Expose model and task_type as public properties in VertexAIEmbedder

[Copilot]

The VertexAIEmbedder class stored model and task_type as private attributes (_model, _task_type) but the example code attempted to access them as public properties, causing AttributeError.

Changes

• Added model property to return the Vertex AI model name
• Added task_type property to return the embedding task type
• Updated class docstring to document the new public attributes
• Added unit tests for both properties

Example

from neo4j_agent_memory.embeddings.vertex_ai import VertexAIEmbedder

embedder = VertexAIEmbedder(
    model="text-embedding-004",
    task_type="RETRIEVAL_DOCUMENT"
)

print(f"Model: {embedder.model}")           # Now works
print(f"Task Type: {embedder.task_type}")   # Now works

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
agent-memory	Ready	Preview, Comment	Feb 5, 2026 2:39pm