教程：构建工具调用代理

%%bash

pip install haystack-ai docstring-parser trafilatura

from getpass import getpass
import os

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass("Enter OpenAI API key:")
if "SERPERDEV_API_KEY" not in os.environ:
    os.environ["SERPERDEV_API_KEY"] = getpass("Enter SerperDev API key: ")

from haystack.components.agents import Agent
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.components.websearch import SerperDevWebSearch
from haystack.dataclasses import ChatMessage
from haystack.tools.component_tool import ComponentTool

# Create a web search tool using SerperDevWebSearch
web_tool = ComponentTool(component=SerperDevWebSearch(), name="web_tool")

# Create the agent with the web search tool
agent = Agent(chat_generator=OpenAIChatGenerator(model="gpt-4o-mini"), tools=[web_tool])

# Run the agent with a query
result = agent.run(messages=[ChatMessage.from_user("Find information about Haystack AI framework")])

# Print the final response
print(result["messages"][-1].text)

from haystack.components.generators.utils import print_streaming_chunk

agent = Agent(
    chat_generator=OpenAIChatGenerator(model="gpt-4o-mini"), tools=[web_tool], streaming_callback=print_streaming_chunk
)

result = agent.run(messages=[ChatMessage.from_user("Find information about Haystack AI framework")])

from haystack.components.builders.answer_builder import AnswerBuilder
from haystack.components.converters.html import HTMLToDocument
from haystack.components.converters.output_adapter import OutputAdapter
from haystack.components.fetchers.link_content import LinkContentFetcher
from haystack.components.websearch.serper_dev import SerperDevWebSearch
from haystack.dataclasses import ChatMessage
from haystack.core.pipeline import Pipeline

search_pipeline = Pipeline()

search_pipeline.add_component("search", SerperDevWebSearch(top_k=10))
search_pipeline.add_component("fetcher", LinkContentFetcher(timeout=3, raise_on_failure=False, retry_attempts=2))
search_pipeline.add_component("converter", HTMLToDocument())
search_pipeline.add_component(
    "output_adapter",
    OutputAdapter(
        template="""
{%- for doc in docs -%}
  {%- if doc.content -%}
  <search-result url="{{ doc.meta.url }}">
  {{ doc.content|truncate(25000) }}
  </search-result>
  {%- endif -%}
{%- endfor -%}
""",
        output_type=str,
    ),
)

search_pipeline.connect("search.links", "fetcher.urls")
search_pipeline.connect("fetcher.streams", "converter.sources")
search_pipeline.connect("converter.documents", "output_adapter.docs")

from haystack.core.super_component import SuperComponent
from haystack.tools import ComponentTool
from haystack.components.agents import Agent
from haystack.components.generators.chat import OpenAIChatGenerator

search_component = SuperComponent(
    pipeline=search_pipeline,
    input_mapping={"query": ["search.query"]},
    output_mapping={"output_adapter.output": "search_result"},
)

search_tool = ComponentTool(
    name="search",
    description="Use this tool to search for information on the internet.",
    component=search_component,
    outputs_to_string={"source": "search_result"},
)

agent = Agent(
    chat_generator=OpenAIChatGenerator(model="gpt-4o-mini"),
    tools=[search_tool],
    system_prompt="""
    You are a deep research assistant.
    You create comprehensive research reports to answer the user's questions.
    You use the 'search'-tool to answer any questions.
    You perform multiple searches until you have the information you need to answer the question.
    Make sure you research different aspects of the question.
    Use markdown to format your response.
    When you use information from the websearch results, cite your sources using markdown links.
    It is important that you cite accurately.
    """,
    exit_conditions=["text"],
    max_agent_steps=20,
)

query = "What are the latest updates on the Artemis moon mission?"
messages = [ChatMessage.from_user(query)]

agent.warm_up()
agent_output = agent.run(messages=messages)

print(agent_output["messages"][-1].text)

from IPython.display import Markdown, display

display(Markdown(agent_output["messages"][-1].text))