OB Cloud VectorとFirecrawlの連携

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 FIRECRAWL_API_KEY=YOUR_FIRECRAWL_API_KEY
export JINAAI_API_KEY=YOUR_JINAAI_API_KEY

import os ,requests
from firecrawl import FirecrawlApp
from sqlalchemy import Column, Integer, String
from pyobvector import ObVecClient, VECTOR, IndexParam, cosine_distance
from tqdm import tqdm

def split_markdown_content(content):
    return [section.strip() for section in content.split("# ") if section.strip()]

app = FirecrawlApp(api_key=os.environ["FIRECRAWL_API_KEY"])

# Scrape a website:
scrape_status = app.scrape(
url="https://en.oceanbase.com/docs/common-oceanbase-database-10000000001970957",
formats=["markdown"]
)

markdown_content = scrape_status.markdown

# Process the scraped markdown content
sections = split_markdown_content(markdown_content)

JINAAI_API_KEY = os.getenv('JINAAI_API_KEY')

def generate_embeddings(text: str):
    JINAAI_API_URL = 'https://api.jina.ai/v1/embeddings'
    JINAAI_HEADERS = {
        'Content-Type': 'application/json',
        'Authorization': f'Bearer {JINAAI_API_KEY}'
    }
    JINAAI_REQUEST_DATA = {
        'input': [text],
        'model': 'jina-embeddings-v3'  # with dimension 1024.
    }
    response = requests.post(JINAAI_API_URL, headers=JINAAI_HEADERS, json=JINAAI_REQUEST_DATA)
    return response.json()['data'][0]['embedding']

data = []

for i, section in enumerate(tqdm(sections, desc="Processing sections")):
    try:
        embedding = generate_embeddings(section)
        truncated_content = section[:4900] if len(section) > 4900 else section
        data.append({"content": truncated_content, "content_vec": embedding})
    except Exception as e:
        print(f"Error processing section {i}: {e}")
        continue

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 = "firecrawl_oceanbase_demo_documents"
client.drop_table_if_exist(table_name)

cols = [
    Column("id", Integer, primary_key=True, autoincrement=True),
    Column("content", String(5000), nullable=False),
    Column("content_vec", VECTOR(1024))
]

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

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)

query = 'what is OceanBase High compatibility'
# Generate the embedding for the query via Jina AI API.
query_embedding = generate_embeddings(query)

res = client.ann_search(
    table_name,
    vec_data=query_embedding,
    vec_column_name="content_vec",
    distance_func=cosine_distance,  # コサイン距離関数を使用
    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: 5
  content: High compatibility

OceanBase Database is highly compatible with most general features of Oracle and MySQL, and supports advanced features such as procedural language and triggers. OceanBase Migration Service (OMS), an automatic migration tool, is provided to support migration assessment and reverse synchronization to ensure data migration security when a core system is migrated to OceanBase Database in key industries such as finance, public governance, and communication service.

##
  distance: 0.2341035693195166