OceanBase VectorとOllamaの連携

obclient -h$host -P$port -u$user_name -p$password -D$database_name

export OCEANBASE_DATABASE_URL=YOUR_OCEANBASE_DATABASE_URL
export OCEANBASE_DATABASE_USER=YOUR_OCEANBASE_DATABASE_USER
export OCEANBASE_DATABASE_DB_NAME=YOUR_OCEANBASE_DATABASE_DB_NAME
export OCEANBASE_DATABASE_PASSWORD=YOUR_OCEANBASE_DATABASE_PASSWORD

curl -fsSL https://ollama.ai/install.sh | sh
export PATH="/usr/local/bin:$PATH"
ollama --version
ollama pull qwen3-embedding:latest

import requests,os,json,ollama
from tqdm import tqdm

from sqlalchemy import Column, Integer, String
from pyobvector import ObVecClient, VECTOR, IndexParam, l2_distance

# text URL
url = "https://raw.githubusercontent.com/oceanbase/oceanbase-doc/refs/heads/V4.3.5/en-US/640.ob-vector-search/800.ob-vector-search-faq.md"
response = requests.get(url)
text_lines = []
file_text = response.text
text_lines += file_text.split("# ")

def emb_text(text):
    response = ollama.embeddings(model="qwen3-embedding", prompt=text)
    return response["embedding"]

data = []
for i, line in enumerate(tqdm(text_lines, desc="Creating embeddings")):
    data.append({"text": line, "embedding": emb_text(line)})

OCEANBASE_DATABASE_URL = os.getenv('OCEANBASE_DATABASE_URL')
OCEANBASE_DATABASE_USER = os.getenv('OCEANBASE_DATABASE_USER')
OCEANBASE_DATABASE_DB_NAME = os.getenv('OCEANBASE_DATABASE_DB_NAME')
OCEANBASE_DATABASE_PASSWORD = os.getenv('OCEANBASE_DATABASE_PASSWORD')

client = ObVecClient(uri=OCEANBASE_DATABASE_URL, user=OCEANBASE_DATABASE_USER,password=OCEANBASE_DATABASE_PASSWORD,db_name=OCEANBASE_DATABASE_DB_NAME)
table_name = "ollama_oceanbase_demo_documents"
client.drop_table_if_exist(table_name)

cols = [
    Column("id", Integer, primary_key=True, autoincrement=True),
    Column("text", String(255), nullable=False),
    Column("embedding", VECTOR(4096))
]

# Create vector index
vector_index_params = IndexParam(
    index_name="idx_question_embedding",
    field_name="embedding",
    index_type="HNSW",
    distance_metric="l2"
)

client.create_table_with_index_params(
    table_name=table_name,
    columns=cols,
    vidxs=[vector_index_params]
)

print('- Inserting Data to OceanBase...')
client.insert(table_name, data=data)

question = "Which mode supports vector search?"
search_res = client.ann_search(
    table_name,
    vec_data=emb_text(question),
    vec_column_name="embedding",
    distance_func=l2_distance,
    with_dist=True,
    topk=1,
    output_column_names=["id","text"],
)

print('- The Most Relevant Document and Its Distance to the Query:')
for row in search_res.fetchall():
    print(f'  - ID: {row[0]}\n'
          f'    content: {row[1]}\n'
          f'    distance: {row[2]}')

- ID: 3
  content: Which mode supports vector search?

  Vector search is supported only in the MySQL mode of OceanBase Database.

  distance: 0.509979758468682