调用Anthropic代理功能¶

本笔记本将向您展示如何利用 Anthropic 智能代理（基于函数调用功能）进行开发。

注意： 仅 claude-3* 系列模型支持通过 Anthropic API 实现函数调用功能。

初始设置¶

让我们从导入一些基础构建模块开始。

主要需要以下几项：

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

如果您在 Colab 上打开此 Notebook，可能需要安装 LlamaIndex 🦙。

In [ ]:

%pip install llama-index
%pip install llama-index-llms-anthropic
%pip install llama-index-embeddings-openai

%pip install llama-index %pip install llama-index-llms-anthropic %pip install llama-index-embeddings-openai

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

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

In [ ]:

from llama_index.llms.anthropic import Anthropic

llm = Anthropic(model="claude-3-opus-20240229", api_key="sk-...")

from llama_index.llms.anthropic import Anthropic llm = Anthropic(model="claude-3-opus-20240229", api_key="sk-...")

初始化 Anthropic 代理¶

这里我们初始化了一个带有计算器功能的简单Anthropic智能体。

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 {'a': 121, 'b': 2}
Got result: 123
Called tool multiply with args {'a': 123, 'b': 5}
Got result: 615
Therefore, (121 + 2) * 5 = 615

In [ ]:

# inspect sources
print(response.tool_calls)

# inspect sources print(response.tool_calls)

[ToolCallResult(tool_name='add', tool_kwargs={'a': 121, 'b': 2}, tool_id='toolu_01MH6ME7ppxGPSJcCMEUAN5Q', tool_output=ToolOutput(content='123', tool_name='add', raw_input={'args': (), 'kwargs': {'a': 121, 'b': 2}}, raw_output=123, is_error=False), return_direct=False), ToolCallResult(tool_name='multiply', tool_kwargs={'a': 123, 'b': 5}, tool_id='toolu_01JE5TVERND5YC97E68gYoPw', 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 context 对象。

In [ ]:

from llama_index.core.workflow import Context

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 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))

基于 RAG 管道的 Anthropic 智能体构建¶

在简单的 10K 文档上构建 Anthropic 智能体。我们使用 OpenAI 嵌入技术和 claude-3-haiku-20240307 模型来构建 RAG（检索增强生成）管道，并将其作为工具传递给 Anthropic Opus 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'

--2025-03-24 12:52:55--  https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/uber_2021.pdf
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.111.133, 185.199.108.133, 185.199.109.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.111.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 1880483 (1.8M) [application/octet-stream]
Saving to: ‘data/10k/uber_2021.pdf’

data/10k/uber_2021. 100%[===================>]   1.79M  8.98MB/s    in 0.2s    

2025-03-24 12:52:56 (8.98 MB/s) - ‘data/10k/uber_2021.pdf’ saved [1880483/1880483]

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.anthropic import Anthropic

embed_model = OpenAIEmbedding(
    model_name="text-embedding-3-large", api_key="sk-proj-..."
)
query_llm = Anthropic(model="claude-3-haiku-20240307", api_key="sk-...")

# 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.anthropic import Anthropic embed_model = OpenAIEmbedding( model_name="text-embedding-3-large", api_key="sk-proj-..." ) query_llm = Anthropic(model="claude-3-haiku-20240307", api_key="sk-...") # 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))

In summary, based on Uber's 2021 10-K filing, some of the company's key risk factors included:

- Significant expected increases in operating expenses 
- Challenges attracting and retaining drivers, consumers, merchants, shippers, and carriers
- Risks to Uber's brand and reputation
- Challenges from Uber's historical workplace culture 
- Difficulties optimizing organizational structure and managing growth
- Risks related to criminal activity by platform users
- Risks from new offerings and technologies like autonomous vehicles
- Data security and privacy risks
- Climate change exposure 
- Reliance on third-party platforms
- Regulatory and legal risks
- Intellectual property risks

In terms of growth opportunities and tailwinds, Uber's strategy in 2021 focused on restructuring by divesting certain markets and business lines, and instead partnering with and taking minority ownership positions in local ridesharing and delivery companies in those markets. This suggests Uber saw opportunities to still participate in the growth of those markets through its investments, rather than operating independently.