OceanBase AI 数据库 seekdb 正式发布！到底有多强？

-- 注册重排序模型和端点
CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_rerank');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_rerank_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_rerank', '{
    "type": "rerank",
    "model_name": "BAAI/bge-reranker-v2-m3"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_rerank_endpoint', '{
    "ai_model_name": "ob_rerank",
    "url": "https://api.siliconflow.cn/v1/rerank",
    -- 需替换为实际的 access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "siliconflow"
}');

-- 尝试重排序
SELECT AI_RERANK("ob_rerank", "Apple", '["apple", "banana", "fruit", "vegetable"]');

-- 返回结果
+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| AI_RERANK("ob_rerank", "Apple", '["apple", "banana", "fruit", "vegetable"]')                                                                                                                                                   |
+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| [{"index": 0, "relevance_score": 0.9911285638809204}, {"index": 1, "relevance_score": 0.0030552432872354984}, {"index": 2, "relevance_score": 0.0003349370090290904}, {"index": 3, "relevance_score": 0.00001892922773549799}] |
+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
1 row in set

# 使用 pip 安装，会自动识别默认的 Python 版本和平台
pip install pyseekdb

# 如果您的 pip 版本比较低，请先升级 pip 后再安装
pip install --upgrade pip

# 通过 Python SDK 体验 seekdb（Embedding Functions 示例）

import pyseekdb

# ==================== Step 1: Create Client Connection ====================
# You can use embedded mode, server mode, or OceanBase mode
# For this example, we'll use server mode (you can change to embedded or OceanBase)

# Embedded mode (local SeekDB)
client = pyseekdb.Client()
# Alternative: Server mode (connecting to remote SeekDB server)
# client = pyseekdb.Client(
#     host="127.0.0.1",
#     port=2881,
#     database="test",
#     user="root",
#     password=""
# )

# Alternative: Remote server mode (OceanBase Server)
# client = pyseekdb.Client(
#     host="127.0.0.1",
#     port=2881,
#     tenant="test",  # OceanBase default tenant
#     database="test",
#     user="root",
#     password=""
# )

# ==================== Step 2: Create a Collection with Embedding Function ====================
# A collection is like a table that stores documents with vector embeddings
collection_name = "my_simple_collection"

# Create collection with default embedding function
# The embedding function will automatically convert documents to embeddings
collection = client.create_collection(
    name=collection_name,
)

print(f"Created collection '{collection_name}' with dimension: {collection.dimension}")
print(f"Embedding function: {collection.embedding_function}")

# ==================== Step 3: Add Data to Collection ====================
# With embedding function, you can add documents directly without providing embeddings
# The embedding function will automatically generate embeddings from documents

documents = [
    "Machine learning is a subset of artificial intelligence",
    "Python is a popular programming language",
    "Vector databases enable semantic search",
    "Neural networks are inspired by the human brain",
    "Natural language processing helps computers understand text"
]

ids = ["id1", "id2", "id3", "id4", "id5"]

# Add data with documents only - embeddings will be auto-generated by embedding function
collection.add(
    ids=ids,
    documents=documents,  # embeddings will be automatically generated
    metadatas=[
        {"category": "AI", "index": 0},
        {"category": "Programming", "index": 1},
        {"category": "Database", "index": 2},
        {"category": "AI", "index": 3},
        {"category": "NLP", "index": 4}
    ]
)

print(f"\nAdded {len(documents)} documents to collection")
print("Note: Embeddings were automatically generated from documents using the embedding function")

# ==================== Step 4: Query the Collection ====================
# With embedding function, you can query using text directly
# The embedding function will automatically convert query text to query vector

# Query using text - query vector will be auto-generated by embedding function
query_text = "artificial intelligence and machine learning"

results = collection.query(
    query_texts=query_text,  # Query text - will be embedded automatically
    n_results=3# Return top 3 most similar documents
)

print(f"\nQuery: '{query_text}'")
print(f"Query results: {len(results['ids'][0])} items found")

# ==================== Step 5: Print Query Results ====================
for i in range(len(results['ids'][0])):
    print(f"\nResult {i+1}:")
    print(f"  ID: {results['ids'][0][i]}")
    print(f"  Distance: {results['distances'][0][i]:.4f}")
    if results.get('documents'):
        print(f"  Document: {results['documents'][0][i]}")
    if results.get('metadatas'):
        print(f"  Metadata: {results['metadatas'][0][i]}")

# ==================== Step 6: Cleanup ====================
# Delete the collection
client.delete_collection(collection_name)
print(f"\nDeleted collection '{collection_name}'")