Fix: set cosine distance metadata on all collection creation sites

ChromaDB defaults HNSW index to L2 (Euclidean) distance, but
MemPalace scoring uses 1-distance which requires cosine (range 0-2).
Add metadata={"hnsw:space": "cosine"} to the 4 production and 3 test
call sites that were missing it.

Closes #218
This commit is contained in:
eblander
2026-04-13 11:00:52 -04:00
parent 6614b9b4e7
commit 1e86892e62
7 changed files with 224 additions and 66 deletions
+6 -2
View File
@@ -101,7 +101,9 @@ def config(tmp_dir, palace_path):
def collection(palace_path):
"""A ChromaDB collection pre-seeded in the temp palace."""
client = chromadb.PersistentClient(path=palace_path)
col = client.get_or_create_collection("mempalace_drawers")
col = client.get_or_create_collection(
"mempalace_drawers", metadata={"hnsw:space": "cosine"}
)
yield col
client.delete_collection("mempalace_drawers")
del client
@@ -185,7 +187,9 @@ def seeded_kg(kg):
kg.add_triple("Alice", "parent_of", "Max", valid_from="2015-04-01")
kg.add_triple("Max", "does", "swimming", valid_from="2025-01-01")
kg.add_triple("Max", "does", "chess", valid_from="2024-06-01")
kg.add_triple("Alice", "works_at", "Acme Corp", valid_from="2020-01-01", valid_to="2024-12-31")
kg.add_triple(
"Alice", "works_at", "Acme Corp", valid_from="2020-01-01", valid_to="2024-12-31"
)
kg.add_triple("Alice", "works_at", "NewCo", valid_from="2025-01-01")
return kg