UPDATE

rag/retrieve.py

@@ -3,6 +3,7 @@
 """
 from .config import load_rag_config, RAGConfig, get_service_config
 from .embedding import embed_single, embed_texts
+from .observability import observe_operation, record_metric
 from .vector_store import QdrantVectorStore
 
 
@@ -63,15 +64,19 @@ def search_with_query(
         use_user_embeddings=use_user_embeddings,
     )
 
-    query_vector = embed_single(query, config=cfg)
-    store = QdrantVectorStore(config=cfg)
-    return store.search(
-        query_vector=query_vector,
-        limit=limit,
-        score_threshold=score_threshold,
-        sensor_uuids=sensor_filters,
-        kb_names=kb_filters,
-    )
+    with observe_operation(source="rag.retrieve", provider=cfg.embedding.provider, operation="search_with_query"):
+        query_vector = embed_single(query, config=cfg)
+        store = QdrantVectorStore(config=cfg)
+        results = store.search(
+            query_vector=query_vector,
+            limit=limit,
+            score_threshold=score_threshold,
+            sensor_uuids=sensor_filters,
+            kb_names=kb_filters,
+        )
+        if not results:
+            record_metric("rag.retrieve.empty_result", operation="search_with_query", service_id=service_id)
+        return results
 
 
 def search_with_texts(
@@ -102,24 +107,28 @@ def search_with_texts(
     )
 
     store = QdrantVectorStore(config=cfg)
-    vectors = embed_texts(normalized_texts, config=cfg)
-    merged_results: dict[str, dict] = {}
+    with observe_operation(source="rag.retrieve", provider=cfg.embedding.provider, operation="search_with_texts"):
+        vectors = embed_texts(normalized_texts, config=cfg)
+        merged_results: dict[str, dict] = {}
 
-    for vector in vectors:
-        results = store.search(
-            query_vector=vector,
-            limit=per_text_limit,
-            score_threshold=score_threshold,
-            sensor_uuids=sensor_filters,
-            kb_names=kb_filters,
-        )
-        for item in results:
-            current = merged_results.get(item["id"])
-            if current is None or item["score"] > current["score"]:
-                merged_results[item["id"]] = item
+        for vector in vectors:
+            results = store.search(
+                query_vector=vector,
+                limit=per_text_limit,
+                score_threshold=score_threshold,
+                sensor_uuids=sensor_filters,
+                kb_names=kb_filters,
+            )
+            for item in results:
+                current = merged_results.get(item["id"])
+                if current is None or item["score"] > current["score"]:
+                    merged_results[item["id"]] = item
 
-    return sorted(
-        merged_results.values(),
-        key=lambda item: item["score"],
-        reverse=True,
-    )[:limit]
+        final_results = sorted(
+            merged_results.values(),
+            key=lambda item: item["score"],
+            reverse=True,
+        )[:limit]
+        if not final_results:
+            record_metric("rag.retrieve.empty_result", operation="search_with_texts", service_id=service_id)
+        return final_results