rag-observability-evals

# rag_eval.py
"""Evaluate RAG pipeline quality using RAGAS metrics."""
from ragas import evaluate
from ragas.metrics import (
    faithfulness,
    answer_relevancy,
    context_precision,
    context_recall,
    context_entity_recall,
    answer_similarity,
)
from datasets import Dataset
import json
import sys

def load_eval_dataset(path: str) -> Dataset:
    """Load evaluation dataset with required columns."""
    with open(path) as f:
        data = json.load(f)

    return Dataset.from_dict({
        "question": [d["question"] for d in data],
        "answer": [d["generated_answer"] for d in data],
        "contexts": [d["retrieved_contexts"] for d in data],
        "ground_truth": [d["reference_answer"] for d in data],
    })

def run_evaluation(dataset_path: str, output_path: str):
    """Run full RAGAS evaluation suite."""
    dataset = load_eval_dataset(dataset_path)

    metrics = [
        faithfulness,
        answer_relevancy,
        context_precision,
        context_recall,
        context_entity_recall,
        answer_similarity,
    ]

    results = evaluate(dataset, metrics=metrics)

    # Print summary
    print("=== RAG Evaluation Results ===")
    for metric_name, score in results.items():
        print(f"  {metric_name}: {score:.4f}")

    # Save detailed results
    with open(output_path, "w") as f:
        json.dump({
            "summary": {k: float(v) for k, v in results.items()},
            "dataset_size": len(dataset),
        }, f, indent=2)

    return results

if __name__ == "__main__":
    run_evaluation(sys.argv[1], sys.argv[2])

# groundedness.py
"""Score whether generated answers are grounded in retrieved context."""
from openai import OpenAI
import json
from typing import List

client = OpenAI()

GROUNDEDNESS_PROMPT = """You are evaluating whether an AI answer is fully grounded
in the provided context documents. Score each claim in the answer.

Context documents:
{contexts}

Answer to evaluate:
{answer}

For each distinct claim in the answer, determine:
1. SUPPORTED - the claim is directly supported by the context
2. PARTIALLY_SUPPORTED - the claim is partially supported
3. NOT_SUPPORTED - the claim has no support in the context

Return JSON:
{{
  "claims": [
    {{"claim": "...", "verdict": "SUPPORTED|PARTIALLY_SUPPORTED|NOT_SUPPORTED", "evidence": "..."}}
  ],
  "groundedness_score": <float 0-1>,
  "unsupported_claims": ["..."]
}}
"""

def score_groundedness(answer: str, contexts: List[str]) -> dict:
    """Score groundedness of a single answer against its contexts."""
    context_text = "\n---\n".join(
        f"[Document {i+1}]: {c}" for i, c in enumerate(contexts)
    )

    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{
            "role": "user",
            "content": GROUNDEDNESS_PROMPT.format(
                contexts=context_text, answer=answer
            ),
        }],
        response_format={"type": "json_object"},
        temperature=0,
    )

    return