AI Building Blocks

Every AI feature in WSO2 Agent Builder, agents, direct LLM calls, and knowledge bases, is composed from the same small set of shared connections and stores. Configure one once, then reuse it wherever it's needed in your agentic integration.

Model Providers

Connect to the LLM behind every prompt: the Default WSO2 provider, models from WSO2 Agent Manager, OpenAI, Azure OpenAI, Anthropic, Amazon Bedrock, Google Vertex, Mistral, DeepSeek, Ollama, and OpenRouter.

Embedding Providers

Turn text into semantic vectors used on both ingest and query for similarity search.

Vector Stores

Persist embeddings and run similarity search across In-Memory, Pinecone, pgvector, Weaviate, or Milvus.

Chunkers

Split documents into chunks before embedding. Smaller chunks improve retrieval precision; larger chunks preserve more surrounding context.

Data Loaders

Read source documents, such as text files or a Microsoft SharePoint library, into ai:Document values ready for chunking and ingestion.

What's next

• How Knowledge Bases Work — Combine these building blocks into a knowledge base that grounds agent responses in your own documents
• AI Agents — Use a model provider to power an agent's reasoning