Capability Module | Core Feature | Typical Scenario |
Large Model Invocation | Directly invoke large language models in SQL via the tencentdb_ai plugin. | Text Classification, Sentiment Analysis, Intelligent Summarization |
Vector Search | Based on pgvector (HNSW/IVFFlat) and pgvectorscale (DiskANN) | RAG search, semantic search, image search |
Graph Database | Attribute graph storage and Cypher query based on Apache AGE | Knowledge Graph, GraphRAG, Relationship Reasoning |
Agent Memory | Long-term memory storage for multiple agents, integrating vector + graph + relational data in a unified architecture | Long-term memory for AI agents, multi-agent collaboration |
REST API | HTTP interface based on PostgREST | Frontend-backend separation, Serverless applications |
Capability Module | Core Feature | Typical Scenario |
Intelligent Index Recommendation | tencentdb_index_advisor automatically analyzes workloads and recommends optimal indexes. | Performance tuning, new service launch assessment |
AI Slow SQL Diagnosis | Automatically diagnoses slow queries and provides optimization suggestions by leveraging AI large models. | Routine Ops, performance troubleshooting |
Was this page helpful?
You can also Contact sales or Submit a Ticket for help.
Help us improve! Rate your documentation experience in 5 mins.
Feedback