Why this change is needed: To support vector storage model isolation, we need to track which model is used for embeddings and generate unique identifiers for collections/tables. How it solves it: - Added model_name field to EmbeddingFunc - Added get_model_identifier() method to generate sanitized suffix - Added unit tests to verify behavior Impact: Enables subsequent changes in storage backends to isolate data by model. Testing: Added tests/test_embedding_func.py passing. |
||
|---|---|---|
| .. | ||
| conftest.py | ||
| README_WORKSPACE_ISOLATION_TESTS.md | ||
| test_aquery_data_endpoint.py | ||
| test_curl_aquery_data.sh | ||
| test_embedding_func.py | ||
| test_graph_storage.py | ||
| test_lightrag_ollama_chat.py | ||
| test_postgres_retry_integration.py | ||
| test_workspace_isolation.py | ||
| test_write_json_optimization.py | ||