Elasticsearchの検索再現率を測定・改善する方法：ハイブリッド検索で0.43から0.75へ

pip install elasticsearch pandas plotly python-dotenv

ELASTICSEARCH_URL=https://your-cluster-url
ELASTICSEARCH_API_KEY=your-api-key

ID: B06XX6DS3P, Score: 9.0552, Title: Replenix Retinol Smooth + Tighten Body Lotion - Collagen-Boosting, Regenerating Anti-Aging Body Cream, Reduces Appearance of Stretch Marks, 6.7 oz.

  ID: B08XMPKJ1L, Score: 5.2699, Title: Bio-Oil Skincare Body Oil (Natural) Serum for Scars and Stretchmarks, Face and Body Moisturizer Hydrates Skin, with Organic Jojoba Oil and Vitamin E, For All Skin Types, 6.7 oz

  ID: B01CY764KQ, Score: 5.0057, Title: Nike Up Or Down Men Deodorant - Pack of 2 | Long-Lasting Fragrance, Body Spray Combo for Men | Deodorant for Active Living | Nike Men's Deo Set | Ultimate Odor Protection | Grooming Essentials | Signature Nike Scent | High-Performance Men's Deodorant

ID: B0BVV7BKTW, Score: 7.4371, Title: Large Foldable Travel Duffel Bag with Shoes Compartment

ID: B07TNPHYNV, Score: 6.6455, Title: 40 Pieces Christmas Bronze Jingle Bells Craft Small Bells

ID: B08R8FRW53, Score: 6.6335, Title: CUBY Dog and Cat Sling Carrier
ID: B08QMCQYGM, Score: 6.5259, Title: YTFGGY Whiteboard Pinstripe Tape 6 Rolls 1/8"
ID: B0CP3LQSWM, Score: 6.2994, Title: Portable Dog Water Bottle 32 Oz

Recall@k = (relevant documents found in top k) / (total relevant documents)

Precision@k = (relevant documents in top k) / k

judgments = [
    # Query 1: "running shoes" BM25 handles well (tokens appear in product titles) 
    {"query_id": "q1", "doc_id": "B09NQJFRW6", "grade": 2, "query": "running shoes"},
    {"query_id": "q1", "doc_id": "B08JMD4LMM", "grade": 2, "query": "running shoes"},
    {"query_id": "q1", "doc_id": "B08VRJ6F2Q", "grade": 2, "query": "running shoes"},
    {"query_id": "q1", "doc_id": "B07S8NRRWR", "grade": 2, "query": "running shoes"},
    {"query_id": "q1", "doc_id": "B01HD620I8", "grade": 2, "query": "running shoes"},
    {"query_id": "q1", "doc_id": "B07DX86321", "grade": 2, "query": "running shoes"},
    {"query_id": "q1", "doc_id": "B0968YVLQ8", "grade": 1, "query": "running shoes"},
    {"query_id": "q1", "doc_id": "B093QJ39ZS", "grade": 1, "query": "running shoes"},
    {"query_id": "q1", "doc_id": "B096FGSC39", "grade": 1, "query": "running shoes"},
    {"query_id": "q1", "doc_id": "B01GVQWVV2", "grade": 1, "query": "running shoes"},

    # Query 2: "skincare routine" intent-based, "routine" never appears in product titles
    {"query_id": "q2", "doc_id": "B08XMPKJ1L", "grade": 2, "query": "skincare routine"},
    {"query_id": "q2", "doc_id": "B0BN3WQB92", "grade": 2, "query": "skincare routine"},
    {"query_id": "q2", "doc_id": "B0BT7B7P5T", "grade": 2, "query": "skincare routine"},
    {"query_id": "q2", "doc_id": "B00NPA2WEY", "grade": 2, "query": "skincare routine"},
    {"query_id": "q2", "doc_id": "B06XX6DS3P", "grade": 1, "query": "skincare routine"},
    {"query_id": "q2", "doc_id": "B07PDRD1KT", "grade": 1, "query": "skincare routine"},
    {"query_id": "q2", "doc_id": "B074J7869B", "grade": 1, "query": "skincare routine"},
    {"query_id": "q2", "doc_id": "B08JV31QW4", "grade": 1, "query": "skincare routine"},
    {"query_id": "q2", "doc_id": "B00K3TVJMQ", "grade": 1, "query": "skincare routine"},

    # Query 3: "study desk setup" intent-based, products are desks/stands/organizers
    {"query_id": "q3", "doc_id": "B08CS35J2T", "grade": 2, "query": "study desk setup"},
    {"query_id": "q3", "doc_id": "B09B3LFDXJ", "grade": 2, "query": "study desk setup"},
    {"query_id": "q3", "doc_id": "B07W58LMND", "grade": 1, "query": "study desk setup"},
    {"query_id": "q3", "doc_id": "B0CHYDX91L", "grade": 1, "query": "study desk setup"},

    # Query 4: "pet travel accessories" use-case grouping, products are carriers/crates/seats
    {"query_id": "q4", "doc_id": "B08R8FRW53", "grade": 2, "query": "pet travel accessories"},
    {"query_id": "q4", "doc_id": "B01MYUYX33", "grade": 2, "query": "pet travel accessories"},
    {"query_id": "q4", "doc_id": "B003C5RKE4", "grade": 2, "query": "pet travel accessories"},
    {"query_id": "q4", "doc_id": "B09GF8GBF6", "grade": 1, "query": "pet travel accessories"},
    {"query_id": "q4", "doc_id": "B0CP3LQSWM", "grade": 1, "query": "pet travel accessories"},
]

import os
import json
import pandas as pd
import plotly.graph_objects as go
from elasticsearch import Elasticsearch, helpers
from dotenv import load_dotenv

load_dotenv()

es = Elasticsearch(
    os.getenv("ELASTICSEARCH_URL"),
    api_key=os.getenv("ELASTICSEARCH_API_KEY")
)

INDEX_NAME = "ecommerce-products"

judgments_df = pd.DataFrame(judgments)

bm25_requests = []
for query_id, query_text in (
    judgments_df[["query_id", "query"]].drop_duplicates().values
):
    relevant_docs = judgments_df[judgments_df["query_id"] == query_id]
    ratings = [
        {"_index": INDEX_NAME, "_id": row["doc_id"], "rating": row["grade"]}
        for _, row in relevant_docs.iterrows()
    ]

    bm25_requests.append({
        "id": query_id,
        "request": {
            "query": {
                "multi_match": {
                    "query": query_text,
                    "fields": ["title", "description"]
                }
            }
        },
        "ratings": ratings,
    })

bm25_eval = {
    "requests": bm25_requests,
    "metric": {"recall": {"k": 10, "relevant_rating_threshold": 1}},
}

bm25_result = es.rank_eval(index=INDEX_NAME, body=bm25_eval)
print("BM25 Recall@10:", bm25_result.body["metric_score"])

BM25 Recall@10: 0.43

INFERENCE_ENDPOINT_ID = ".jina-embeddings-v5-text-small"

index_mappings = {
    "mappings": {
        "properties": {
            "title": {"type": "text", "copy_to": "semantic_field"},
            "description": {"type": "text", "copy_to": "semantic_field"},
            "brand": {"type": "keyword"},
            "category": {"type": "keyword"},
            "semantic_field": {
                "type": "semantic_text",
                "inference_id": INFERENCE_ENDPOINT_ID,
            },
        }
    }
}

if not es.indices.exists(index=INDEX_NAME):
    es.indices.create(index=INDEX_NAME, body=index_mappings)
    print(f"Created index: {INDEX_NAME}")

def bulk_index(products, index_name):
    actions = []
    for product in products:
        doc_id = product.get("_id")
        source = {k: v for k, v in product.items() if k != "_id"}
        action = {"_index": index_name, "_source": source}
        if doc_id:
            action["_id"] = doc_id
        actions.append(action)

    success, failed = helpers.bulk(es, actions, raise_on_error=False)
    if failed:
        for error in failed:
            print(f"Error: {error}")
    else:
        print(f"Successfully indexed {success} documents")

bulk_index(products, INDEX_NAME)

score = sum(1 / (rank_constant + rank))

hybrid_requests = []

for query_id, query_text in (
    judgments_df[["query_id", "query"]].drop_duplicates().values
):
    relevant_docs = judgments_df[judgments_df["query_id"] == query_id]
    ratings = [
        {"_index": INDEX_NAME, "_id": row["doc_id"], "rating": row["grade"]}
        for _, row in relevant_docs.iterrows()
    ]

    hybrid_requests.append({
        "id": query_id,
        "request": {
            "retriever": {
                "rrf": {
                    "retrievers": [
                        {
                            "standard": {
                                "query": {
                                    "multi_match": {
                                        "query": query_text,
                                        "fields": ["title", "description"],
                                    }
                                }
                            }
                        },
                        {
                            "standard": {
                                "query": {
                                    "match": {
                                        "semantic_field": {"query": query_text}
                                    }
                                }
                            }
                        },
                    ],
                    "rank_window_size": 50,
                    "rank_constant": 5,
                }
            }
        },
        "ratings": ratings,
    })

hybrid_eval = {
    "requests": hybrid_requests,
    "metric": {"recall": {"k": 10, "relevant_rating_threshold": 1}},
}

hybrid_result = es.rank_eval(index=INDEX_NAME, body=hybrid_eval)
print("Hybrid Recall@10:", hybrid_result.body["metric_score"])

Hybrid Recall@10: 0.75

methods = {
    "BM25 (Lexical)": bm25_requests,
    "Hybrid (BM25 + Vectors)": hybrid_requests,
}

recall_metric = {"recall": {"k": 10, "relevant_rating_threshold": 1}}

comparison_data = []
for method_name, requests in methods.items():
    result = es.rank_eval(
        index=INDEX_NAME,
        body={"requests": requests, "metric": recall_metric}
    )
    comparison_data.append({
        "method": method_name,
        "recall@10": result.body["metric_score"]
    })

comparison_df = pd.DataFrame(comparison_data)
print(comparison_df.to_string(index=False))