e
  raise OutputParserException.new("Failed to parse. Text: \"#{text}\". Error: #{e}", text)
end

#to_h ⇒ Object 



17
18
19
20
21
22
 
# File 'lib/langchain/output_parsers/structured_output_parser.rb', line 17

def to_h
  {
    _type: "StructuredOutputParser",
    schema: schema.to_json
  }
end