为新版本智能体运行回测

import getpass
import os

# Set the project name to whichever project you'd like to be testing against
project_name = "Tweet Writing Task"
os.environ["LANGSMITH_PROJECT"] = project_name
os.environ["LANGSMITH_TRACING"] = "true"

if not os.environ.get("LANGSMITH_API_KEY"):
    os.environ["LANGSMITH_API_KEY"] = getpass.getpass("YOUR API KEY")

# Optional. You can swap OpenAI for any other tool-calling chat model.
os.environ["OPENAI_API_KEY"] = "YOUR OPENAI API KEY"

# Optional. You can swap Tavily for the free DuckDuckGo search tool if preferred.
# Get Tavily API key: https://tavily.com
os.environ["TAVILY_API_KEY"] = "YOUR TAVILY API KEY"

from langchain.chat_models import init_chat_model
from langchain.agents import create_agent
from langchain_community.tools import DuckDuckGoSearchRun, TavilySearchResults
from langchain_core.rate_limiters import InMemoryRateLimiter


# We will use GPT-3.5 Turbo as the baseline and compare against GPT-4o
gpt_3_5_turbo = init_chat_model(
    "gpt-3.5-turbo",
    temperature=1,
    configurable_fields=("model", "model_provider"),
)

# The instrucitons are passed as a system message to the agent
instructions = """You are a tweet writing assistant. Given a topic, do some research and write a relevant and engaging tweet about it.
- Use at least 3 emojis in each tweet
- The tweet should be no longer than 280 characters
- Always use the search tool to gather recent information on the tweet topic
- Write the tweet only based on the search content. Do not rely on your internal knowledge
- When relevant, link to your sources
- Make your tweet as engaging as possible"""

# Define the tools our agent can use
# If you have a higher tiered Tavily API plan you can increase this
rate_limiter = InMemoryRateLimiter(requests_per_second=0.08)

# Use DuckDuckGo if you don't have a Tavily API key:
# tools = [DuckDuckGoSearchRun(rate_limiter=rate_limiter)]
tools = [TavilySearchResults(max_results=5, rate_limiter=rate_limiter)]

agent = create_agent(gpt_3_5_turbo, tools=tools, system_prompt=instructions)

fake_production_inputs = [
    "Alan turing's early childhood",
    "Economic impacts of the European Union",
    "Underrated philosophers",
    "History of the Roxie theater in San Francisco",
    "ELI5: gravitational waves",
    "The arguments for and against a parliamentary system",
    "Pivotal moments in music history",
    "Big ideas in programming languages",
    "Big questions in biology",
    "The relationship between math and reality",
    "What makes someone funny",
]

agent.batch(
    [{"messages": [{"role": "user", "content": content}]} for content in fake_production_inputs],
)

from datetime import datetime, timedelta, timezone
from uuid import uuid4
from langsmith import Client
from langsmith.beta import convert_runs_to_test

# Fetch the runs we want to convert to a dataset/experiment
client = Client()

# How we are sampling runs to include in our dataset
end_time = datetime.now(tz=timezone.utc)
start_time = end_time - timedelta(days=1)
run_filter = f'and(gt(start_time, "{start_time.isoformat()}"), lt(end_time, "{end_time.isoformat()}"))'
prod_runs = list(
    client.list_runs(
        project_name=project_name,
        is_root=True,
        filter=run_filter,
    )
)

# Name of the dataset we want to create
dataset_name = f'{project_name}-backtesting {start_time.strftime("%Y-%m-%d")}-{end_time.strftime("%Y-%m-%d")}'
# Name of the experiment we want to create from the historical runs
baseline_experiment_name = f"prod-baseline-gpt-3.5-turbo-{str(uuid4())[:4]}"

# This converts the runs to a dataset + experiment
convert_runs_to_test(
    prod_runs,
    # Name of the resulting dataset
    dataset_name=dataset_name,
    # Whether to include the run outputs as reference/ground truth
    include_outputs=False,
    # Whether to include the full traces in the resulting experiment
    # (default is to just include the root run)
    load_child_runs=True,
    # Name of the experiment so we can apply evalautors to it after
    test_project_name=baseline_experiment_name
)

import emoji
from pydantic import BaseModel, Field
from langchain_core.messages import convert_to_openai_messages

class Grade(BaseModel):
    """Grade whether a response is supported by some context."""
    grounded: bool = Field(..., description="Is the majority of the response supported by the retrieved context?")

grounded_instructions = f"""You have given somebody some contextual information and asked them to write a statement grounded in that context.

Grade whether their response is fully supported by the context you have provided. \
If any meaningful part of their statement is not backed up directly by the context you provided, then their response is not grounded. \
Otherwise it is grounded."""
grounded_model = init_chat_model(model="gpt-4o").with_structured_output(Grade)

def lt_280_chars(outputs: dict) -> bool:
    messages = convert_to_openai_messages(outputs["messages"])
    return len(messages[-1]['content']) <= 280

def gte_3_emojis(outputs: dict) -> bool:
    messages = convert_to_openai_messages(outputs["messages"])
    return len(emoji.emoji_list(messages[-1]['content'])) >= 3

async def is_grounded(outputs: dict) -> bool:
    context = ""
    messages = convert_to_openai_messages(outputs["messages"])
    for message in messages:
        if message["role"] == "tool":
            # Tool message outputs are the results returned from the Tavily/DuckDuckGo tool
            context += "\n\n" + message["content"]
    tweet = messages[-1]["content"]
    user = f"""CONTEXT PROVIDED:
    {context}

    RESPONSE GIVEN:
    {tweet}"""
    grade = await grounded_model.ainvoke([
        {"role": "system", "content": grounded_instructions},
        {"role": "user", "content": user}
    ])
    return grade.grounded

baseline_results = await client.aevaluate(
    baseline_experiment_name,
    evaluators=[lt_280_chars, gte_3_emojis, is_grounded],
)
# 如果已安装 pandas，可将结果转换为 DataFrame 查看
# baseline_results.to_pandas()

candidate_results = await client.aevaluate(
    agent.with_config(model="gpt-4o"),
    data=dataset_name,
    evaluators=[lt_280_chars, gte_3_emojis, is_grounded],
    experiment_prefix="candidate-gpt-4o",
)
# 如果已安装 pandas，可将结果转换为 DataFrame 查看
# candidate_results.to_pandas()