Spaces:
Sleeping
Sleeping
File size: 10,412 Bytes
4b95d23 |
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 |
import openai
import time, tiktoken
from openai import OpenAI
import os, anthropic, json
import google.generativeai as genai
TOKENS_IN = dict()
TOKENS_OUT = dict()
encoding = tiktoken.get_encoding("cl100k_base")
def curr_cost_est():
costmap_in = {
"gpt-4o": 2.50 / 1000000,
"gpt-4o-mini": 0.150 / 1000000,
"o1-preview": 15.00 / 1000000,
"o1-mini": 3.00 / 1000000,
"claude-3-5-sonnet": 3.00 / 1000000,
"deepseek-chat": 1.00 / 1000000,
"o1": 15.00 / 1000000,
"o3-mini": 1.10 / 1000000,
}
costmap_out = {
"gpt-4o": 10.00/ 1000000,
"gpt-4o-mini": 0.6 / 1000000,
"o1-preview": 60.00 / 1000000,
"o1-mini": 12.00 / 1000000,
"claude-3-5-sonnet": 12.00 / 1000000,
"deepseek-chat": 5.00 / 1000000,
"o1": 60.00 / 1000000,
"o3-mini": 4.40 / 1000000,
}
return sum([costmap_in[_]*TOKENS_IN[_] for _ in TOKENS_IN]) + sum([costmap_out[_]*TOKENS_OUT[_] for _ in TOKENS_OUT])
def query_model(model_str, prompt, system_prompt, openai_api_key=None, gemini_api_key=None, anthropic_api_key=None, tries=5, timeout=5.0, temp=None, print_cost=True, version="1.5"):
preloaded_api = os.getenv('OPENAI_API_KEY')
if openai_api_key is None and preloaded_api is not None:
openai_api_key = preloaded_api
if openai_api_key is None and anthropic_api_key is None:
raise Exception("No API key provided in query_model function")
if openai_api_key is not None:
openai.api_key = openai_api_key
os.environ["OPENAI_API_KEY"] = openai_api_key
if anthropic_api_key is not None:
os.environ["ANTHROPIC_API_KEY"] = anthropic_api_key
if gemini_api_key is not None:
os.environ["GEMINI_API_KEY"] = gemini_api_key
for _ in range(tries):
try:
if model_str == "gpt-4o-mini" or model_str == "gpt4omini" or model_str == "gpt-4omini" or model_str == "gpt4o-mini":
model_str = "gpt-4o-mini"
messages = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": prompt}]
if version == "0.28":
if temp is None:
completion = openai.ChatCompletion.create(
model=f"{model_str}", # engine = "deployment_name".
messages=messages
)
else:
completion = openai.ChatCompletion.create(
model=f"{model_str}", # engine = "deployment_name".
messages=messages, temperature=temp
)
else:
client = OpenAI()
if temp is None:
completion = client.chat.completions.create(
model="gpt-4o-mini-2024-07-18", messages=messages, )
else:
completion = client.chat.completions.create(
model="gpt-4o-mini-2024-07-18", messages=messages, temperature=temp)
answer = completion.choices[0].message.content
elif model_str == "gemini-2.0-pro":
genai.configure(api_key=gemini_api_key)
model = genai.GenerativeModel(model_name="gemini-2.0-pro-exp-02-05", system_instruction=system_prompt)
answer = model.generate_content(prompt).text
elif model_str == "gemini-1.5-pro":
genai.configure(api_key=gemini_api_key)
model = genai.GenerativeModel(model_name="gemini-1.5-pro", system_instruction=system_prompt)
answer = model.generate_content(prompt).text
elif model_str == "o3-mini":
model_str = "o3-mini"
messages = [
{"role": "user", "content": system_prompt + prompt}]
if version == "0.28":
completion = openai.ChatCompletion.create(
model=f"{model_str}", messages=messages)
else:
client = OpenAI()
completion = client.chat.completions.create(
model="o3-mini-2025-01-31", messages=messages)
answer = completion.choices[0].message.content
elif model_str == "claude-3.5-sonnet":
client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])
message = client.messages.create(
model="claude-3-5-sonnet-latest",
system=system_prompt,
messages=[{"role": "user", "content": prompt}])
answer = json.loads(message.to_json())["content"][0]["text"]
elif model_str == "gpt4o" or model_str == "gpt-4o":
model_str = "gpt-4o"
messages = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": prompt}]
if version == "0.28":
if temp is None:
completion = openai.ChatCompletion.create(
model=f"{model_str}", # engine = "deployment_name".
messages=messages
)
else:
completion = openai.ChatCompletion.create(
model=f"{model_str}", # engine = "deployment_name".
messages=messages, temperature=temp)
else:
client = OpenAI()
if temp is None:
completion = client.chat.completions.create(
model="gpt-4o-2024-08-06", messages=messages, )
else:
completion = client.chat.completions.create(
model="gpt-4o-2024-08-06", messages=messages, temperature=temp)
answer = completion.choices[0].message.content
elif model_str == "deepseek-chat":
model_str = "deepseek-chat"
messages = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": prompt}]
if version == "0.28":
raise Exception("Please upgrade your OpenAI version to use DeepSeek client")
else:
deepseek_client = OpenAI(
api_key=os.getenv('DEEPSEEK_API_KEY'),
base_url="https://api.deepseek.com/v1"
)
if temp is None:
completion = deepseek_client.chat.completions.create(
model="deepseek-chat",
messages=messages)
else:
completion = deepseek_client.chat.completions.create(
model="deepseek-chat",
messages=messages,
temperature=temp)
answer = completion.choices[0].message.content
elif model_str == "o1-mini":
model_str = "o1-mini"
messages = [
{"role": "user", "content": system_prompt + prompt}]
if version == "0.28":
completion = openai.ChatCompletion.create(
model=f"{model_str}", # engine = "deployment_name".
messages=messages)
else:
client = OpenAI()
completion = client.chat.completions.create(
model="o1-mini-2024-09-12", messages=messages)
answer = completion.choices[0].message.content
elif model_str == "o1":
model_str = "o1"
messages = [
{"role": "user", "content": system_prompt + prompt}]
if version == "0.28":
completion = openai.ChatCompletion.create(
model="o1-2024-12-17", # engine = "deployment_name".
messages=messages)
else:
client = OpenAI()
completion = client.chat.completions.create(
model="o1-2024-12-17", messages=messages)
answer = completion.choices[0].message.content
elif model_str == "o1-preview":
model_str = "o1-preview"
messages = [
{"role": "user", "content": system_prompt + prompt}]
if version == "0.28":
completion = openai.ChatCompletion.create(
model=f"{model_str}", # engine = "deployment_name".
messages=messages)
else:
client = OpenAI()
completion = client.chat.completions.create(
model="o1-preview", messages=messages)
answer = completion.choices[0].message.content
try:
if model_str in ["o1-preview", "o1-mini", "claude-3.5-sonnet", "o1", "o3-mini"]:
encoding = tiktoken.encoding_for_model("gpt-4o")
elif model_str in ["deepseek-chat"]:
encoding = tiktoken.encoding_for_model("cl100k_base")
else:
encoding = tiktoken.encoding_for_model(model_str)
if model_str not in TOKENS_IN:
TOKENS_IN[model_str] = 0
TOKENS_OUT[model_str] = 0
TOKENS_IN[model_str] += len(encoding.encode(system_prompt + prompt))
TOKENS_OUT[model_str] += len(encoding.encode(answer))
if print_cost:
print(f"Current experiment cost = ${curr_cost_est()}, ** Approximate values, may not reflect true cost")
except Exception as e:
if print_cost: print(f"Cost approximation has an error? {e}")
return answer
except Exception as e:
print("Inference Exception:", e)
time.sleep(timeout)
continue
raise Exception("Max retries: timeout")
#print(query_model(model_str="o1-mini", prompt="hi", system_prompt="hey")) |