[geaflow/ai-memory] Add `EntityVectorIndex` wrapper around graph entity embeddings

Priority: P0
Difficulty: Intermediate

Context: Graph entity embedding exists, but Phase 1 needs explicit entity-vector semantics for fuzzy entity anchoring.

Scope:

- Wrap current `EmbeddingIndexStore` behavior behind `EntityVectorIndex`.
- Add entity ID, entity type, model metadata, and vector version.
- Add compatibility tests with existing `EmbeddingOperator`.

Constraints:

- Do not change retrieval ranking yet.
- Link existing embedding correctness fix issue/PR where applicable.

Acceptance Criteria:

- Entity vector lookup can distinguish vertex and edge entities.
- Dimension/model mismatch is detected before search.

Suggested paths:

- `geaflow-ai/src/main/java/org/apache/geaflow/ai/index/entity`

Start in geaflow-ai/src/main/java/org/apache/geaflow/ai/index/entity and trace the current EmbeddingIndexStore behavior and EmbeddingOperator compatibility points. Define the wrapper's entity ID, entity type, model metadata, and vector version based on the existing interfaces. Add compatibility tests showing vertex and edge lookup separation and dimension/model mismatch detection before search, without changing retrieval ranking.

Written by the indexing model from the issue text.