StructuredOutputParser
from langchain.output_parsers import ResponseSchema, StructuredOutputParser
response_schemas = [
ResponseSchema(name="name", description="名前", type="string"),
ResponseSchema(name="length", description="体長(cm)", type="int"),
]
output_parser = StructuredOutputParser.from_response_schemas(response_schemas)
print(output_parser.get_format_instructions())
The output should be a markdown code snippet formatted in the following schema, including the leading and trailing "```json" and "```":
```json
{
"name": string // 名前
"length": int // 体長(cm)
}
```
体感StructuredOutputParserの方が失敗しにくい
PydanticOutputParser
from pydantic import BaseModel, Field
from langchain.output_parsers import PydanticOutputParser
class Bird(BaseModel):
name: str = Field(description="名前")
length: int = Field(description="体長(cm)")
output_parser = PydanticOutputParser(pydantic_object=Bird)
print(output_parser.get_format_instructions())
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:
```
{"properties": {"name": {"description": "名前", "title": "Name", "type": "string"}, "length": {"description": "体長(cm)", "title": "Length", "type": "integer"}}, "required": ["name", "length"]}
```