Agent with Query Engine 工具¶

构建 Query Engine 工具¶

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

In [ ]

%pip install llama-index

%pip install llama-index

In [ ]

import os

os.environ["OPENAI_API_KEY"] = "sk-..."

import os os.environ["OPENAI_API_KEY"] = "sk-..."

In [ ]

from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.core import Settings

Settings.llm = OpenAI(model="gpt-4o-mini")
Settings.embed_model = OpenAIEmbedding(model="text-embedding-3-small")

from llama_index.llms.openai import OpenAI from llama_index.embeddings.openai import OpenAIEmbedding from llama_index.core import Settings Settings.llm = OpenAI(model="gpt-4o-mini") Settings.embed_model = OpenAIEmbedding(model="text-embedding-3-small")

In [ ]

from llama_index.core import StorageContext, load_index_from_storage

try:
    storage_context = StorageContext.from_defaults(
        persist_dir="./storage/lyft"
    )
    lyft_index = load_index_from_storage(storage_context)

    storage_context = StorageContext.from_defaults(
        persist_dir="./storage/uber"
    )
    uber_index = load_index_from_storage(storage_context)

    index_loaded = True
except:
    index_loaded = False

from llama_index.core import StorageContext, load_index_from_storage try: storage_context = StorageContext.from_defaults( persist_dir="./storage/lyft" ) lyft_index = load_index_from_storage(storage_context) storage_context = StorageContext.from_defaults( persist_dir="./storage/uber" ) uber_index = load_index_from_storage(storage_context) index_loaded = True except: index_loaded = False

下载数据

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'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/lyft_2021.pdf' -O 'data/10k/lyft_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' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/lyft_2021.pdf' -O 'data/10k/lyft_2021.pdf'

In [ ]

from llama_index.core import SimpleDirectoryReader, VectorStoreIndex

if not index_loaded:
    # load data
    lyft_docs = SimpleDirectoryReader(
        input_files=["./data/10k/lyft_2021.pdf"]
    ).load_data()
    uber_docs = SimpleDirectoryReader(
        input_files=["./data/10k/uber_2021.pdf"]
    ).load_data()

    # build index
    lyft_index = VectorStoreIndex.from_documents(lyft_docs)
    uber_index = VectorStoreIndex.from_documents(uber_docs)

    # persist index
    lyft_index.storage_context.persist(persist_dir="./storage/lyft")
    uber_index.storage_context.persist(persist_dir="./storage/uber")

from llama_index.core import SimpleDirectoryReader, VectorStoreIndex if not index_loaded: # load data lyft_docs = SimpleDirectoryReader( input_files=["./data/10k/lyft_2021.pdf"] ).load_data() uber_docs = SimpleDirectoryReader( input_files=["./data/10k/uber_2021.pdf"] ).load_data() # build index lyft_index = VectorStoreIndex.from_documents(lyft_docs) uber_index = VectorStoreIndex.from_documents(uber_docs) # persist index lyft_index.storage_context.persist(persist_dir="./storage/lyft") uber_index.storage_context.persist(persist_dir="./storage/uber")

In [ ]

lyft_engine = lyft_index.as_query_engine(similarity_top_k=3)
uber_engine = uber_index.as_query_engine(similarity_top_k=3)

lyft_engine = lyft_index.as_query_engine(similarity_top_k=3) uber_engine = uber_index.as_query_engine(similarity_top_k=3)

In [ ]

from llama_index.core.tools import QueryEngineTool

query_engine_tools = [
    QueryEngineTool.from_defaults(
        query_engine=lyft_engine,
        name="lyft_10k",
        description=(
            "Provides information about Lyft financials for year 2021. "
            "Use a detailed plain text question as input to the 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 query_engine_tools = [ QueryEngineTool.from_defaults( query_engine=lyft_engine, name="lyft_10k", description=( "提供关于 Lyft 2021 年财务信息。 " "使用详细的纯文本问题作为工具的输入。" ), ), QueryEngineTool.from_defaults( query_engine=uber_engine, name="uber_10k", description=( "提供关于 Uber 2021 年财务信息。 " "使用详细的纯文本问题作为工具的输入。" ), ), ]

设置 Agent¶

对于像 OpenAI 这样具有函数调用 API 的 LLM，我们应该使用 FunctionAgent。

对于其他 LLM，我们可以使用 ReActAgent。

In [ ]

from llama_index.core.agent.workflow import FunctionAgent, ReActAgent
from llama_index.core.workflow import Context

agent = FunctionAgent(tools=query_engine_tools, llm=OpenAI(model="gpt-4o"))

# context to hold the session/state
ctx = Context(agent)

from llama_index.core.agent.workflow import FunctionAgent, ReActAgent from llama_index.core.workflow import Context agent = FunctionAgent(tools=query_engine_tools, llm=OpenAI(model="gpt-4o")) # 用于持有会话/状态的上下文 ctx = Context(agent)

让我们来试试！¶

In [ ]

from llama_index.core.agent.workflow import ToolCallResult, AgentStream

handler = agent.run("What's the revenue for Lyft in 2021 vs Uber?", ctx=ctx)

async for ev in handler.stream_events():
    if isinstance(ev, ToolCallResult):
        print(
            f"Call {ev.tool_name} with args {ev.tool_kwargs}\nReturned: {ev.tool_output}"
        )
    elif isinstance(ev, AgentStream):
        print(ev.delta, end="", flush=True)

response = await handler

from llama_index.core.agent.workflow import ToolCallResult, AgentStream handler = agent.run("Lyft 和 Uber 在 2021 年的收入是多少？", ctx=ctx) async for ev in handler.stream_events(): if isinstance(ev, ToolCallResult): print( f"调用 {ev.tool_name}，参数 {ev.tool_kwargs}\n返回: {ev.tool_output}" ) elif isinstance(ev, AgentStream): print(ev.delta, end="", flush=True) response = await handler

Call lyft_10k with args {'input': "What was Lyft's revenue for the year 2021?"}
Returned: Lyft's revenue for the year 2021 was $3,208,323,000.
Call uber_10k with args {'input': "What was Uber's revenue for the year 2021?"}
Returned: Uber's revenue for the year 2021 was $17.455 billion.
In 2021, Lyft's revenue was approximately $3.21 billion, while Uber's revenue was significantly higher at $17.455 billion.