!pip install -qU anthropic weave pydantic requests PyPDF2 set-env-colab-kaggle-dotenv

import io
import os
from datetime import datetime, timezone

import anthropic
import requests
from pydantic import BaseModel
from PyPDF2 import PdfReader
from set_env import set_env

import weave

set_env("WANDB_API_KEY")
set_env("ANTHROPIC_API_KEY")

weave.init("summarization-chain-of-density-cookbook")
anthropic_client = anthropic.Anthropic(api_key=os.getenv("ANTHROPIC_API_KEY"))

# ArxivPaper モデルを定義する
class ArxivPaper(BaseModel):
    entry_id: str
    updated: datetime
    published: datetime
    title: str
    authors: list[str]
    summary: str
    pdf_url: str

# サンプルの ArxivPaper を作成する
arxiv_paper = ArxivPaper(
    entry_id="http://arxiv.org/abs/2406.04744v1",
    updated=datetime(2024, 6, 7, 8, 43, 7, tzinfo=timezone.utc),
    published=datetime(2024, 6, 7, 8, 43, 7, tzinfo=timezone.utc),
    title="CRAG -- Comprehensive RAG Benchmark",
    authors=["Xiao Yang", "Kai Sun", "Hao Xin"],  # 簡略化のため省略
    summary="Retrieval-Augmented Generation (RAG) has recently emerged as a promising solution...",  # 省略
    pdf_url="https://arxiv.org/pdf/2406.04744",
)

@weave.op()
def load_pdf(pdf_url: str) -> str:
    # PDFをダウンロードする
    response = requests.get(pdf_url)
    pdf_file = io.BytesIO(response.content)

    # PDFを読み込む
    pdf_reader = PdfReader(pdf_file)

    # 全ページからテキストを抽出する
    text = ""
    for page in pdf_reader.pages:
        text += page.extract_text()

    return text

# Chain of Density Summarization
@weave.op()
def summarize_current_summary(
    document: str,
    instruction: str,
    current_summary: str = "",
    iteration: int = 1,
    model: str = "claude-3-sonnet-20240229",
):
    prompt = f"""
    Document: {document}
    Current summary: {current_summary}
    Instruction to focus on: {instruction}
    Iteration: {iteration}

    Generate an increasingly concise, entity-dense, and highly technical summary from the provided document that specifically addresses the given instruction.
    """
    response = anthropic_client.messages.create(
        model=model, max_tokens=4096, messages=[{"role": "user", "content": prompt}]
    )
    return response.content[0].text

@weave.op()
def iterative_density_summarization(
    document: str,
    instruction: str,
    current_summary: str,
    density_iterations: int,
    model: str = "claude-3-sonnet-20240229",
):
    iteration_summaries = []
    for iteration in range(1, density_iterations + 1):
        current_summary = summarize_current_summary(
            document, instruction, current_summary, iteration, model
        )
        iteration_summaries.append(current_summary)
    return current_summary, iteration_summaries

@weave.op()
def final_summary(
    instruction: str, current_summary: str, model: str = "claude-3-sonnet-20240229"
):
    prompt = f"""
    Given this summary: {current_summary}
    And this instruction to focus on: {instruction}
    Create an extremely dense, final summary that captures all key technical information in the most concise form possible, while specifically addressing the given instruction.
    """
    return (
        anthropic_client.messages.create(
            model=model, max_tokens=4096, messages=[{"role": "user", "content": prompt}]
        )
        .content[0]
        .text
    )

@weave.op()
def chain_of_density_summarization(
    document: str,
    instruction: str,
    current_summary: str = "",
    model: str = "claude-3-sonnet-20240229",
    density_iterations: int = 2,
):
    current_summary, iteration_summaries = iterative_density_summarization(
        document, instruction, current_summary, density_iterations, model
    )
    final_summary_text = final_summary(instruction, current_summary, model)
    return {
        "final_summary": final_summary_text,
        "accumulated_summary": current_summary,
        "iteration_summaries": iteration_summaries,
    }

# Weave Model
class ArxivChainOfDensityPipeline(weave.Model):
    model: str = "claude-3-sonnet-20240229"
    density_iterations: int = 3

    @weave.op()
    def predict(self, paper: ArxivPaper, instruction: str) -> dict:
        text = load_pdf(paper.pdf_url)
        result = chain_of_density_summarization(
            text,
            instruction,
            model=self.model,
            density_iterations=self.density_iterations,
        )
        return result

import json

@weave.op()
def evaluate_summary(
    summary: str, instruction: str, model: str = "claude-3-sonnet-20240229"
) -> dict:
    prompt = f"""
    Summary: {summary}
    Instruction: {instruction}

    Evaluate the summary based on the following criteria:
    1. Relevance (1-5): How well does the summary address the given instruction?
    2. Conciseness (1-5): How concise is the summary while retaining key information?
    3. Technical Accuracy (1-5): How accurately does the summary convey technical details?

    Your response MUST be in the following JSON format:
    {{
        "relevance": {{
            "score": <int>,
            "explanation": "<string>"
        }},
        "conciseness": {{
            "score": <int>,
            "explanation": "<string>"
        }},
        "technical_accuracy": {{
            "score": <int>,
            "explanation": "<string>"
        }}
    }}

    Ensure that the scores are integers between 1 and 5, and that the explanations are concise.
    """
    response = anthropic_client.messages.create(
        model=model, max_tokens=1000, messages=[{"role": "user", "content": prompt}]
    )
    print(response.content[0].text)

    eval_dict = json.loads(response.content[0].text)

    return {
        "relevance": eval_dict["relevance"]["score"],
        "conciseness": eval_dict["conciseness"]["score"],
        "technical_accuracy": eval_dict["technical_accuracy"]["score"],
        "average_score": sum(eval_dict[k]["score"] for k in eval_dict) / 3,
        "evaluation_text": response.content[0].text,
    }

# Weave Dataset を作成する
dataset = weave.Dataset(
    name="arxiv_papers",
    rows=[
        {
            "paper": arxiv_paper,
            "instruction": "What was the approach to experimenting with different data mixtures?",
        },
    ],
)

weave.publish(dataset)

# スコアラー関数を定義する
@weave.op()
def quality_scorer(instruction: str, output: dict) -> dict:
    result = evaluate_summary(output["final_summary"], instruction)
    return result
python
# 評価を実行する
evaluation = weave.Evaluation(dataset=dataset, scorers=[quality_scorer])
arxiv_chain_of_density_pipeline = ArxivChainOfDensityPipeline()
results = await evaluation.evaluate(arxiv_chain_of_density_pipeline)