为 langchain 中的嵌套 json 定义输出模式

Question

为嵌套 json 定义输出模式的推荐方法是什么，我使用的方法感觉不太理想。

# adding to planner -> from langchain.experimental.plan_and_execute import load_chat_planner

refinement_response_schemas = [
        ResponseSchema(name="plan", description="""{'1': {'step': '','tools': [],'data_sources': [],'sub_steps_needed': bool},
 '2': {'step': '','tools': [<empty list>],'data_sources': [<>], 'sub_steps_needed': bool},}"""),] #define json schema in description, works but doesn't feel proper
    
refinement_output_parser = StructuredOutputParser.from_response_schemas(refinement_response_schemas)
refinement_format_instructions = refinement_output_parser.get_format_instructions()

refinement_output_parser.parse(output)

给出：

{'plan': {'1': {'step': 'Identify the top 5 strikers in La Liga',
   'tools': [],
   'data_sources': ['sports websites', 'official league statistics'],
   'sub_steps_needed': False},
  '2': {'step': 'Identify the top 5 strikers in the Premier League',
   'tools': [],
   'data_sources': ['sports websites', 'official league statistics'],
   'sub_steps_needed': False},
    ...
  '6': {'step': 'Given the above steps taken, please respond to the users original question',
   'tools': [],
   'data_sources': [],
   'sub_steps_needed': False}}}

它有效，但我想知道是否有更好的方法来解决这个问题。

Answer 1

据我所知，推荐的方法是使用 pydantic 输出解析器而不是结构化输出解析器... python.langchain.com/docs/modules/model_io/output_parsers /\xe2\x80\xa6 （并处理嵌套此处解释... youtube.com/watch?v=yD_oDTeObJY）。

\n

例如

\n

from langchain.output_parsers import PydanticOutputParser\nfrom pydantic import BaseModel, Field, validator\nfrom typing import List, Optional\n\n...\n\nclass PlanItem(BaseModel):\n    step: str\n    tools: Optional[str] = []\n    data_sources: Optional[str] = []\n    sub_steps_needed: str\n\nclass Plan(BaseModel):\n    plan: List[PlanItem]\n\n\nparser = PydanticOutputParser(pydantic_object=Plan)\nparser.get_format_instructions()\n\n

\n