### 検索クエリの埋め込みを生成する
[Sentence Transformers](https://www.sbert.net/) は、文や段落のセマンティックな意味を捉えるための、ローカルで手軽に使える埋め込みモデルを提供します。
このHackerNewsデータセットには、[all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)モデルによって生成されたベクトル埋め込みが含まれています。
以下に、`sentence_transformers` Pythonパッケージを使用して埋め込みベクトルをプログラム的に生成する方法を示すPythonスクリプトの例を示します。検索用の埋め込みベクトルは、`SELECT` クエリ内の [`cosineDistance()`](/ja/reference/functions/regular-functions/distance-functions#cosineDistance) 関数に引数として渡されます。
```python theme={null}
from sentence_transformers import SentenceTransformer
import sys
import clickhouse_connect
print("Initializing...")
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
chclient = clickhouse_connect.get_client() # ClickHouse credentials here
while True:
# ユーザーから検索クエリを受け取る
print("Enter a search query :")
input_query = sys.stdin.readline();
texts = [input_query]
# モデルを実行して検索ベクトルを取得する
print("Generating the embedding for ", input_query);
embeddings = model.encode(texts)
print("Querying ClickHouse...")
params = {'v1':list(embeddings[0]), 'v2':20}
result = chclient.query("SELECT id, title, text FROM hackernews ORDER BY cosineDistance(vector, %(v1)s) LIMIT %(v2)s", parameters=params)
print("Results :")
for row in result.result_rows:
print(row[0], row[2][:100])
print("---------")
```
上記の Python スクリプトの実行例と類似検索の結果を以下に示します
(上位20件の投稿はそれぞれ先頭100文字のみを表示しています) ：
```text theme={null}
初期化中...
検索クエリを入力してください：
Are OLAP cubes useful
「Are OLAP cubes useful」の埋め込みを生成中
ClickHouseにクエリ中...
結果：
27742647 smartmic:
slt2021: OLAP Cube is not dead, as long as you use some form of:1. GROUP BY multiple fi
---------
27744260 georgewfraser:A data mart is a logical organization of data to help humans understand the schema. Wh
---------
27761434 mwexler:"We model data according to rigorous frameworks like Kimball or Inmon because we must r
---------
28401230 chotmat:
erosenbe0: OLAP database is just a copy, replica, or archive of data with a schema designe
---------
22198879 Merick:+1 for Apache Kylin, it's a great project and awesome open source community. If anyone i
---------
27741776 crazydoggers:I always felt the value of an OLAP cube was uncovering questions you may not know to as
---------
22189480 shadowsun7:
_Codemonkeyism: After maintaining an OLAP cube system for some years, I'm not that
---------
27742029 smartmic:
gengstrand: My first exposure to OLAP was on a team developing a front end to Essbase that
---------
22364133 irfansharif:
simo7: I'm wondering how this technology could work for OLAP cubes.
An OLAP cube
---------
23292746 scoresmoke:When I was developing my pet project for Web analytics ( int:
encoding = tiktoken.encoding_for_model(encoding_name)
num_tokens = len(encoding.encode(string))
return num_tokens
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
chclient = clickhouse_connect.get_client(compress=False) # ここに ClickHouse の認証情報を設定
while True:
# ユーザーから検索クエリを取得する
print("Enter a search topic :")
input_query = sys.stdin.readline();
texts = [input_query]
# モデルを実行して、検索ベクトルまたは参照ベクトルを取得する
print("Generating the embedding for ----> ", input_query);
embeddings = model.encode(texts)
print("Querying ClickHouse...")
params = {'v1':list(embeddings[0]), 'v2':100}
result = chclient.query("SELECT id,title,text FROM hackernews ORDER BY cosineDistance(vector, %(v1)s) LIMIT %(v2)s", parameters=params)
# 検索結果をすべて連結する
doc_results = ""
for row in result.result_rows:
doc_results = doc_results + "\n" + row[2]
print("Initializing chatgpt-3.5-turbo model")
model_name = "gpt-3.5-turbo"
text_splitter = CharacterTextSplitter.from_tiktoken_encoder(
model_name=model_name
)
texts = text_splitter.split_text(doc_results)
docs = [Document(page_content=t) for t in texts]
llm = ChatOpenAI(temperature=0, model_name=model_name)
prompt_template = """
Write a concise summary of the following in not more than 10 sentences:
{text}
CONSCISE SUMMARY :
"""
prompt = PromptTemplate(template=prompt_template, input_variables=["text"])
num_tokens = num_tokens_from_string(doc_results, model_name)
gpt_35_turbo_max_tokens = 4096
verbose = False
print("Summarizing search results retrieved from ClickHouse...")
if num_tokens <= gpt_35_turbo_max_tokens:
chain = load_summarize_chain(llm, chain_type="stuff", prompt=prompt, verbose=verbose)
else:
chain = load_summarize_chain(llm, chain_type="map_reduce", map_prompt=prompt, combine_prompt=prompt, verbose=verbose)
summary = chain.run(docs)
print(f"Summary from chatgpt-3.5: {summary}")
```