test(test_amazing_vertex_completion.py): handle rate limit errors

This commit is contained in:
Krrish Dholakia
2024-02-16 11:54:12 -08:00
committed by ishaan-jaff
parent 01077b20b9
commit 0d54887149
2 changed files with 4 additions and 2 deletions
@@ -964,14 +964,14 @@
"mode": "completion"
},
"dolphin": {
"max_tokens": 4096,
"max_tokens": 16384,
"input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.0000005,
"litellm_provider": "nlp_cloud",
"mode": "completion"
},
"chatdolphin": {
"max_tokens": 4096,
"max_tokens": 16384,
"input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.0000005,
"litellm_provider": "nlp_cloud",
@@ -266,6 +266,8 @@ async def test_async_vertexai_streaming_response():
complete_response += chunk.choices[0].delta.content
print(f"complete_response: {complete_response}")
assert len(complete_response) > 0
except litellm.RateLimitError as e:
pass
except litellm.Timeout as e:
pass
except Exception as e: