​
Introduction

Memory can be configured at different levels. Here are examples of each:

# Workflow level memory configuration
memory:
  id: global_memory
  vector:
    use: compozy/vector:pg-vector
    config:
      url: "{{ env.POSTGRES_URL }}"

# Using workflow level memory
workflows:
  memory: global_memory
  tasks:
    - id: analyze_request
      use: compozy/tasks:analyze-request

Memory can be accessed through {{ memory.<id>.current_thread }}, {{ memory.<id>.last_messages }}, or {{ memory.<id>.semantic_search }}, allowing contextual responses based on past interactions.

​
Core Features

Vector Databases

Choose from various vector storage solutions to match your needs.

Vector Search

Semantic search capabilities through vector embeddings.

Embeddings

Flexible embedding options for semantic search.

Memory Types

Different memory structures for various use cases.

​
Key Points

Multiple Storage Options

Support for various vector databases including PgVector, Pinecone, Qdrant, and more.

Semantic Search

Vector search capabilities for intelligent context retrieval.

Working Memory

Structured persistent memory for maintaining user context.

Conversation History

Efficient storage and retrieval of interaction history.

​
Next Steps