File size: 17,211 Bytes
7db0ae4 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 |
import sys, os
import traceback
from dotenv import load_dotenv
load_dotenv()
import os, io
sys.path.insert(
0, os.path.abspath("../..")
) # Adds the parent directory to the system path
import pytest, asyncio
import litellm
from litellm import embedding, completion, completion_cost, Timeout, acompletion
from litellm import RateLimitError
import json
import os
import tempfile
litellm.num_retries = 3
litellm.cache = None
user_message = "Write a short poem about the sky"
messages = [{"content": user_message, "role": "user"}]
def load_vertex_ai_credentials():
# Define the path to the vertex_key.json file
print("loading vertex ai credentials")
filepath = os.path.dirname(os.path.abspath(__file__))
vertex_key_path = filepath + "/vertex_key.json"
# Read the existing content of the file or create an empty dictionary
try:
with open(vertex_key_path, "r") as file:
# Read the file content
print("Read vertexai file path")
content = file.read()
# If the file is empty or not valid JSON, create an empty dictionary
if not content or not content.strip():
service_account_key_data = {}
else:
# Attempt to load the existing JSON content
file.seek(0)
service_account_key_data = json.load(file)
except FileNotFoundError:
# If the file doesn't exist, create an empty dictionary
service_account_key_data = {}
# Update the service_account_key_data with environment variables
private_key_id = os.environ.get("VERTEX_AI_PRIVATE_KEY_ID", "")
private_key = os.environ.get("VERTEX_AI_PRIVATE_KEY", "")
private_key = private_key.replace("\\n", "\n")
service_account_key_data["private_key_id"] = private_key_id
service_account_key_data["private_key"] = private_key
# Create a temporary file
with tempfile.NamedTemporaryFile(mode="w+", delete=False) as temp_file:
# Write the updated content to the temporary file
json.dump(service_account_key_data, temp_file, indent=2)
# Export the temporary file as GOOGLE_APPLICATION_CREDENTIALS
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = os.path.abspath(temp_file.name)
@pytest.mark.asyncio
async def get_response():
load_vertex_ai_credentials()
prompt = '\ndef count_nums(arr):\n """\n Write a function count_nums which takes an array of integers and returns\n the number of elements which has a sum of digits > 0.\n If a number is negative, then its first signed digit will be negative:\n e.g. -123 has signed digits -1, 2, and 3.\n >>> count_nums([]) == 0\n >>> count_nums([-1, 11, -11]) == 1\n >>> count_nums([1, 1, 2]) == 3\n """\n'
try:
response = await acompletion(
model="gemini-pro",
messages=[
{
"role": "system",
"content": "Complete the given code with no more explanation. Remember that there is a 4-space indent before the first line of your generated code.",
},
{"role": "user", "content": prompt},
],
)
return response
except litellm.UnprocessableEntityError as e:
pass
except Exception as e:
pytest.fail(f"An error occurred - {str(e)}")
def test_vertex_ai():
import random
load_vertex_ai_credentials()
test_models = (
litellm.vertex_chat_models
+ litellm.vertex_code_chat_models
+ litellm.vertex_text_models
+ litellm.vertex_code_text_models
)
litellm.set_verbose = False
litellm.vertex_project = "reliablekeys"
test_models = random.sample(test_models, 1)
# test_models += litellm.vertex_language_models # always test gemini-pro
test_models = litellm.vertex_language_models # always test gemini-pro
for model in test_models:
try:
if model in [
"code-gecko",
"code-gecko@001",
"code-gecko@002",
"code-gecko@latest",
"code-bison@001",
"text-bison@001",
]:
# our account does not have access to this model
continue
print("making request", model)
response = completion(
model=model,
messages=[{"role": "user", "content": "hi"}],
temperature=0.7,
)
print("\nModel Response", response)
print(response)
assert type(response.choices[0].message.content) == str
assert len(response.choices[0].message.content) > 1
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_vertex_ai()
def test_vertex_ai_stream():
load_vertex_ai_credentials()
litellm.set_verbose = False
litellm.vertex_project = "reliablekeys"
import random
test_models = (
litellm.vertex_chat_models
+ litellm.vertex_code_chat_models
+ litellm.vertex_text_models
+ litellm.vertex_code_text_models
)
test_models = random.sample(test_models, 1)
test_models += litellm.vertex_language_models # always test gemini-pro
for model in test_models:
try:
if model in [
"code-gecko",
"code-gecko@001",
"code-gecko@002",
"code-gecko@latest",
"code-bison@001",
"text-bison@001",
]:
# our account does not have access to this model
continue
print("making request", model)
response = completion(
model=model,
messages=[
{"role": "user", "content": "write 10 line code code for saying hi"}
],
stream=True,
)
completed_str = ""
for chunk in response:
print(chunk)
content = chunk.choices[0].delta.content or ""
print("\n content", content)
completed_str += content
assert type(content) == str
# pass
assert len(completed_str) > 4
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_vertex_ai_stream()
@pytest.mark.asyncio
async def test_async_vertexai_response():
import random
load_vertex_ai_credentials()
test_models = (
litellm.vertex_chat_models
+ litellm.vertex_code_chat_models
+ litellm.vertex_text_models
+ litellm.vertex_code_text_models
)
test_models = random.sample(test_models, 1)
test_models += litellm.vertex_language_models # always test gemini-pro
for model in test_models:
print(f"model being tested in async call: {model}")
if model in [
"code-gecko",
"code-gecko@001",
"code-gecko@002",
"code-gecko@latest",
"code-bison@001",
"text-bison@001",
]:
# our account does not have access to this model
continue
try:
user_message = "Hello, how are you?"
messages = [{"content": user_message, "role": "user"}]
response = await acompletion(
model=model, messages=messages, temperature=0.7, timeout=5
)
print(f"response: {response}")
except litellm.Timeout as e:
pass
except Exception as e:
pytest.fail(f"An exception occurred: {e}")
# asyncio.run(test_async_vertexai_response())
@pytest.mark.asyncio
async def test_async_vertexai_streaming_response():
import random
load_vertex_ai_credentials()
test_models = (
litellm.vertex_chat_models
+ litellm.vertex_code_chat_models
+ litellm.vertex_text_models
+ litellm.vertex_code_text_models
)
test_models = random.sample(test_models, 1)
test_models += litellm.vertex_language_models # always test gemini-pro
for model in test_models:
if model in [
"code-gecko",
"code-gecko@001",
"code-gecko@002",
"code-gecko@latest",
"code-bison@001",
"text-bison@001",
]:
# our account does not have access to this model
continue
try:
user_message = "Hello, how are you?"
messages = [{"content": user_message, "role": "user"}]
response = await acompletion(
model="gemini-pro",
messages=messages,
temperature=0.7,
timeout=5,
stream=True,
)
print(f"response: {response}")
complete_response = ""
async for chunk in response:
print(f"chunk: {chunk}")
complete_response += chunk.choices[0].delta.content
print(f"complete_response: {complete_response}")
assert len(complete_response) > 0
except litellm.Timeout as e:
pass
except Exception as e:
print(e)
pytest.fail(f"An exception occurred: {e}")
# asyncio.run(test_async_vertexai_streaming_response())
def test_gemini_pro_vision():
try:
load_vertex_ai_credentials()
litellm.set_verbose = True
litellm.num_retries = 0
resp = litellm.completion(
model="vertex_ai/gemini-pro-vision",
messages=[
{
"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 == 263 # the gemini api returns 263 to us
except Exception as e:
import traceback
traceback.print_exc()
raise e
# test_gemini_pro_vision()
def gemini_pro_function_calling():
load_vertex_ai_credentials()
tools = [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location"],
},
},
}
]
messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]
completion = litellm.completion(
model="gemini-pro", messages=messages, tools=tools, tool_choice="auto"
)
print(f"completion: {completion}")
# gemini_pro_function_calling()
async def gemini_pro_async_function_calling():
load_vertex_ai_credentials()
tools = [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location"],
},
},
}
]
messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]
completion = await litellm.acompletion(
model="gemini-pro", messages=messages, tools=tools, tool_choice="auto"
)
print(f"completion: {completion}")
asyncio.run(gemini_pro_async_function_calling())
# Extra gemini Vision tests for completion + stream, async, async + stream
# if we run into issues with gemini, we will also add these to our ci/cd pipeline
# def test_gemini_pro_vision_stream():
# try:
# litellm.set_verbose = False
# litellm.num_retries=0
# print("streaming response from gemini-pro-vision")
# resp = litellm.completion(
# model = "vertex_ai/gemini-pro-vision",
# messages=[
# {
# "role": "user",
# "content": [
# {
# "type": "text",
# "text": "Whats in this image?"
# },
# {
# "type": "image_url",
# "image_url": {
# "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
# }
# }
# ]
# }
# ],
# stream=True
# )
# print(resp)
# for chunk in resp:
# print(chunk)
# except Exception as e:
# import traceback
# traceback.print_exc()
# raise e
# test_gemini_pro_vision_stream()
# def test_gemini_pro_vision_async():
# try:
# litellm.set_verbose = True
# litellm.num_retries=0
# async def test():
# resp = await litellm.acompletion(
# model = "vertex_ai/gemini-pro-vision",
# messages=[
# {
# "role": "user",
# "content": [
# {
# "type": "text",
# "text": "Whats in this image?"
# },
# {
# "type": "image_url",
# "image_url": {
# "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
# }
# }
# ]
# }
# ],
# )
# print("async response gemini pro vision")
# print(resp)
# asyncio.run(test())
# except Exception as e:
# import traceback
# traceback.print_exc()
# raise e
# test_gemini_pro_vision_async()
# def test_gemini_pro_vision_async_stream():
# try:
# litellm.set_verbose = True
# litellm.num_retries=0
# async def test():
# resp = await litellm.acompletion(
# model = "vertex_ai/gemini-pro-vision",
# messages=[
# {
# "role": "user",
# "content": [
# {
# "type": "text",
# "text": "Whats in this image?"
# },
# {
# "type": "image_url",
# "image_url": {
# "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
# }
# }
# ]
# }
# ],
# stream=True
# )
# print("async response gemini pro vision")
# print(resp)
# for chunk in resp:
# print(chunk)
# asyncio.run(test())
# except Exception as e:
# import traceback
# traceback.print_exc()
# raise e
# test_gemini_pro_vision_async()
|