OceanBase Vector 与 Cloudflare Workers AI 集成

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
export CLOUDFLARE_API_KEY=YOUR_CLOUDFLARE_API_KEY

import requests,os,httpx
from sqlalchemy import Column, Integer, String
from pyobvector import ObVecClient, VECTOR, IndexParam, cosine_distance

documents = [
    "Machine learning is the core technology of artificial intelligence",
    "Python is the preferred programming language for data science",
    "Cloud computing provides elastic and scalable computing resources",
    "Blockchain technology ensures data security and transparency", 
    "Natural language processing helps computers understand human language"
]


BASE_URL = "https://api.cloudflare.com/client/v4/accounts"
model_name = "@cf/baai/bge-base-en-v1.5"
account_id="0f390650bbe6ff23336badcf24e85c93"
CLOUDFLARE_API_KEY = os.getenv('CLOUDFLARE_API_KEY')

api_url = f"{BASE_URL}/{account_id}/ai/run/{model_name}"

# 创建HTTP客户端
httpclient = httpx.Client()
httpclient.headers.update({
    "Authorization": f"Bearer {CLOUDFLARE_API_KEY}", 
    "Accept-Encoding": "identity"
})


payload = {"text": documents}
response = httpclient.post(api_url, json=payload)
embedding_response = response.json()["result"]["data"]

data = []
for i, text in enumerate(documents):
    data.append({
        'content': text,
        'content_vec': embedding_response[i]  # 转换为列表格式
    })

print(f"Successfully processed {len(data)} texts")

#Connect OceanBase Serverless
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')

ob_client = ObVecClient(uri=OCEANBASE_DATABASE_URL, user=OCEANBASE_DATABASE_USER,password=OCEANBASE_DATABASE_PASSWORD,db_name=OCEANBASE_DATABASE_DB_NAME)


#Create the vector table.
table_name = "cloudflare_oceanbase_demo_documents"
ob_client.drop_table_if_exist(table_name)

cols = [
    Column("id", Integer, primary_key=True, autoincrement=True),
    Column("content", String(500), nullable=False),
    Column("content_vec", VECTOR(768))
]

# Create vector index
vector_index_params = IndexParam(
    index_name="idx_content_vec",
    field_name="content_vec",  
    index_type="HNSW",
    distance_metric="cosine"
)

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

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

#  Query the most relevant document based on the query.
query = "Programming languages for data analysis"
# Generate the embedding for the query via Jina AI API.
payload = {"text": query}
response = httpclient.post(api_url, json=payload)
query_embedding = response.json()["result"]["data"]

res = ob_client.ann_search(
    table_name,
    vec_data=query_embedding[0],
    vec_column_name="content_vec",
    distance_func=cosine_distance,  
    with_dist=True,
    topk=1,
    output_column_names=["id", "content"],
)

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

  - ID: 2
    content: Python is the preferred programming language for data science
    distance: 0.139745337621493