Fireworks 函数调用指南¶

Fireworks.ai 为其大语言模型提供类似 OpenAI 的函数调用功能。这使得用户可以直接描述可用工具/函数集，让模型动态选择需要调用的正确函数，而无需用户进行复杂的提示工程。

由于我们的 Fireworks 大语言模型直接继承自 OpenAI 的类结构，因此可以复用现有的抽象层与 Fireworks 交互。

我们将通过三个层面展示这一功能：直接在模型 API 上使用、作为 Pydantic 程序（结构化输出提取）的一部分使用，以及作为智能体的一部分使用。

In [ ]:

%pip install llama-index-llms-fireworks

%pip install llama-index-llms-fireworks

In [ ]:

%pip install llama-index

%pip install llama-index

In [ ]:

import os

os.environ["FIREWORKS_API_KEY"] = ""

import os os.environ["FIREWORKS_API_KEY"] = ""

In [ ]:

from llama_index.llms.fireworks import Fireworks

## define fireworks model
llm = Fireworks(
    model="accounts/fireworks/models/firefunction-v1", temperature=0
)

from llama_index.llms.fireworks import Fireworks ## define fireworks model llm = Fireworks( model="accounts/fireworks/models/firefunction-v1", temperature=0 )

/Users/jerryliu/Programming/gpt_index/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm

大语言模型模块的函数调用功能¶

您可以直接在大语言模型模块中输入函数调用。

In [ ]:

from pydantic import BaseModel
from llama_index.llms.openai.utils import to_openai_tool


class Song(BaseModel):
    """A song with name and artist"""

    name: str
    artist: str


# this converts pydantic model into function to extract structured outputs
song_fn = to_openai_tool(Song)


response = llm.complete("Generate a song from Beyonce", tools=[song_fn])
tool_calls = response.additional_kwargs["tool_calls"]
print(tool_calls)

from pydantic import BaseModel from llama_index.llms.openai.utils import to_openai_tool class Song(BaseModel): """A song with name and artist""" name: str artist: str # this converts pydantic model into function to extract structured outputs song_fn = to_openai_tool(Song) response = llm.complete("Generate a song from Beyonce", tools=[song_fn]) tool_calls = response.additional_kwargs["tool_calls"] print(tool_calls)

[ChatCompletionMessageToolCall(id='call_34ZaM0xPl1cveODjVUpO78ra', function=Function(arguments='{"name": "Crazy in Love", "artist": "Beyonce"}', name='Song'), type='function', index=0)]

使用 Pydantic 程序¶

我们的 Pydantic 程序支持将结构化输出提取为 Pydantic 对象。OpenAIPydanticProgram 利用函数调用功能实现结构化输出提取。

In [ ]:

from llama_index.program.openai import OpenAIPydanticProgram

from llama_index.program.openai import OpenAIPydanticProgram

In [ ]:

prompt_template_str = "Generate a song about {artist_name}"
program = OpenAIPydanticProgram.from_defaults(
    output_cls=Song, prompt_template_str=prompt_template_str, llm=llm
)

prompt_template_str = "Generate a song about {artist_name}" program = OpenAIPydanticProgram.from_defaults( output_cls=Song, prompt_template_str=prompt_template_str, llm=llm )

In [ ]:

output = program(artist_name="Eminem")

output = program(artist_name="Eminem")

In [ ]:

output

output

Out[ ]:

Song(name='Rap God', artist='Eminem')

使用 OpenAI 智能代理¶

In [ ]:

from llama_index.agent.openai import OpenAIAgent

from llama_index.agent.openai import OpenAIAgent

In [ ]:

from llama_index.core.tools import BaseTool, FunctionTool


def multiply(a: int, b: int) -> int:
    """Multiple two integers and returns the result integer"""
    return a * b


multiply_tool = FunctionTool.from_defaults(fn=multiply)


def add(a: int, b: int) -> int:
    """Add two integers and returns the result integer"""
    return a + b


add_tool = FunctionTool.from_defaults(fn=add)

from llama_index.core.tools import BaseTool, FunctionTool def multiply(a: int, b: int) -> int: """Multiple two integers and returns the result integer""" return a * b multiply_tool = FunctionTool.from_defaults(fn=multiply) def add(a: int, b: int) -> int: """Add two integers and returns the result integer""" return a + b add_tool = FunctionTool.from_defaults(fn=add)

In [ ]:

agent = OpenAIAgent.from_tools(
    [multiply_tool, add_tool], llm=llm, verbose=True
)

agent = OpenAIAgent.from_tools( [multiply_tool, add_tool], llm=llm, verbose=True )

In [ ]:

response = agent.chat("What is (121 * 3) + 42?")
print(str(response))

response = agent.chat("What is (121 * 3) + 42?") print(str(response))

Added user message to memory: What is (121 * 3) + 42?
=== Calling Function ===
Calling function: multiply with args: {"a": 121, "b": 3}
Got output: 363
========================

=== Calling Function ===
Calling function: add with args: {"a": 363, "b": 42}
Got output: 405
========================

The result of (121 * 3) + 42 is 405.