Stop Stitching, Start Building: Get Started with OceanBase seekdb

pip install -U pyseekdb

import pyseekdb# ==================== Step 1: Create Client Connection ====================# Start in embedded mode (local SeekDB)client = pyseekdb.Client()# ==================== Step 2: Create a Collection with Embedding Function ====================# A collection is like a table that stores documents with vector embeddingscollection_name = "my_simple_collection"# Create collection with default embedding function# The embedding function will automatically convert documents to embeddingscollection = 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 documentsdocuments = [    "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 functioncollection.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 ====================# The embedding function will automatically convert query text to query vector# Query using text - query vector will be auto-generated by embedding functionquery_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 collectionclient.delete_collection(collection_name)print(f"\nDeleted collection '{collection_name}'")

>>> Creating collection: my_simple_collection    - Dimension: 384    - Embedding function: DefaultEmbeddingFunction(model_name='all-MiniLM-L6-v2')>>> Ingesting data (Auto-Embedding)...    - Added 5 documents in 5.31s>>> Querying for: 'artificial intelligence and machine learning'    - Found 3 matches.Result 1:  ID: id1  Distance: 0.3008  Document: Machine learning is a subset of artificial intelligence  Metadata: {'index': 0, 'category': 'AI'}Result 2:  ID: id4  Distance: 0.5983  Document: Neural networks are inspired by the human brain  Metadata: {'index': 3, 'category': 'AI'}

import pyseekdbfrom pprint import pprintimport timeprint(">>> Initializing SeekDB Client...")# Initialize Embedded Engineclient = pyseekdb.Client()collection_name = "quickstart_demo"# Idempotency: Clean up previous runtry:    client.delete_collection(collection_name)except:    passprint(f">>> Creating collection '{collection_name}'...")collection = client.create_collection(name=collection_name)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",]print(">>> Indexing documents...")# The engine performs Vectorization + Inverted Index building herecollection.add(    ids=["id1", "id2", "id3", "id4", "id5"],    documents=documents,    metadatas=[        {"tag": "ai"}, {"tag": "code"}, {"tag": "db"}, {"tag": "ai"}, {"tag": "ai"},    ],)print(f"    - Indexed {len(documents)} documents.")# ---------------------------------------------------------# Hybrid Search: Vector('AI') + Keyword('learning') + RRF# ---------------------------------------------------------print("\n>>> Executing Hybrid Search...")print("    Criteria: Near 'artificial intelligence' (Vector) AND contains 'learning' (Text)")try:    hybrid_results = collection.hybrid_search(        query={            # Full text condition (lexical match)            # Note: The backslash before $ is for shell escaping; Python sees "\$contains"            "where_document": {"\$contains": "learning"},            "n_results": 5,        },        knn={            # Semantic condition (vector match)            "query_texts": ["artificial intelligence"],            "n_results": 5,        },        # Reciprocal Rank Fusion (RRF)        rank={"rrf": {}},        n_results=3,        include=["documents", "metadatas"],    )    print("\n--- RRF Re-ranked Results ---")    pprint(hybrid_results)except AttributeError:    print("\n[NOTE] Feature unavailable. Your current pyseekdb version or embedded binary")    print("       may not support 'hybrid_search'. This is a standard feature in OceanBase Server.")except Exception as e:    print(f"\n[ERROR] Hybrid search failed: {e}")# Cleanupclient.delete_collection(collection_name)print(f"\n>>> Cleanup complete.")EOF

...- Indexed 5 documents.>>> Executing Hybrid Search...    Criteria: Near 'artificial intelligence' (Vector) AND contains 'learning' (Text)--- RRF Re-ranked Results ---{'distances': [[Decimal('0.0328'), Decimal('0.0161'), Decimal('0.0159')]], 'documents': [['Machine learning is a subset of artificial intelligence',                'Natural language processing helps computers understand text',                'Neural networks are inspired by the human brain']], 'ids': [['id1', 'id5', 'id4']], 'metadatas': [[{'tag': 'ai'}, {'tag': 'ai'}, {'tag': 'ai'}]]}

Prototype: client = pyseekdb.Client()Production: client = pyseekdb.Client(host="...", port=2881)