Integrate Tablestore with popular AI frameworks, platforms, and applications to power high-performance data storage and retrieval for AI development.
Agent Open Source Components
Tablestore for Agent Memory
The Agent Memory SDK is a framework built on Tablestore that provides general-purpose memory storage and query capabilities for AI agent scenarios. It supports two primary scenarios: real-time memory storage and long-term semantic retrieval of knowledge.
MCP Protocol Integration
The Model Context Protocol (MCP) is a standard protocol for managing the context of AI applications. Tablestore provides several MCP service implementations to support various application scenarios.
Tablestore MCP Server
The following are the general-purpose Tablestore MCP service implementations:
-
Documentation: Tablestore MCP Server
-
Function AI plugin for Function Compute: Tablestore MCP Server plugin
Tablestore OpenMemory MCP
This cross-platform AI memory service is based on Mem0 and enables intelligent memory sharing and reuse across multiple applications through unified memory storage:
-
Function AI plugin for Function Compute: Tablestore OpenMemory MCP plugin
AI Framework Integration
LlamaIndex
LlamaIndex is a popular framework for developing Large Language Model (LLM) applications. Tablestore fully supports its core storage components:
-
VectorStore: Stores high-dimensional vectors and supports similarity retrieval.
-
DocumentStore: Stores and manages original document content.
-
IndexStore: Manages and maintains various index metadata.
-
ChatStore: Saves and retrieves chat history.
-
KvStore: Provides general-purpose key-value storage.
LangChain
LangChain is a popular AI application development framework. Tablestore supports the following component:
-
VectorStore: Stores vector embeddings and supports retrieval.
LangChain4j
LangChain4j is the Java implementation of LangChain. Tablestore supports the following components:
-
EmbeddingStore: Manages embeddings that are generated from text vectorization.
-
MemStore: Used for chat history and context management.
LangEngine
LangEngine is an AI application development framework developed by Alibaba. Tablestore supports the following component:
-
VectorStore: Provides vector embedding storage and retrieval capabilities.
AgentScope Runtime
AgentScope is an open source multi-agent platform from Alibaba, and Tablestore supports it.
-
TablestoreRAGService: A retrieval-augmented generation (RAG) service that provides document retrieval and knowledge base query capabilities.
-
TablestoreMemoryService: An agent memory service that manages the long-term and short-term memory of agents.
For more information about the integration, see Integrate Tablestore with AgentScope Runtime.
AI Application Platform Integration
Dify
Dify is an open source platform for developing LLM applications, and Tablestore has been integrated.
-
VectorStore: Provides vector retrieval capabilities for RAG applications.
Related documentation:
PAI-RAG
PAI-RAG is a RAG application framework provided by Platform for AI (PAI) from Alibaba Cloud. Tablestore provides the following integration:
-
VectorStore: Provides high-performance vector retrieval services.
Related documentation:
Stable Diffusion
Stable Diffusion is a popular AI image generation model. It supports scenarios such as text-to-image and image-to-image generation. Tablestore provides the following integration support:
-
Image Management Extension: Manages and organizes generated image resources. This extension is integrated with applications on Alibaba Cloud Function Compute (FC).