Module●Since v1.0

openai_functions

Functions

Create a citation fuzzy match Runnable.

Example usage:

from langchain_classic.chains import create_citation_fuzzy_match_runnable
from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="gpt-4o-mini")

context = "Alice has blue eyes. Bob has brown eyes. Charlie has green eyes."
question = "What color are Bob's eyes?"

chain = create_citation_fuzzy_match_runnable(model)
chain.invoke({"question": question, "context": context})

function

get_openai_output_parser

Get the appropriate function output parser given the user functions.

deprecatedfunction

create_openai_fn_chain

[Legacy] Create an LLM chain that uses OpenAI functions.

deprecatedfunction

create_structured_output_chain

[Legacy] Create an LLMChain that uses an OpenAI function to get a structured output.

deprecatedfunction

create_citation_fuzzy_match_chain

Create a citation fuzzy match chain.

deprecatedfunction

create_extraction_chain

Creates a chain that extracts information from a passage.

deprecatedfunction

create_extraction_chain_pydantic

Creates a chain that extracts information from a passage using Pydantic schema.

deprecatedfunction

create_qa_with_sources_chain

Create a question answering chain that returns an answer with sources.

deprecatedfunction

create_qa_with_structure_chain

Create a question answering chain with structure.

Create a question answering chain that returns an answer with sources based on schema.

deprecatedfunction

create_tagging_chain

Create tagging chain from schema.

Create a chain that extracts information from a passage based on a schema.

This function is deprecated. Please use with_structured_output instead. See example usage below:

from typing_extensions import Annotated, TypedDict
from langchain_anthropic import ChatAnthropic

class Joke(TypedDict):
    """Tagged joke."""

    setup: Annotated[str, ..., "The setup of the joke"]
    punchline: Annotated[str, ..., "The punchline of the joke"]

# Or any other chat model that supports tools.
# Please reference to the documentation of structured_output
# to see an up to date list of which models support
# with_structured_output.
model = ChatAnthropic(model="claude-3-haiku-20240307", temperature=0)
structured_model = model.with_structured_output(Joke)
structured_model.invoke(
    "Why did the cat cross the road? To get to the other "
    "side... and then lay down in the middle of it!"
)

deprecatedfunction

create_tagging_chain_pydantic

Create tagging chain from Pydantic schema.

Create a chain that extracts information from a passage based on a Pydantic schema.

This function is deprecated. Please use with_structured_output instead. See example usage below:

from pydantic import BaseModel, Field
from langchain_anthropic import ChatAnthropic

class Joke(BaseModel):
    setup: str = Field(description="The setup of the joke")
    punchline: str = Field(description="The punchline to the joke")

# Or any other chat model that supports tools.
# Please reference to the documentation of structured_output
# to see an up to date list of which models support
# with_structured_output.
model = ChatAnthropic(model="claude-opus-4-1-20250805", temperature=0)
structured_model = model.with_structured_output(Joke)
structured_model.invoke(
    "Why did the cat cross the road? To get to the other "
    "side... and then lay down in the middle of it!"
)