调用 Google Gemini 代理的函数¶

本笔记本将向您展示如何利用函数调用功能驱动的 Google Gemini Agent。

Google 的 Gemini 2.5 Pro、Gemini 2.5 Flash、Gemini 2.5 Flash-Lite 以及 Gemini 2.0 Flash 模型均支持函数调用功能。您可以在模型概览页面查看完整的功能说明。

初始设置¶

让我们从导入一些基础组件开始。

我们主要需要以下内容：

1. Google Gemini API（使用我们自己的 llama_index LLM 类）
2. 存储对话历史记录的容器
3. 定义智能体可使用的工具集

如果你在 Colab 中打开这个 Notebook，可能需要先安装 LlamaIndex 🦙。

In [ ]:

%pip install llama-index-llms-google-genai llama-index -q

%pip install llama-index-llms-google-genai llama-index -q

In [ ]:

# import os

# os.environ["GOOGLE_API_KEY"] = "..."

# import os # os.environ["GOOGLE_API_KEY"] = "..."

让我们为智能体定义一些非常简单的计算器工具。

In [ ]:

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


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

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

确保已设置 GOOGLE_API_KEY 环境变量。若未设置，请显式指定 api_key 参数。

In [ ]:

from llama_index.llms.google_genai import GoogleGenAI
from google.genai import types

llm = GoogleGenAI(
    model="gemini-2.5-flash",
    generation_config=types.GenerateContentConfig(
        thinking_config=types.ThinkingConfig(
            thinking_budget=0
        )  # Disables thinking
    ),
)

from llama_index.llms.google_genai import GoogleGenAI from google.genai import types llm = GoogleGenAI( model="gemini-2.5-flash", generation_config=types.GenerateContentConfig( thinking_config=types.ThinkingConfig( thinking_budget=0 ) # Disables thinking ), )

初始化 Google Gemini 代理¶

此处我们初始化一个具备计算器功能的简易 Google Gemini 代理。

In [ ]:

from llama_index.core.agent.workflow import FunctionAgent

agent = FunctionAgent(
    tools=[multiply, add],
    llm=llm,
)

from llama_index.core.agent.workflow import FunctionAgent agent = FunctionAgent( tools=[multiply, add], llm=llm, )

In [ ]:

from llama_index.core.agent.workflow import ToolCallResult


async def run_agent_verbose(query: str):
    handler = agent.run(query)
    async for event in handler.stream_events():
        if isinstance(event, ToolCallResult):
            print(
                f"Called tool {event.tool_name} with args {event.tool_kwargs}\nGot result: {event.tool_output}"
            )

    return await handler

from llama_index.core.agent.workflow import ToolCallResult async def run_agent_verbose(query: str): handler = agent.run(query) async for event in handler.stream_events(): if isinstance(event, ToolCallResult): print( f"Called tool {event.tool_name} with args {event.tool_kwargs}\nGot result: {event.tool_output}" ) return await handler

聊天¶

In [ ]:

response = await run_agent_verbose("What is (121 + 2) * 5?")
print(str(response))

response = await run_agent_verbose("What is (121 + 2) * 5?") print(str(response))

Called tool add with args {'b': 2, 'a': 121}
Got result: 123
Called tool multiply with args {'a': 123, 'b': 5}
Got result: 615
The answer is 615.

In [ ]:

# inspect sources
print(response.tool_calls)

# inspect sources print(response.tool_calls)

[ToolCallResult(tool_name='add', tool_kwargs={'b': 2, 'a': 121}, tool_id='add', tool_output=ToolOutput(content='123', tool_name='add', raw_input={'args': (), 'kwargs': {'b': 2, 'a': 121}}, raw_output=123, is_error=False), return_direct=False), ToolCallResult(tool_name='multiply', tool_kwargs={'a': 123, 'b': 5}, tool_id='multiply', tool_output=ToolOutput(content='615', tool_name='multiply', raw_input={'args': (), 'kwargs': {'a': 123, 'b': 5}}, raw_output=615, is_error=False), return_direct=False)]

管理上下文/记忆¶

默认情况下，.run() 是无状态的。如需保持状态，可传入一个上下文对象。

In [ ]:

from llama_index.core.workflow import Context

agent = FunctionAgent(llm=llm)
ctx = Context(agent)

response = await agent.run("My name is John Doe", ctx=ctx)
response = await agent.run("What is my name?", ctx=ctx)

print(str(response))

from llama_index.core.workflow import Context agent = FunctionAgent(llm=llm) ctx = Context(agent) response = await agent.run("My name is John Doe", ctx=ctx) response = await agent.run("What is my name?", ctx=ctx) print(str(response))

Your name is John Doe.

基于 RAG 管道的 Google Gemini 智能体¶

基于一份简单的10K文档构建Anthropic智能体。我们使用OpenAI嵌入技术和Gemini 2.0 Flash构建RAG（检索增强生成）管道，并将其作为工具传递给Gemini 2.5 Flash智能体。

In [ ]:

!mkdir -p 'data/10k/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/uber_2021.pdf' -O 'data/10k/uber_2021.pdf'

!mkdir -p 'data/10k/' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/uber_2021.pdf' -O 'data/10k/uber_2021.pdf'

In [ ]:

from llama_index.core.tools import QueryEngineTool
from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.llms.google_genai import GoogleGenAI

embed_model = OpenAIEmbedding(model_name="text-embedding-3-large")
query_llm = GoogleGenAI(model="gemini-2.0-flash")

# load data
uber_docs = SimpleDirectoryReader(
    input_files=["./data/10k/uber_2021.pdf"]
).load_data()

# build index
uber_index = VectorStoreIndex.from_documents(
    uber_docs, embed_model=embed_model
)
uber_engine = uber_index.as_query_engine(similarity_top_k=3, llm=query_llm)
query_engine_tool = QueryEngineTool.from_defaults(
    query_engine=uber_engine,
    name="uber_10k",
    description=(
        "Provides information about Uber financials for year 2021. "
        "Use a detailed plain text question as input to the tool."
    ),
)

from llama_index.core.tools import QueryEngineTool from llama_index.core import SimpleDirectoryReader, VectorStoreIndex from llama_index.embeddings.openai import OpenAIEmbedding from llama_index.llms.google_genai import GoogleGenAI embed_model = OpenAIEmbedding(model_name="text-embedding-3-large") query_llm = GoogleGenAI(model="gemini-2.0-flash") # load data uber_docs = SimpleDirectoryReader( input_files=["./data/10k/uber_2021.pdf"] ).load_data() # build index uber_index = VectorStoreIndex.from_documents( uber_docs, embed_model=embed_model ) uber_engine = uber_index.as_query_engine(similarity_top_k=3, llm=query_llm) query_engine_tool = QueryEngineTool.from_defaults( query_engine=uber_engine, name="uber_10k", description=( "Provides information about Uber financials for year 2021. " "Use a detailed plain text question as input to the tool." ), )

In [ ]:

from llama_index.core.agent.workflow import FunctionAgent

agent = FunctionAgent(tools=[query_engine_tool], llm=llm, verbose=True)

from llama_index.core.agent.workflow import FunctionAgent agent = FunctionAgent(tools=[query_engine_tool], llm=llm, verbose=True)

In [ ]:

response = await agent.run(
    "Tell me both the risk factors and tailwinds for Uber?"
)
print(str(response))

response = await agent.run( "Tell me both the risk factors and tailwinds for Uber?" ) print(str(response))