mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-08 03:08:45 +00:00
vtx test fix gemini-2.5-flash-lite
This commit is contained in:
parent
65cf982d5b
commit
deb1dd93e2
1 changed files with 70 additions and 1 deletions
|
|
@ -504,6 +504,75 @@ async def test_async_vertexai_streaming_response():
|
|||
pytest.fail(f"An exception occurred: {e}")
|
||||
|
||||
|
||||
# asyncio.run(test_async_vertexai_streaming_response())
|
||||
|
||||
|
||||
@pytest.mark.parametrize("provider", ["vertex_ai"]) # "vertex_ai_beta"
|
||||
@pytest.mark.parametrize("sync_mode", [True, False])
|
||||
@pytest.mark.flaky(retries=3, delay=1)
|
||||
@pytest.mark.asyncio
|
||||
async def test_gemini_pro_vision(provider, sync_mode):
|
||||
try:
|
||||
load_vertex_ai_credentials()
|
||||
litellm.set_verbose = True
|
||||
litellm.num_retries = 3
|
||||
if sync_mode:
|
||||
resp = litellm.completion(
|
||||
model="{}/gemini-2.5-flash-lite".format(provider),
|
||||
messages=[
|
||||
{"role": "system", "content": "Be a good bot"},
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "text", "text": "Whats in this image?"},
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url": {
|
||||
"url": "gs://cloud-samples-data/generative-ai/image/boats.jpeg"
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
)
|
||||
else:
|
||||
resp = await litellm.acompletion(
|
||||
model="{}/gemini-2.5-flash-lite".format(provider),
|
||||
messages=[
|
||||
{"role": "system", "content": "Be a good bot"},
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "text", "text": "Whats in this image?"},
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url": {
|
||||
"url": "gs://cloud-samples-data/generative-ai/image/boats.jpeg"
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
)
|
||||
print(resp)
|
||||
|
||||
prompt_tokens = resp.usage.prompt_tokens
|
||||
|
||||
# DO Not DELETE this ASSERT
|
||||
# Google counts the prompt tokens for us, we should ensure we use the tokens from the orignal response
|
||||
assert prompt_tokens == 267 # the gemini api returns 267 to us
|
||||
|
||||
except litellm.RateLimitError as e:
|
||||
pass
|
||||
except Exception as e:
|
||||
if "500 Internal error encountered.'" in str(e):
|
||||
pass
|
||||
else:
|
||||
pytest.fail(f"An exception occurred - {str(e)}")
|
||||
|
||||
|
||||
# test_gemini_pro_vision()
|
||||
|
||||
|
||||
@pytest.mark.parametrize("load_pdf", [False]) # True,
|
||||
@pytest.mark.flaky(retries=3, delay=1)
|
||||
|
|
@ -536,7 +605,7 @@ def test_completion_function_plus_pdf(load_pdf):
|
|||
image_message = {"role": "user", "content": image_content}
|
||||
|
||||
response = completion(
|
||||
model="vertex_ai_beta/gemini-1.5-flash-preview-0514",
|
||||
model="vertex_ai_beta/gemini-2.5-flash-lite",
|
||||
messages=[image_message],
|
||||
stream=False,
|
||||
)
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue