File size: 7,291 Bytes
395201c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 |
import sys, os
import traceback
import pytest
from dotenv import load_dotenv
import openai
load_dotenv()
sys.path.insert(
0, os.path.abspath("../..")
) # Adds the parent directory to the system path
import litellm
from litellm import embedding, completion
litellm.set_verbose = False
def test_openai_embedding():
try:
litellm.set_verbose=True
response = embedding(
model="text-embedding-ada-002",
input=["good morning from litellm", "this is another item"],
metadata = {"anything": "good day"}
)
litellm_response = dict(response)
litellm_response_keys = set(litellm_response.keys())
litellm_response_keys.discard('_response_ms')
print(litellm_response_keys)
print("LiteLLM Response\n")
# print(litellm_response)
# same request with OpenAI 1.0+
import openai
client = openai.OpenAI(api_key=os.environ['OPENAI_API_KEY'])
response = client.embeddings.create(
model="text-embedding-ada-002", input=["good morning from litellm", "this is another item"]
)
response = dict(response)
openai_response_keys = set(response.keys())
print(openai_response_keys)
assert litellm_response_keys == openai_response_keys # ENSURE the Keys in litellm response is exactly what the openai package returns
assert len(litellm_response["data"]) == 2 # expect two embedding responses from litellm_response since input had two
print(openai_response_keys)
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_openai_embedding()
def test_openai_azure_embedding_simple():
try:
response = embedding(
model="azure/azure-embedding-model",
input=["good morning from litellm"],
)
print(response)
response_keys = set(dict(response).keys())
response_keys.discard('_response_ms')
assert set(["usage", "model", "object", "data"]) == set(response_keys) #assert litellm response has expected keys from OpenAI embedding response
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_openai_azure_embedding_simple()
def test_openai_azure_embedding_timeouts():
try:
response = embedding(
model="azure/azure-embedding-model",
input=["good morning from litellm"],
timeout=0.00001
)
print(response)
except openai.APITimeoutError:
print("Good job got timeout error!")
pass
except Exception as e:
pytest.fail(f"Expected timeout error, did not get the correct error. Instead got {e}")
# test_openai_azure_embedding_timeouts()
def test_openai_embedding_timeouts():
try:
response = embedding(
model="text-embedding-ada-002",
input=["good morning from litellm"],
timeout=0.00001
)
print(response)
except openai.APITimeoutError:
print("Good job got OpenAI timeout error!")
pass
except Exception as e:
pytest.fail(f"Expected timeout error, did not get the correct error. Instead got {e}")
# test_openai_embedding_timeouts()
def test_openai_azure_embedding():
try:
api_key = os.environ['AZURE_API_KEY']
api_base = os.environ['AZURE_API_BASE']
api_version = os.environ['AZURE_API_VERSION']
os.environ['AZURE_API_VERSION'] = ""
os.environ['AZURE_API_BASE'] = ""
os.environ['AZURE_API_KEY'] = ""
response = embedding(
model="azure/azure-embedding-model",
input=["good morning from litellm", "this is another item"],
api_key=api_key,
api_base=api_base,
api_version=api_version,
)
print(response)
os.environ['AZURE_API_VERSION'] = api_version
os.environ['AZURE_API_BASE'] = api_base
os.environ['AZURE_API_KEY'] = api_key
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_openai_azure_embedding()
# test_openai_embedding()
def test_cohere_embedding():
try:
# litellm.set_verbose=True
response = embedding(
model="embed-english-v2.0", input=["good morning from litellm", "this is another item"]
)
print(f"response:", response)
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_cohere_embedding()
def test_cohere_embedding3():
try:
litellm.set_verbose=True
response = embedding(
model="embed-english-v3.0",
input=["good morning from litellm", "this is another item"],
)
print(f"response:", response)
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_cohere_embedding3()
def test_bedrock_embedding():
try:
response = embedding(
model="amazon.titan-embed-text-v1", input=["good morning from litellm, attempting to embed data",
"lets test a second string for good measure"]
)
print(f"response:", response)
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_bedrock_embedding()
# comment out hf tests - since hf endpoints are unstable
def test_hf_embedding():
try:
# huggingface/microsoft/codebert-base
# huggingface/facebook/bart-large
response = embedding(
model="huggingface/sentence-transformers/all-MiniLM-L6-v2", input=["good morning from litellm", "this is another item"]
)
print(f"response:", response)
except Exception as e:
# Note: Huggingface inference API is unstable and fails with "model loading errors all the time"
pass
# test_hf_embedding()
# test async embeddings
def test_aembedding():
try:
import asyncio
async def embedding_call():
try:
response = await litellm.aembedding(
model="text-embedding-ada-002",
input=["good morning from litellm", "this is another item"]
)
print(response)
except Exception as e:
pytest.fail(f"Error occurred: {e}")
asyncio.run(embedding_call())
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_aembedding()
def test_aembedding_azure():
try:
import asyncio
async def embedding_call():
try:
response = await litellm.aembedding(
model="azure/azure-embedding-model",
input=["good morning from litellm", "this is another item"]
)
print(response)
except Exception as e:
pytest.fail(f"Error occurred: {e}")
asyncio.run(embedding_call())
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_aembedding_azure()
# def test_custom_openai_embedding():
# litellm.set_verbose=True
# response = embedding(
# model="openai/custom_embedding",
# input=["good morning from litellm"],
# api_base="http://0.0.0.0:8000/"
# )
# print(response)
# test_custom_openai_embedding()
|