diff --git a/openai/cognee/cognee.env b/openai/cognee/cognee.env
index 44ebcf3..6b16b64 100644
--- a/openai/cognee/cognee.env
+++ b/openai/cognee/cognee.env
@@ -70,15 +70,23 @@ LLM_INSTRUCTOR_MODE=json_mode
 # own default is "http://localhost:11434/api/embed"), unlike the
 # openai_compatible engine which appends its own path onto a base URL. Ollama's
 # native /api/embed (batch endpoint, not the singular /api/embeddings) returns
-# {"embeddings": [[...]]}; the engine handles that key. Tested directly against
-# :11436 with model nomic-embed-text -> 768-dim vector, confirmed working
-# before wiring this in.
+# {"embeddings": [[...]]}; the engine handles that key.
+#
+# Swapped nomic-embed-text (768-d) -> bge-m3 (1024-d, multilingual, GPU-served)
+# 2026-07-06 [Adolf kb#60]. bge-m3 pulled into the same :11436 ollama; tested
+# directly against :11436 -> 1024-dim vector, confirmed working. cognee's
+# Qdrant collections were all still 768-d (a handful of P4 smoke-test points
+# only — "pineapple-7742"/"p4 deployment smoke test" fixtures, no real
+# conversation data; adolf-llm's cogneeSearch/cogneeAdd are still stubs and
+# have never actually written to cognee), so the stale 768-d collections were
+# dropped rather than migrated — cognee recreates them at the new dimension
+# on first write.
 ###############################################################################
 EMBEDDING_PROVIDER=ollama
-EMBEDDING_MODEL=nomic-embed-text
+EMBEDDING_MODEL=bge-m3
 EMBEDDING_ENDPOINT=http://host.docker.internal:11436/api/embed
-EMBEDDING_DIMENSIONS=768
-HUGGINGFACE_TOKENIZER=nomic-ai/nomic-embed-text-v1.5
+EMBEDDING_DIMENSIONS=1024
+HUGGINGFACE_TOKENIZER=BAAI/bge-m3
 
 ###############################################################################
 # Graph store — SPIKE-FINDINGS gate 4: Kuzu embedded, not Neo4j.