[AI] Using LiteLLM to unify LLMs calls

python3 -m venv litellm_venv #create the venv

#litellm_venv\Scripts\activate #activate venv (windows)
source litellm_venv/bin/activate #(linux)

pip install litellm==1.55.9 #https://pypi.org/project/litellm/#history

source .env

#export OPENAI_API_KEY="your-api-key-here"
#set OPENAI_API_KEY=your-api-key-here
#$env:OPENAI_API_KEY="your-api-key-here"
echo $OPENAI_API_KEY

import os

from dotenv import load_dotenv

# Load environment variables from the .env file - 
## Instead of hardcoding them in the py script
load_dotenv()

from litellm import completion
import os

## set ENV variables
##os.environ["OPENAI_API_KEY"] = "your-openai-key"

messages = [{ "content": "Hello, how are you?","role": "user"}]

# openai call
response = completion(model="openai/gpt-4o", messages=messages)

# anthropic call
response = completion(model="anthropic/claude-3-sonnet-20240229", messages=messages)
print(response)

from litellm import completion
import os

## set ENV variables
##os.environ["ANTHROPIC_API_KEY"] = "sk-ant-api03-..."
import os
from litellm import completion

#anthropic api call
messages = [{"role": "user", "content": "Hey! Which model are you and who train you?"}]
response = completion(model="claude-3-5-sonnet-20240620", messages=messages)
print(response)

#Extracting the message content
message_content = response.choices[0].message.content
print(message_content)


# Extracting the total tokens
total_tokens = response.usage.total_tokens
print(total_tokens)

    client = anthropic.Anthropic(api_key=api_key)
    response = client.messages.create(
        model=model,
        max_tokens=1024,
        temperature=temperature,
        system="Generate 5 attention-grabbing blog titles based on user-provived keywords",
        messages=[{"role":"user", "content":user_content}],
    )
    return response.content[0].text

from litellm import completion
import os

##os.environ['GROQ_API_KEY'] = "gsk_...."
response = completion(
    model="groq/llama3-8b-8192",  #llama3-70b-8192 #mixtral-8x7b-32768 
    #llama-3.1-70b-versatile #llama-3.3-70b-versatile
    messages=[
       {"role": "user", "content": "hello from litellm, which model are you?"}
   ],
)
##print(response)

message_content = response.choices[0].message.content
print(message_content)


# Extracting the total tokens
total_tokens = response.usage.total_tokens
print(total_tokens)

source .env

curl https://api.groq.com/openai/v1/models \
-H "Authorization: Bearer $GROQ_API_KEY"

from litellm import completion

response = completion(
            model="ollama/llama2",
            messages = [{ "content": "Hello, how are you?","role": "user"}],
            api_base="http://localhost:11434"
)

import os
from litellm import completion

# [OPTIONAL] set env var
##os.environ["HUGGINGFACE_API_KEY"] = "huggingface_api_key"

messages = [{ "content": "There's a llama in my garden 😱 What should I do?","role": "user"}]

# e.g. Call 'https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct' from Serverless Inference API
response = completion(
    model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[{ "content": "Hello, how are you?","role": "user"}],
    stream=True
)
print(response)