mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-13 21:47:12 +00:00
OpenAI runnable constructor (#12455)
This commit is contained in:
Bagatur
GitHub
@@ -1,6 +1,10 @@
|
||||
from langchain.chains.openai_functions.base import (
|
||||
convert_to_openai_function,
|
||||
create_openai_fn_chain,
|
||||
create_openai_fn_runnable,
|
||||
create_structured_output_chain,
|
||||
create_structured_output_runnable,
|
||||
get_openai_output_parser,
|
||||
)
|
||||
from langchain.chains.openai_functions.citation_fuzzy_match import (
|
||||
create_citation_fuzzy_match_chain,
|
||||
@@ -19,6 +23,7 @@ from langchain.chains.openai_functions.tagging import (
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"convert_to_openai_function",
|
||||
"create_tagging_chain",
|
||||
"create_tagging_chain_pydantic",
|
||||
"create_extraction_chain_pydantic",
|
||||
@@ -28,4 +33,7 @@ __all__ = [
|
||||
"create_qa_with_sources_chain",
|
||||
"create_structured_output_chain",
|
||||
"create_openai_fn_chain",
|
||||
"create_structured_output_runnable",
|
||||
"create_openai_fn_runnable",
|
||||
"get_openai_output_parser",
|
||||
]
|
||||
|
||||
@@ -23,6 +23,8 @@ from langchain.output_parsers.openai_functions import (
|
||||
from langchain.prompts import BasePromptTemplate
|
||||
from langchain.pydantic_v1 import BaseModel
|
||||
from langchain.schema import BaseLLMOutputParser
|
||||
from langchain.schema.output_parser import BaseGenerationOutputParser, BaseOutputParser
|
||||
from langchain.schema.runnable import Runnable
|
||||
from langchain.utils.openai_functions import convert_pydantic_to_openai_function
|
||||
|
||||
PYTHON_TO_JSON_TYPES = {
|
||||
@@ -161,11 +163,23 @@ def convert_to_openai_function(
|
||||
)
|
||||
|
||||
|
||||
def _get_openai_output_parser(
|
||||
def get_openai_output_parser(
|
||||
functions: Sequence[Union[Dict[str, Any], Type[BaseModel], Callable]],
|
||||
function_names: Sequence[str],
|
||||
) -> BaseLLMOutputParser:
|
||||
"""Get the appropriate function output parser given the user functions."""
|
||||
) -> Union[BaseOutputParser, BaseGenerationOutputParser]:
|
||||
"""Get the appropriate function output parser given the user functions.
|
||||
|
||||
Args:
|
||||
functions: Sequence where element is a dictionary, a pydantic.BaseModel class,
|
||||
or a Python function. If a dictionary is passed in, it is assumed to
|
||||
already be a valid OpenAI function.
|
||||
|
||||
Returns:
|
||||
A PydanticOutputFunctionsParser if functions are Pydantic classes, otherwise
|
||||
a JsonOutputFunctionsParser. If there's only one function and it is
|
||||
not a Pydantic class, then the output parser will automatically extract
|
||||
only the function arguments and not the function name.
|
||||
"""
|
||||
function_names = [convert_to_openai_function(f)["name"] for f in functions]
|
||||
if isinstance(functions[0], type) and issubclass(functions[0], BaseModel):
|
||||
if len(functions) > 1:
|
||||
pydantic_schema: Union[Dict, Type[BaseModel]] = {
|
||||
@@ -173,14 +187,183 @@ def _get_openai_output_parser(
|
||||
}
|
||||
else:
|
||||
pydantic_schema = functions[0]
|
||||
output_parser: BaseLLMOutputParser = PydanticOutputFunctionsParser(
|
||||
pydantic_schema=pydantic_schema
|
||||
)
|
||||
output_parser: Union[
|
||||
BaseOutputParser, BaseGenerationOutputParser
|
||||
] = PydanticOutputFunctionsParser(pydantic_schema=pydantic_schema)
|
||||
else:
|
||||
output_parser = JsonOutputFunctionsParser(args_only=len(functions) <= 1)
|
||||
return output_parser
|
||||
|
||||
|
||||
def create_openai_fn_runnable(
|
||||
functions: Sequence[Union[Dict[str, Any], Type[BaseModel], Callable]],
|
||||
llm: Runnable,
|
||||
prompt: BasePromptTemplate,
|
||||
*,
|
||||
output_parser: Optional[Union[BaseOutputParser, BaseGenerationOutputParser]] = None,
|
||||
**kwargs: Any,
|
||||
) -> Runnable:
|
||||
"""Create a runnable sequence that uses OpenAI functions.
|
||||
|
||||
Args:
|
||||
functions: A sequence of either dictionaries, pydantic.BaseModels classes, or
|
||||
Python functions. If dictionaries are passed in, they are assumed to
|
||||
already be a valid OpenAI functions. If only a single
|
||||
function is passed in, then it will be enforced that the model use that
|
||||
function. pydantic.BaseModels and Python functions should have docstrings
|
||||
describing what the function does. For best results, pydantic.BaseModels
|
||||
should have descriptions of the parameters and Python functions should have
|
||||
Google Python style args descriptions in the docstring. Additionally,
|
||||
Python functions should only use primitive types (str, int, float, bool) or
|
||||
pydantic.BaseModels for arguments.
|
||||
llm: Language model to use, assumed to support the OpenAI function-calling API.
|
||||
prompt: BasePromptTemplate to pass to the model.
|
||||
output_parser: BaseLLMOutputParser to use for parsing model outputs. By default
|
||||
will be inferred from the function types. If pydantic.BaseModels are passed
|
||||
in, then the OutputParser will try to parse outputs using those. Otherwise
|
||||
model outputs will simply be parsed as JSON. If multiple functions are
|
||||
passed in and they are not pydantic.BaseModels, the chain output will
|
||||
include both the name of the function that was returned and the arguments
|
||||
to pass to the function.
|
||||
|
||||
Returns:
|
||||
A runnable sequence that will pass in the given functions to the model when run.
|
||||
|
||||
Example:
|
||||
.. code-block:: python
|
||||
|
||||
from typing import Optional
|
||||
|
||||
from langchain.chains.openai_functions import create_openai_fn_chain
|
||||
from langchain.chat_models import ChatOpenAI
|
||||
from langchain.prompts import ChatPromptTemplate
|
||||
from langchain.pydantic_v1 import BaseModel, Field
|
||||
|
||||
|
||||
class RecordPerson(BaseModel):
|
||||
\"\"\"Record some identifying information about a person.\"\"\"
|
||||
|
||||
name: str = Field(..., description="The person's name")
|
||||
age: int = Field(..., description="The person's age")
|
||||
fav_food: Optional[str] = Field(None, description="The person's favorite food")
|
||||
|
||||
|
||||
class RecordDog(BaseModel):
|
||||
\"\"\"Record some identifying information about a dog.\"\"\"
|
||||
|
||||
name: str = Field(..., description="The dog's name")
|
||||
color: str = Field(..., description="The dog's color")
|
||||
fav_food: Optional[str] = Field(None, description="The dog's favorite food")
|
||||
|
||||
|
||||
llm = ChatOpenAI(model="gpt-4", temperature=0)
|
||||
prompt = ChatPromptTemplate.from_messages(
|
||||
[
|
||||
("system", "You are a world class algorithm for recording entities."),
|
||||
("human", "Make calls to the relevant function to record the entities in the following input: {input}"),
|
||||
("human", "Tip: Make sure to answer in the correct format"),
|
||||
]
|
||||
)
|
||||
chain = create_openai_fn_runnable([RecordPerson, RecordDog], llm, prompt)
|
||||
chain.invoke({"input": "Harry was a chubby brown beagle who loved chicken"})
|
||||
# -> RecordDog(name="Harry", color="brown", fav_food="chicken")
|
||||
""" # noqa: E501
|
||||
if not functions:
|
||||
raise ValueError("Need to pass in at least one function. Received zero.")
|
||||
openai_functions = [convert_to_openai_function(f) for f in functions]
|
||||
llm_kwargs: Dict[str, Any] = {"functions": openai_functions, **kwargs}
|
||||
if len(openai_functions) == 1:
|
||||
llm_kwargs["function_call"] = {"name": openai_functions[0]["name"]}
|
||||
output_parser = output_parser or get_openai_output_parser(functions)
|
||||
return prompt | llm.bind(**llm_kwargs) | output_parser
|
||||
|
||||
|
||||
def create_structured_output_runnable(
|
||||
output_schema: Union[Dict[str, Any], Type[BaseModel]],
|
||||
llm: Runnable,
|
||||
prompt: BasePromptTemplate,
|
||||
*,
|
||||
output_parser: Optional[Union[BaseOutputParser, BaseGenerationOutputParser]] = None,
|
||||
**kwargs: Any,
|
||||
) -> Runnable:
|
||||
"""Create a runnable that uses an OpenAI function to get a structured output.
|
||||
|
||||
Args:
|
||||
output_schema: Either a dictionary or pydantic.BaseModel class. If a dictionary
|
||||
is passed in, it's assumed to already be a valid JsonSchema.
|
||||
For best results, pydantic.BaseModels should have docstrings describing what
|
||||
the schema represents and descriptions for the parameters.
|
||||
llm: Language model to use, assumed to support the OpenAI function-calling API.
|
||||
prompt: BasePromptTemplate to pass to the model.
|
||||
output_parser: BaseLLMOutputParser to use for parsing model outputs. By default
|
||||
will be inferred from the function types. If pydantic.BaseModels are passed
|
||||
in, then the OutputParser will try to parse outputs using those. Otherwise
|
||||
model outputs will simply be parsed as JSON.
|
||||
|
||||
Returns:
|
||||
A runnable sequence that will pass the given function to the model when run.
|
||||
|
||||
Example:
|
||||
.. code-block:: python
|
||||
|
||||
from typing import Optional
|
||||
|
||||
from langchain.chains.openai_functions import create_structured_output_chain
|
||||
from langchain.chat_models import ChatOpenAI
|
||||
from langchain.prompts import ChatPromptTemplate
|
||||
from langchain.pydantic_v1 import BaseModel, Field
|
||||
|
||||
class Dog(BaseModel):
|
||||
\"\"\"Identifying information about a dog.\"\"\"
|
||||
|
||||
name: str = Field(..., description="The dog's name")
|
||||
color: str = Field(..., description="The dog's color")
|
||||
fav_food: Optional[str] = Field(None, description="The dog's favorite food")
|
||||
|
||||
llm = ChatOpenAI(model="gpt-3.5-turbo-0613", temperature=0)
|
||||
prompt = ChatPromptTemplate.from_messages(
|
||||
[
|
||||
("system", "You are a world class algorithm for extracting information in structured formats."),
|
||||
("human", "Use the given format to extract information from the following input: {input}"),
|
||||
("human", "Tip: Make sure to answer in the correct format"),
|
||||
]
|
||||
)
|
||||
chain = create_structured_output_chain(Dog, llm, prompt)
|
||||
chain.invoke({"input": "Harry was a chubby brown beagle who loved chicken"})
|
||||
# -> Dog(name="Harry", color="brown", fav_food="chicken")
|
||||
""" # noqa: E501
|
||||
if isinstance(output_schema, dict):
|
||||
function: Any = {
|
||||
"name": "output_formatter",
|
||||
"description": (
|
||||
"Output formatter. Should always be used to format your response to the"
|
||||
" user."
|
||||
),
|
||||
"parameters": output_schema,
|
||||
}
|
||||
else:
|
||||
|
||||
class _OutputFormatter(BaseModel):
|
||||
"""Output formatter. Should always be used to format your response to the user.""" # noqa: E501
|
||||
|
||||
output: output_schema # type: ignore
|
||||
|
||||
function = _OutputFormatter
|
||||
output_parser = output_parser or PydanticAttrOutputFunctionsParser(
|
||||
pydantic_schema=_OutputFormatter, attr_name="output"
|
||||
)
|
||||
return create_openai_fn_runnable(
|
||||
[function],
|
||||
llm,
|
||||
prompt,
|
||||
output_parser=output_parser,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
|
||||
""" --- Legacy --- """
|
||||
|
||||
|
||||
def create_openai_fn_chain(
|
||||
functions: Sequence[Union[Dict[str, Any], Type[BaseModel], Callable]],
|
||||
llm: BaseLanguageModel,
|
||||
@@ -190,7 +373,7 @@ def create_openai_fn_chain(
|
||||
output_parser: Optional[BaseLLMOutputParser] = None,
|
||||
**kwargs: Any,
|
||||
) -> LLMChain:
|
||||
"""Create an LLM chain that uses OpenAI functions.
|
||||
"""[Legacy] Create an LLM chain that uses OpenAI functions.
|
||||
|
||||
Args:
|
||||
functions: A sequence of either dictionaries, pydantic.BaseModels classes, or
|
||||
@@ -260,8 +443,7 @@ def create_openai_fn_chain(
|
||||
if not functions:
|
||||
raise ValueError("Need to pass in at least one function. Received zero.")
|
||||
openai_functions = [convert_to_openai_function(f) for f in functions]
|
||||
fn_names = [oai_fn["name"] for oai_fn in openai_functions]
|
||||
output_parser = output_parser or _get_openai_output_parser(functions, fn_names)
|
||||
output_parser = output_parser or get_openai_output_parser(functions)
|
||||
llm_kwargs: Dict[str, Any] = {
|
||||
"functions": openai_functions,
|
||||
}
|
||||
@@ -287,7 +469,7 @@ def create_structured_output_chain(
|
||||
output_parser: Optional[BaseLLMOutputParser] = None,
|
||||
**kwargs: Any,
|
||||
) -> LLMChain:
|
||||
"""Create an LLMChain that uses an OpenAI function to get a structured output.
|
||||
"""[Legacy] Create an LLMChain that uses an OpenAI function to get a structured output.
|
||||
|
||||
Args:
|
||||
output_schema: Either a dictionary or pydantic.BaseModel class. If a dictionary
|
||||
|
||||
Reference in New Issue
Block a user