Quickstart notebook - Summarization task

1
%pip install -U opik openai requests PyPDF2 --quiet

1
import opik
2
import os
3
4
# Configure Opik
5
opik.configure()

1
import opik
2
3
ITERATION_SUMMARY_PROMPT = opik.Prompt(
4
    name="Iteration Summary Prompt",
5
    prompt="""
6
Document: {{document}}
7
Current summary: {{current_summary}}
8
Instruction to focus on: {{instruction}}
9
10
Generate a concise, entity-dense, and highly technical summary from the provided Document that specifically addresses the given Instruction.
11
12
Guidelines:
13
- Make every word count: If there is a current summary re-write it to improve flow, density and conciseness.
14
- Remove uninformative phrases like "the article discusses".
15
- The summary should become highly dense and concise yet self-contained, e.g. , easily understood without the Document.
16
- Make sure that the summary specifically addresses the given Instruction
17
""".rstrip().lstrip(),
18
)
19
20
FINAL_SUMMARY_PROMPT = opik.Prompt(
21
    name="Final Summary Prompt",
22
    prompt="""
23
Given this summary: {{current_summary}}
24
And this instruction to focus on: {{instruction}}
25
Create an extremely dense, final summary that captures all key technical information in the most concise form possible, while specifically addressing the given instruction.
26
""".rstrip().lstrip(),
27
)

1
from opik.integrations.openai import track_openai
2
from openai import OpenAI
3
import opik
4
5
# Use a dedicated quickstart endpoint, replace with your own OpenAI API Key in your own code
6
openai_client = track_openai(
7
    OpenAI(
8
        base_url="https://odbrly0rrk.execute-api.us-east-1.amazonaws.com/Prod/",
9
        api_key="Opik-Quickstart",
10
    )
11
)
12
13
14
@opik.track
15
def summarize_current_summary(
16
    document: str,
17
    instruction: str,
18
    current_summary: str,
19
    model: str = "gpt-4o-mini",
20
):
21
    prompt = ITERATION_SUMMARY_PROMPT.format(
22
        document=document, current_summary=current_summary, instruction=instruction
23
    )
24
25
    response = openai_client.chat.completions.create(
26
        model=model, max_tokens=4096, messages=[{"role": "user", "content": prompt}]
27
    )
28
29
    return response.choices[0].message.content
30
31
32
@opik.track
33
def iterative_density_summarization(
34
    document: str,
35
    instruction: str,
36
    density_iterations: int,
37
    model: str = "gpt-4o-mini",
38
):
39
    summary = ""
40
    for iteration in range(1, density_iterations + 1):
41
        summary = summarize_current_summary(document, instruction, summary, model)
42
    return summary
43
44
45
@opik.track
46
def final_summary(instruction: str, current_summary: str, model: str = "gpt-4o-mini"):
47
    prompt = FINAL_SUMMARY_PROMPT.format(
48
        current_summary=current_summary, instruction=instruction
49
    )
50
51
    return (
52
        openai_client.chat.completions.create(
53
            model=model, max_tokens=4096, messages=[{"role": "user", "content": prompt}]
54
        )
55
        .choices[0]
56
        .message.content
57
    )
58
59
60
@opik.track(project_name="Chain of Density Summarization")
61
def chain_of_density_summarization(
62
    document: str,
63
    instruction: str,
64
    model: str = "gpt-4o-mini",
65
    density_iterations: int = 2,
66
):
67
    summary = iterative_density_summarization(
68
        document, instruction, density_iterations, model
69
    )
70
    final_summary_text = final_summary(instruction, summary, model)
71
72
    return final_summary_text

1
import textwrap
2
3
document = """
4
Artificial intelligence (AI) is transforming industries, revolutionizing healthcare, finance, education, and even creative fields. AI systems
5
today are capable of performing tasks that previously required human intelligence, such as language processing, visual perception, and
6
decision-making. In healthcare, AI assists in diagnosing diseases, predicting patient outcomes, and even developing personalized treatment plans.
7
In finance, it helps in fraud detection, algorithmic trading, and risk management. Education systems leverage AI for personalized learning, adaptive
8
testing, and educational content generation. Despite these advancements, ethical concerns such as data privacy, bias, and the impact of AI on employment
9
remain. The future of AI holds immense potential, but also significant challenges.
10
"""
11
12
instruction = "Summarize the main contributions of AI to different industries, and highlight both its potential and associated challenges."
13
14
summary = chain_of_density_summarization(document, instruction)
15
16
print("\n".join(textwrap.wrap(summary, width=80)))

1
import opik
2
3
dataset_items = [
4
    {
5
        "pdf_url": "https://arxiv.org/pdf/2301.00234",
6
        "title": "A Survey on In-context Learning",
7
        "instruction": "Summarize the key findings on the impact of prompt engineering in in-context learning.",
8
    },
9
    {
10
        "pdf_url": "https://arxiv.org/pdf/2301.03728",
11
        "title": "Scaling Laws for Generative Mixed-Modal Language Models",
12
        "instruction": "How do scaling laws apply to generative mixed-modal models according to the paper?",
13
    },
14
    {
15
        "pdf_url": "https://arxiv.org/pdf/2308.10792",
16
        "title": "Instruction Tuning for Large Language Models: A Survey",
17
        "instruction": "What are the major challenges in instruction tuning for large language models identified in the paper?",
18
    },
19
    {
20
        "pdf_url": "https://arxiv.org/pdf/2302.08575",
21
        "title": "Foundation Models in Natural Language Processing: A Survey",
22
        "instruction": "Explain the role of foundation models in the current natural language processing landscape.",
23
    },
24
    {
25
        "pdf_url": "https://arxiv.org/pdf/2306.13398",
26
        "title": "Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey",
27
        "instruction": "What are the cutting edge techniques used in multi-modal pre-training models?",
28
    },
29
    {
30
        "pdf_url": "https://arxiv.org/pdf/2103.07492",
31
        "title": "Continual Learning in Neural Networks: An Empirical Evaluation",
32
        "instruction": "What are the main challenges of continual learning for neural networks according to the paper?",
33
    },
34
    {
35
        "pdf_url": "https://arxiv.org/pdf/2304.00685v2",
36
        "title": "Vision-Language Models for Vision Tasks: A Survey",
37
        "instruction": "What are the most widely used vision-language models?",
38
    },
39
    {
40
        "pdf_url": "https://arxiv.org/pdf/2303.08774",
41
        "title": "GPT-4 Technical Report",
42
        "instruction": "What are the main differences between GPT-4 and GPT-3.5?",
43
    },
44
    {
45
        "pdf_url": "https://arxiv.org/pdf/2406.04744",
46
        "title": "CRAG -- Comprehensive RAG Benchmark",
47
        "instruction": "What was the approach to experimenting with different data mixtures?",
48
    },
49
]
50
51
client = opik.Opik()
52
DATASET_NAME = "arXiv Papers"
53
dataset = client.get_or_create_dataset(name=DATASET_NAME)
54
dataset.insert(dataset_items)

1
from opik.evaluation.metrics import base_metric, score_result
2
import json
3
4
# We will define the response format so the output has the correct schema. You can also use structured outputs with Pydantic models for this.
5
json_schema = {
6
    "type": "json_schema",
7
    "json_schema": {
8
        "name": "summary_evaluation_schema",
9
        "schema": {
10
            "type": "object",
11
            "properties": {
12
                "relevance": {
13
                    "type": "object",
14
                    "properties": {
15
                        "score": {
16
                            "type": "integer",
17
                            "minimum": 1,
18
                            "maximum": 5,
19
                            "description": "Score between 1-5 for how well the summary addresses the instruction",
20
                        },
21
                        "explanation": {
22
                            "type": "string",
23
                            "description": "Brief explanation of the relevance score",
24
                        },
25
                    },
26
                    "required": ["score", "explanation"],
27
                },
28
                "conciseness": {
29
                    "type": "object",
30
                    "properties": {
31
                        "score": {
32
                            "type": "integer",
33
                            "minimum": 1,
34
                            "maximum": 5,
35
                            "description": "Score between 1-5 for how concise the summary is while retaining key information",
36
                        },
37
                        "explanation": {
38
                            "type": "string",
39
                            "description": "Brief explanation of the conciseness score",
40
                        },
41
                    },
42
                    "required": ["score", "explanation"],
43
                },
44
                "technical_accuracy": {
45
                    "type": "object",
46
                    "properties": {
47
                        "score": {
48
                            "type": "integer",
49
                            "minimum": 1,
50
                            "maximum": 5,
51
                            "description": "Score between 1-5 for how accurately the summary conveys technical details",
52
                        },
53
                        "explanation": {
54
                            "type": "string",
55
                            "description": "Brief explanation of the technical accuracy score",
56
                        },
57
                    },
58
                    "required": ["score", "explanation"],
59
                },
60
            },
61
            "required": ["relevance", "conciseness", "technical_accuracy"],
62
            "additionalProperties": False,
63
        },
64
    },
65
}
66
67
68
# Custom Metric: One template/prompt to extract 4 scores/results
69
class EvaluateSummary(base_metric.BaseMetric):
70
    # Constructor
71
    def __init__(self, name: str):
72
        self.name = name
73
74
    def score(
75
        self, summary: str, instruction: str, model: str = "gpt-4o-mini", **kwargs
76
    ):
77
        prompt = f"""
78
            Summary: {summary}
79
            Instruction: {instruction}
80
81
            Evaluate the summary based on the following criteria:
82
            1. Relevance (1-5): How well does the summary address the given instruction?
83
            2. Conciseness (1-5): How concise is the summary while retaining key information?
84
            3. Technical Accuracy (1-5): How accurately does the summary convey technical details?
85
86
            Your response MUST be in the following JSON format:
87
            {{
88
                "relevance": {{
89
                    "score": <int>,
90
                    "explanation": "<string>"
91
                }},
92
            "conciseness": {{
93
                "score": <int>,
94
                "explanation": "<string>"
95
                }},
96
            "technical_accuracy": {{
97
                "score": <int>,
98
                "explanation": "<string>"
99
                }}
100
            }}
101
102
            Ensure that the scores are integers between 1 and 5, and that the explanations are concise.
103
        """
104
105
        response = openai_client.chat.completions.create(
106
            model=model,
107
            max_tokens=1000,
108
            messages=[{"role": "user", "content": prompt}],
109
            response_format=json_schema,
110
        )
111
112
        eval_dict = json.loads(response.choices[0].message.content)
113
114
        return [
115
            score_result.ScoreResult(
116
                name="summary_relevance",
117
                value=eval_dict["relevance"]["score"],
118
                reason=eval_dict["relevance"]["explanation"],
119
            ),
120
            score_result.ScoreResult(
121
                name="summary_conciseness",
122
                value=eval_dict["conciseness"]["score"],
123
                reason=eval_dict["conciseness"]["explanation"],
124
            ),
125
            score_result.ScoreResult(
126
                name="summary_technical_accuracy",
127
                value=eval_dict["technical_accuracy"]["score"],
128
                reason=eval_dict["technical_accuracy"]["explanation"],
129
            ),
130
            score_result.ScoreResult(
131
                name="summary_average_score",
132
                value=round(sum(eval_dict[k]["score"] for k in eval_dict) / 3, 2),
133
                reason="The average of the 3 summary evaluation metrics",
134
            ),
135
        ]

1
import requests
2
import io
3
from PyPDF2 import PdfReader
4
from typing import Dict
5
6
7
# Load and extract text from PDFs
8
@opik.track
9
def load_pdf(pdf_url: str) -> str:
10
    # Download the PDF
11
    response = requests.get(pdf_url)
12
    pdf_file = io.BytesIO(response.content)
13
14
    # Read the PDF
15
    pdf_reader = PdfReader(pdf_file)
16
17
    # Extract text from all pages
18
    text = ""
19
    for page in pdf_reader.pages:
20
        text += page.extract_text()
21
22
    # Truncate the text to 100000 characters as this is the maximum supported by OpenAI
23
    text = text[:100000]
24
    return text
25
26
27
def evaluation_task(x: Dict):
28
    text = load_pdf(x["pdf_url"])
29
    instruction = x["instruction"]
30
    model = MODEL
31
    density_iterations = DENSITY_ITERATIONS
32
33
    result = chain_of_density_summarization(
34
        document=text,
35
        instruction=instruction,
36
        model=model,
37
        density_iterations=density_iterations,
38
    )
39
40
    return {"summary": result}

1
from opik.evaluation import evaluate
2
3
os.environ["OPIK_PROJECT_NAME"] = "summary-evaluation-prompts"
4
5
MODEL = "gpt-4o-mini"
6
DENSITY_ITERATIONS = 2
7
8
experiment_config = {
9
    "iteration_summary_prompt": ITERATION_SUMMARY_PROMPT,
10
    "final_summary_prompt": FINAL_SUMMARY_PROMPT,
11
    "model": MODEL,
12
    "density_iterations": DENSITY_ITERATIONS,
13
}
14
15
res = evaluate(
16
    dataset=dataset,
17
    experiment_config=experiment_config,
18
    task=evaluation_task,
19
    scoring_metrics=[EvaluateSummary(name="summary-metrics")],
20
    prompt=ITERATION_SUMMARY_PROMPT,
21
    project_name="Chain of Density Summarization",
22
)

1
import opik
2
3
ITERATION_SUMMARY_PROMPT = opik.Prompt(
4
    name="Iteration Summary Prompt",
5
    prompt="""Document: {{document}}
6
Current summary: {{current_summary}}
7
Instruction to focus on: {{instruction}}
8
9
Generate a concise, entity-dense, and highly technical summary from the provided Document that specifically addresses the given Instruction.
10
11
Guidelines:
12
1. **Maximize Clarity and Density**: Revise the current summary to enhance flow, density, and conciseness.
13
2. **Eliminate Redundant Language**: Avoid uninformative phrases such as "the article discusses."
14
3. **Ensure Self-Containment**: The summary should be dense and concise, easily understandable without referring back to the document.
15
4. **Align with Instruction**: Make sure the summary specifically addresses the given instruction.
16
17
""".rstrip().lstrip(),
18
)

1
from opik.evaluation import evaluate
2
3
os.environ["OPIK_PROJECT_NAME"] = "summary-evaluation-prompts"
4
5
MODEL = "gpt-4o-mini"
6
DENSITY_ITERATIONS = 2
7
8
experiment_config = {
9
    "iteration_summary_prompt": ITERATION_SUMMARY_PROMPT,
10
    "final_summary_prompt": FINAL_SUMMARY_PROMPT,
11
    "model": MODEL,
12
    "density_iterations": DENSITY_ITERATIONS,
13
}
14
15
res = evaluate(
16
    dataset=dataset,
17
    experiment_config=experiment_config,
18
    task=evaluation_task,
19
    scoring_metrics=[EvaluateSummary(name="summary-metrics")],
20
    prompt=ITERATION_SUMMARY_PROMPT,
21
    project_name="Chain of Density Summarization",
22
)