fix async with threads

llm_config.py

@@ -0,0 +1,36 @@
+from google.genai import types
+
+# Vertex AI RAG Corpus resource path
+CORPUS: str = (
+    "projects/520464122471/locations/europe-west3/ragCorpora/2305843009213693952"
+)
+
+tools = [
+    types.Tool(
+        retrieval=types.Retrieval(
+            vertex_rag_store=types.VertexRagStore(
+                rag_resources=[types.VertexRagStoreRagResource(rag_corpus=CORPUS)],
+            )
+        )
+    )
+]
+
+generate_content_config = types.GenerateContentConfig(
+    temperature=1,
+    top_p=0.95,
+    max_output_tokens=65535,
+    safety_settings=[
+        types.SafetySetting(category="HARM_CATEGORY_HATE_SPEECH", threshold="OFF"),
+        types.SafetySetting(
+            category="HARM_CATEGORY_DANGEROUS_CONTENT", threshold="OFF"
+        ),
+        types.SafetySetting(
+            category="HARM_CATEGORY_SEXUALLY_EXPLICIT", threshold="OFF"
+        ),
+        types.SafetySetting(category="HARM_CATEGORY_HARASSMENT", threshold="OFF"),
+    ],
+    tools=tools,
+    thinking_config=types.ThinkingConfig(
+        thinking_level="HIGH",
+    ),
+)