在进行提取时如何使用参考示例

from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder

# Define a custom prompt to provide instructions and any additional context.
# 1) You can add examples into the prompt template to improve extraction quality
# 2) Introduce additional parameters to take context into account (e.g., include metadata
#    about the document from which the text was extracted.)
prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are an expert extraction algorithm. "
            "Only extract relevant information from the text. "
            "If you do not know the value of an attribute asked "
            "to extract, return null for the attribute's value.",
        ),
        # ↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓
        MessagesPlaceholder("examples"),  # <-- EXAMPLES!
        # ↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑
        ("human", "{text}"),
    ]
)

from langchain_core.messages import (
    HumanMessage,
)

prompt.invoke(
    {"text": "this is some text", "examples": [HumanMessage(content="testing 1 2 3")]}
)

from typing import List, Optional

from langchain_openai import ChatOpenAI
from pydantic import BaseModel, Field


class Person(BaseModel):
    """Information about a person."""

    # ^ Doc-string for the entity Person.
    # This doc-string is sent to the LLM as the description of the schema Person,
    # and it can help to improve extraction results.

    # Note that:
    # 1. Each field is an `optional` -- this allows the model to decline to extract it!
    # 2. Each field has a `description` -- this description is used by the LLM.
    # Having a good description can help improve extraction results.
    name: Optional[str] = Field(..., description="The name of the person")
    hair_color: Optional[str] = Field(
        ..., description="The color of the person's hair if known"
    )
    height_in_meters: Optional[str] = Field(..., description="Height in METERs")


class Data(BaseModel):
    """Extracted data about people."""

    # Creates a model so that we can extract multiple entities.
    people: List[Person]

import uuid
from typing import Dict, List, TypedDict

from langchain_core.messages import (
    AIMessage,
    BaseMessage,
    HumanMessage,
    SystemMessage,
    ToolMessage,
)
from pydantic import BaseModel, Field


class Example(TypedDict):
    """A representation of an example consisting of text input and expected tool calls.

    For extraction, the tool calls are represented as instances of pydantic model.
    """

    input: str  # This is the example text
    tool_calls: List[BaseModel]  # Instances of pydantic model that should be extracted


def tool_example_to_messages(example: Example) -> List[BaseMessage]:
    """Convert an example into a list of messages that can be fed into an LLM.

    This code is an adapter that converts our example to a list of messages
    that can be fed into a chat model.

    The list of messages per example corresponds to:

    1) HumanMessage: contains the content from which content should be extracted.
    2) AIMessage: contains the extracted information from the model
    3) ToolMessage: contains confirmation to the model that the model requested a tool correctly.

    The ToolMessage is required because some of the chat models are hyper-optimized for agents
    rather than for an extraction use case.
    """
    messages: List[BaseMessage] = [HumanMessage(content=example["input"])]
    tool_calls = []
    for tool_call in example["tool_calls"]:
        tool_calls.append(
            {
                "id": str(uuid.uuid4()),
                "args": tool_call.dict(),
                # The name of the function right now corresponds
                # to the name of the pydantic model
                # This is implicit in the API right now,
                # and will be improved over time.
                "name": tool_call.__class__.__name__,
            },
        )
    messages.append(AIMessage(content="", tool_calls=tool_calls))
    tool_outputs = example.get("tool_outputs") or [
        "You have correctly called this tool."
    ] * len(tool_calls)
    for output, tool_call in zip(tool_outputs, tool_calls):
        messages.append(ToolMessage(content=output, tool_call_id=tool_call["id"]))
    return messages

examples = [
    (
        "The ocean is vast and blue. It's more than 20,000 feet deep. There are many fish in it.",
        Data(people=[]),
    ),
    (
        "Fiona traveled far from France to Spain.",
        Data(people=[Person(name="Fiona", height_in_meters=None, hair_color=None)]),
    ),
]


messages = []

for text, tool_call in examples:
    messages.extend(
        tool_example_to_messages({"input": text, "tool_calls": [tool_call]})
    )

example_prompt = prompt.invoke({"text": "this is some text", "examples": messages})

for message in example_prompt.messages:
    print(f"{message.type}: {message}")

runnable = prompt | llm.with_structured_output(
    schema=Data,
    method="function_calling",
    include_raw=False,
)

for _ in range(5):
    text = "The solar system is large, but earth has only 1 moon."
    print(runnable.invoke({"text": text, "examples": []}))

for _ in range(5):
    text = "The solar system is large, but earth has only 1 moon."
    print(runnable.invoke({"text": text, "examples": messages}))

runnable.invoke(
    {
        "text": "My name is Harrison. My hair is black.",
        "examples": messages,
    }
)