LiteLLM: 各LLMの差を吸収してくれる薄いライブラリを使ってみる

from litellm import completion

response = completion(
  model="gpt-4o-mini",
  messages=[{ "content": "Hello, how are you?","role": "user"}]
)

response = completion(
  model="claude-3-haiku-20240307",
  messages=[{ "content": "Hello, how are you?","role": "user"}]
)

# 出力トークン数
response.usage.completion_tokens

# 入力トークン数
response.usage.prompt_tokens

# 合計トークン数
response.usage.total_tokens

# プロンプトトークンの詳細を表示
print(response.usage.prompt_tokens_details)

# 出力結果:
PromptTokensDetailsWrapper(audio_tokens=0, cached_tokens=0, text_tokens=None, image_tokens=None)

from litellm import completion 
import litellm 
import os 

litellm.set_verbose = True # 👈 SEE RAW REQUEST
os.environ["ANTHROPIC_API_KEY"] = "" 

response = completion(
    model="anthropic/claude-3-5-sonnet-20240620",
    messages=[
        {
            "role": "system",
            "content": [
                {
                    "type": "text",
                    "text": "You are an AI assistant tasked with analyzing legal documents.",
                },
                {
                    "type": "text",
                    "text": "Here is the full text of a complex legal agreement" * 400,
                    "cache_control": {"type": "ephemeral"},
                },
            ],
        },
        {
            "role": "user",
            "content": "what are the key terms and conditions in this agreement?",
        },
    ]
)

print(response.usage)

import litellm

litellm.success_callback = ["langsmith"]

import os

os.environ["LANGSMITH_API_KEY"] = ""
os.environ["LANGSMITH_PROJECT"] = "" # defaults to litellm-completion
os.environ["LANGSMITH_DEFAULT_RUN_NAME"] = "" # defaults to LLMRun
# LLM API Keys
os.environ['OPENAI_API_KEY']=""

import litellm

# set langsmith as a callback, litellm will send the data to langsmith
litellm.success_callback = ["langsmith"] 
 
# openai call
response = litellm.completion(
  model="gpt-4o-mini",
  messages=[
    {"role": "user", "content": "Hi 👋 - i'm openai"}
  ]
)

from litellm import completion
import os 

os.environ["OPENAI_API_KEY"] = ""

response = completion(
  model="gpt-4o-mini",
  response_format={ "type": "json_object" },
  messages=[
    {"role": "system", "content": "You are a helpful assistant designed to output JSON."},
    {"role": "user", "content": "Who won the world series in 2020?"}
  ]
)
print(response.choices[0].message.content)

import os
from pydantic import BaseModel
from litellm import completion 

# add to env var 
os.environ["OPENAI_API_KEY"] = ""

messages = [{"role": "user", "content": "List 5 cookie recipes"}]

class CalendarEvent(BaseModel):
  name: str
  date: str
  participants: list[str]

resp = completion(
    model="gpt-4o-2024-08-06",
    messages=messages,
    response_format=CalendarEvent
)

print("Received={}".format(resp))

from litellm import get_supported_openai_params

params = get_supported_openai_params(model="anthropic.claude-3", custom_llm_provider="bedrock")

assert "response_format" in params

# !gcloud auth application-default login - run this to add vertex credentials to your env
import litellm, os
from litellm import completion 
from pydantic import BaseModel 


messages=[
        {"role": "system", "content": "Extract the event information."},
        {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."},
    ]

litellm.enable_json_schema_validation = True
litellm.set_verbose = True # see the raw request made by litellm

class CalendarEvent(BaseModel):
  name: str
  date: str
  participants: list[str]

resp = completion(
    model="gemini/gemini-1.5-pro",
    messages=messages,
    response_format=CalendarEvent,
)

print("Received={}".format(resp))