Agno

# tracing.py

import base64
import os
from openinference.instrumentation.agno import AgnoInstrumentor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk import trace as trace_sdk
from opentelemetry.sdk.trace.export import SimpleSpanProcessor
from opentelemetry import trace

# Load sensitive values from environment variables
WANDB_BASE_URL = "https://trace.wandb.ai"
# Your W&B entity/project name e.g. "myteam/myproject"
PROJECT_ID = os.environ.get("WANDB_PROJECT_ID")
# Create a W&B API key at https://wandb.ai/settings
WANDB_API_KEY = os.environ.get("WANDB_API_KEY")

WEAVE_OTLP_ENDPOINT = f"{WANDB_BASE_URL}/otel/v1/traces"
AUTH = base64.b64encode(f"api:{WANDB_API_KEY}".encode()).decode()

OTEL_EXPORTER_OTLP_HEADERS = {
    "Authorization": f"Basic {AUTH}",
    "project_id": PROJECT_ID,
}

# Create the OTLP span exporter with endpoint and headers
exporter = OTLPSpanExporter(
    endpoint=WEAVE_OTLP_ENDPOINT,
    headers=OTEL_EXPORTER_OTLP_HEADERS,
)

# Create a tracer provider and add the exporter
tracer_provider = trace_sdk.TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(exporter))

# Set the global tracer provider BEFORE importing/using Agno
trace.set_tracer_provider(tracer_provider)

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.yfinance import YFinanceTools

from dotenv import load_dotenv
load_dotenv()

# 위에서 생성한 파일에서 AgnoInstrumentor 로드
from tracing import AgnoInstrumentor

# Agno 계측 시작
AgnoInstrumentor().instrument()

# 금융 에이전트 생성
finance_agent = Agent(
    name="Finance Agent",
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[
        YFinanceTools(
            stock_price=True,
            analyst_recommendations=True,
            company_info=True,
            company_news=True
        )
    ],
    instructions=["Use tables to display data"],
    show_tool_calls=True,
    markdown=True,
)

# 에이전트 사용 - Weave가 이 호출을 자동으로 트레이스합니다
finance_agent.print_response(
    "What is the current stock price of Apple and what are the latest analyst recommendations?",
    stream=True
)

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.tools.yfinance import YFinanceTools

from dotenv import load_dotenv
load_dotenv()

# 위에서 생성한 파일에서 AgnoInstrumentor 로드
from tracing import AgnoInstrumentor

# Agno 계측 시작
AgnoInstrumentor().instrument()

# 여러 도구를 사용하는 에이전트 생성
research_agent = Agent(
    name="Research Agent",
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[
        DuckDuckGoTools(),
        YFinanceTools(stock_price=True, company_info=True),
    ],
    instructions=[
        "Search for current information and financial data",
        "Always include sources",
        "Use tables to display financial data"
    ],
    show_tool_calls=True,
    markdown=True,
)

# 에이전트 사용 - Weave가 도구 Call을 트레이스합니다
research_agent.print_response(
    "Research Tesla's recent performance and news. Include stock price and any recent developments.",
    stream=True
)

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.tools.yfinance import YFinanceTools

from dotenv import load_dotenv
load_dotenv()

# tracing.py 파일에서 AgnoInstrumentor 로드
from tracing import AgnoInstrumentor

# Start instrumenting Agno
AgnoInstrumentor().instrument()

# Create specialized agents
web_agent = Agent(
    name="Web Agent",
    role="Search the web for information",
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[DuckDuckGoTools()],
    instructions="Always include sources",
    show_tool_calls=True,
    markdown=True,
)

finance_agent = Agent(
    name="Finance Agent",
    role="Get financial data",
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[YFinanceTools(stock_price=True, analyst_recommendations=True)],
    instructions="Use tables to display data",
    show_tool_calls=True,
    markdown=True,
)

# Create a team of agents
agent_team = Agent(
    team=[web_agent, finance_agent],
    model=OpenAIChat(id="gpt-4o"),
    instructions=["Always include sources", "Use tables to display data"],
    show_tool_calls=True,
    markdown=True,
)

# 팀 사용 - Weave가 모든 에이전트 상호작용을 트레이스합니다
agent_team.print_response(
    "What's the current market sentiment around NVIDIA? Include both news analysis and financial metrics.",
    stream=True
)

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.reasoning import ReasoningTools
from agno.tools.yfinance import YFinanceTools

from dotenv import load_dotenv
load_dotenv()

# tracing.py 파일에서 AgnoInstrumentor 로드
from tracing import AgnoInstrumentor

# Agno 계측 시작
AgnoInstrumentor().instrument()

# 추론 에이전트 생성
reasoning_agent = Agent(
    name="Reasoning Finance Agent",
    model=OpenAIChat(id="gpt-4o"),
    tools=[
        ReasoningTools(add_instructions=True),
        YFinanceTools(
            stock_price=True,
            analyst_recommendations=True,
            company_info=True,
            company_news=True
        ),
    ],
    instructions="Use tables to display data and show your reasoning process",
    show_tool_calls=True,
    markdown=True,
)

# 추론 에이전트 사용
reasoning_agent.print_response(
    "Should I invest in Apple stock right now? Analyze the current situation and provide a reasoned recommendation.",
    stream=True
)

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.memory import AgentMemory
from agno.storage.sqlite import SqliteStorage

from dotenv import load_dotenv
load_dotenv()

# tracing.py 파일에서 AgnoInstrumentor 로드
from tracing import AgnoInstrumentor

# Agno 계측 시작
AgnoInstrumentor().instrument()


# 메모리가 있는 에이전트 생성
memory_agent = Agent(
    name="Memory Agent",
    model=OpenAIChat(id="gpt-4o-mini"),
    memory=AgentMemory(),
    storage=SqliteStorage(
        table_name="agent_sessions",
        db_file="agent_memory.db"
    ),
    instructions="Remember our conversation history",
    show_tool_calls=True,
    markdown=True,
)

# 첫 번째 상호작용
memory_agent.print_response("My name is John and I'm interested in AI investing strategies.")

# 두 번째 상호작용 - 에이전트가 이전 컨텍스트를 기억함
memory_agent.print_response("What specific AI companies would you recommend for my portfolio?")