Simplify your development process by leveraging TiDB's seamless integrations with leading AI vendors and frameworks
Leverage your existing MySQL expertise to seamlessly integrate advanced vector search
Simplify your tech stack with a single, scalable database for both traditional and AI workloads
Leverage your existing MySQL expertise to seamlessly integrate advanced vector search
engine = create_engine(your_tidb_url)
class Entity(Base):
__tablename__ = "entity"
id = Column(Integer, primary_key=True)
content = Column(Text)
content_vec = Column(
VectorType(dim=dim_of_embedding_model),
comment="hnsw(distance=l2)"
)
Base.metadata.create_all(engine)
content = 'TiDB is an open-source distributed SQL database'
open_ai_client = openai.OpenAI(api_key=open_ai_api_key)
embedding = open_ai_client.embeddings.create(
input=[content], model=model_name).data[0].embedding
with Session(engine) as session:
session.add(Entity(content = content, content_vec = embedding))
session.commit()
query = 'What is TiDB?'
embedding_query = open_ai_client.embeddings.create(
input=[query], model=model_name).data[0].embedding
with Session(engine) as session:
entity = session.query(Entity).order_by(
Entity.content_vec.cosine_distance(embedding_query)
).limit(1).first()
print(entity.content)
engine = create_engine(your_tidb_url)
class Entity(Base):
__tablename__ = "entity"
id = Column(Integer, primary_key=True)
content = Column(Text)
content_vec = Column(
VectorType(dim=dim_of_embedding_model),
comment="hnsw(distance=l2)"
)
Base.metadata.create_all(engine)
content = 'TiDB is an open-source distributed SQL database'
open_ai_client = openai.OpenAI(api_key=open_ai_api_key)
embedding = open_ai_client.embeddings.create(
input=[content], model=model_name).data[0].embedding
with Session(engine) as session:
session.add(Entity(content = content, content_vec = embedding))
session.commit()
query = 'What is TiDB?'
embedding_query = open_ai_client.embeddings.create(
input=[query], model=model_name).data[0].embedding
with Session(engine) as session:
entity = session.query(Entity).order_by(
Entity.content_vec.cosine_distance(embedding_query)
).limit(1).first()
print(entity.content)
Understand user preferences and similarities between products to deliver accurate recommendations
Handle numerous concurrent customer interactions using vector search to provide quick and accurate responses
Implement robust image and video analysis for content moderation
Perform sentiment analysis, language translation, and text summarization for more accurate processing
Analyze user behavior and preferences to serve the most relevant ads
