Output Parsers#

pydantic model langchain.output_parsers.CommaSeparatedListOutputParser[source]#

Parse out comma separated lists.

get_format_instructions() → str[source]#: Instructions on how the LLM output should be formatted.

parse(text: str) → List[str][source]#: Parse the output of an LLM call.

pydantic model langchain.output_parsers.DatetimeOutputParser[source]#

field format: str = '%Y-%m-%dT%H:%M:%S.%fZ'#

get_format_instructions() → str[source]#: Instructions on how the LLM output should be formatted.

parse(response: str) → datetime.datetime[source]#

Parse the output of an LLM call.

A method which takes in a string (assumed output of a language model ) and parses it into some structure.

Parameters: text – output of language model
Returns: structured output

pydantic model langchain.output_parsers.GuardrailsOutputParser[source]#

field guard: Any = None#

classmethod from_rail(rail_file: str, num_reasks: int = 1) → langchain.output_parsers.rail_parser.GuardrailsOutputParser[source]#

classmethod from_rail_string(rail_str: str, num_reasks: int = 1) → langchain.output_parsers.rail_parser.GuardrailsOutputParser[source]#

get_format_instructions() → str[source]#: Instructions on how the LLM output should be formatted.

parse(text: str) → Dict[source]#

Parse the output of an LLM call.

A method which takes in a string (assumed output of a language model ) and parses it into some structure.

Parameters: text – output of language model
Returns: structured output

pydantic model langchain.output_parsers.ListOutputParser[source]#

Class to parse the output of an LLM call to a list.

abstract parse(text: str) → List[str][source]#: Parse the output of an LLM call.

pydantic model langchain.output_parsers.OutputFixingParser[source]#

Wraps a parser and tries to fix parsing errors.

field parser: langchain.schema.BaseOutputParser[langchain.output_parsers.fix.T] [Required]#

field retry_chain: langchain.chains.llm.LLMChain [Required]#

classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, parser: langchain.schema.BaseOutputParser[langchain.output_parsers.fix.T], prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['completion', 'error', 'instructions'], output_parser=None, partial_variables={}, template='Instructions:\n--------------\n{instructions}\n--------------\nCompletion:\n--------------\n{completion}\n--------------\n\nAbove, the Completion did not satisfy the constraints given in the Instructions.\nError:\n--------------\n{error}\n--------------\n\nPlease try again. Please only respond with an answer that satisfies the constraints laid out in the Instructions:', template_format='f-string', validate_template=True)) → langchain.output_parsers.fix.OutputFixingParser[langchain.output_parsers.fix.T][source]#

get_format_instructions() → str[source]#: Instructions on how the LLM output should be formatted.

parse(completion: str) → langchain.output_parsers.fix.T[source]#

Parse the output of an LLM call.

A method which takes in a string (assumed output of a language model ) and parses it into some structure.

Parameters: text – output of language model
Returns: structured output

pydantic model langchain.output_parsers.PydanticOutputParser[source]#

field pydantic_object: Type[langchain.output_parsers.pydantic.T] [Required]#

get_format_instructions() → str[source]#: Instructions on how the LLM output should be formatted.

parse(text: str) → langchain.output_parsers.pydantic.T[source]#

Parse the output of an LLM call.

A method which takes in a string (assumed output of a language model ) and parses it into some structure.

Parameters: text – output of language model
Returns: structured output

pydantic model langchain.output_parsers.RegexDictParser[source]#

Class to parse the output into a dictionary.

field no_update_value: Optional[str] = None#

field output_key_to_format: Dict[str, str] [Required]#

field regex_pattern: str = "{}:\\s?([^.'\\n']*)\\.?"#

parse(text: str) → Dict[str, str][source]#: Parse the output of an LLM call.

pydantic model langchain.output_parsers.RegexParser[source]#

Class to parse the output into a dictionary.

field default_output_key: Optional[str] = None#

field output_keys: List[str] [Required]#

field regex: str [Required]#

parse(text: str) → Dict[str, str][source]#: Parse the output of an LLM call.

pydantic model langchain.output_parsers.ResponseSchema[source]#

field description: str [Required]#

field name: str [Required]#

field type: str = 'string'#

pydantic model langchain.output_parsers.RetryOutputParser[source]#

Wraps a parser and tries to fix parsing errors.

Does this by passing the original prompt and the completion to another LLM, and telling it the completion did not satisfy criteria in the prompt.

field parser: langchain.schema.BaseOutputParser[langchain.output_parsers.retry.T] [Required]#

field retry_chain: langchain.chains.llm.LLMChain [Required]#

classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, parser: langchain.schema.BaseOutputParser[langchain.output_parsers.retry.T], prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['completion', 'prompt'], output_parser=None, partial_variables={}, template='Prompt:\n{prompt}\nCompletion:\n{completion}\n\nAbove, the Completion did not satisfy the constraints given in the Prompt.\nPlease try again:', template_format='f-string', validate_template=True)) → langchain.output_parsers.retry.RetryOutputParser[langchain.output_parsers.retry.T][source]#

get_format_instructions() → str[source]#: Instructions on how the LLM output should be formatted.

parse(completion: str) → langchain.output_parsers.retry.T[source]#

Parse the output of an LLM call.

A method which takes in a string (assumed output of a language model ) and parses it into some structure.

Parameters: text – output of language model
Returns: structured output

parse_with_prompt(completion: str, prompt_value: langchain.schema.PromptValue) → langchain.output_parsers.retry.T[source]#

Optional method to parse the output of an LLM call with a prompt.

The prompt is largely provided in the event the OutputParser wants to retry or fix the output in some way, and needs information from the prompt to do so.

Parameters

completion – output of language model
prompt – prompt value

Returns

structured output

pydantic model langchain.output_parsers.RetryWithErrorOutputParser[source]#

Wraps a parser and tries to fix parsing errors.

Does this by passing the original prompt, the completion, AND the error that was raised to another language model and telling it that the completion did not work, and raised the given error. Differs from RetryOutputParser in that this implementation provides the error that was raised back to the LLM, which in theory should give it more information on how to fix it.

field parser: langchain.schema.BaseOutputParser[langchain.output_parsers.retry.T] [Required]#

field retry_chain: langchain.chains.llm.LLMChain [Required]#

classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, parser: langchain.schema.BaseOutputParser[langchain.output_parsers.retry.T], prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['completion', 'error', 'prompt'], output_parser=None, partial_variables={}, template='Prompt:\n{prompt}\nCompletion:\n{completion}\n\nAbove, the Completion did not satisfy the constraints given in the Prompt.\nDetails: {error}\nPlease try again:', template_format='f-string', validate_template=True)) → langchain.output_parsers.retry.RetryWithErrorOutputParser[langchain.output_parsers.retry.T][source]#

get_format_instructions() → str[source]#: Instructions on how the LLM output should be formatted.

parse(completion: str) → langchain.output_parsers.retry.T[source]#

Parse the output of an LLM call.

A method which takes in a string (assumed output of a language model ) and parses it into some structure.

Parameters: text – output of language model
Returns: structured output

parse_with_prompt(completion: str, prompt_value: langchain.schema.PromptValue) → langchain.output_parsers.retry.T[source]#

Optional method to parse the output of an LLM call with a prompt.

The prompt is largely provided in the event the OutputParser wants to retry or fix the output in some way, and needs information from the prompt to do so.

Parameters

completion – output of language model
prompt – prompt value

Returns

structured output

pydantic model langchain.output_parsers.StructuredOutputParser[source]#

field response_schemas: List[langchain.output_parsers.structured.ResponseSchema] [Required]#

classmethod from_response_schemas(response_schemas: List[langchain.output_parsers.structured.ResponseSchema]) → langchain.output_parsers.structured.StructuredOutputParser[source]#

get_format_instructions() → str[source]#: Instructions on how the LLM output should be formatted.

parse(text: str) → Any[source]#

Parse the output of an LLM call.

A method which takes in a string (assumed output of a language model ) and parses it into some structure.

Parameters: text – output of language model
Returns: structured output