Fix Pydantic TextNode validation error - convert numpy.float32 to Python float

The similarity score was being set as a numpy.float32 from SQLite distance calculations.
Pydantic expects Python native float types for the score field, causing validation errors
when querying MCPs or using chat features.

Fix: Convert similarity score to Python float using float() conversion.

🤖 Generated with Claude Code

Co-Authored-By: Claude <noreply@anthropic.com>

app/core/rag_engine.py

@@ -56,7 +56,7 @@ class SimpleVectorRetriever:
                 results["distances"][0]
             ):
                 # Convert distance back to similarity score (1 - distance)
-                similarity = 1 - distance
+                similarity = float(1 - distance)  # Convert numpy float to Python float
 
                 node = TextNode(
                     text=content,