add rate limiter for llama 3.1

langchain-ai · Jul 29, 2024 · 8e057fb · 8e057fb
1 parent f7d139f
commit 8e057fb
Showing 1 changed file with 6 additions and 2 deletions.
diff --git a/libs/partners/groq/tests/integration_tests/test_standard.py b/libs/partners/groq/tests/integration_tests/test_standard.py
@@ -4,12 +4,15 @@
 
 import pytest
 from langchain_core.language_models import BaseChatModel
-from langchain_standard_tests.integration_tests import (  # type: ignore[import-not-found]
-    ChatModelIntegrationTests,  # type: ignore[import-not-found]
+from langchain_core.rate_limiters import InMemoryRateLimiter
+from langchain_standard_tests.integration_tests import (
+    ChatModelIntegrationTests,
 )
 
 from langchain_groq import ChatGroq
 
+rate_limiter = InMemoryRateLimiter(requests_per_second=0.45)
+
 
 class BaseTestGroq(ChatModelIntegrationTests):
     @property
@@ -27,6 +30,7 @@ def chat_model_params(self) -> dict:
         return {
             "model": "llama-3.1-8b-instant",
             "temperature": 0,
+            "rate_limiter": rate_limiter,
         }
 
     @pytest.mark.xfail(