LiteLLM Integration

from litellm import completion
import os

# Set your API keys
os.environ["OPENAI_API_KEY"] = "your-openai-api-key"

# Route through Superagent proxy
response = completion(
    model="openai/gpt-4o",
    messages=[{"content": "Hello world", "role": "user"}],
    api_base="YOUR_SUPERAGENT_PROXY_URL"  # Replace with your Superagent proxy
)

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

model_list:
  - model_name: gpt-4o
    litellm_params:
      model: openai/gpt-4o
      api_base: YOUR_SUPERAGENT_PROXY_URL  # Replace with your Superagent proxy
      api_key: "os.environ/OPENAI_API_KEY"
  
  - model_name: claude-3-opus
    litellm_params:
      model: anthropic/claude-3-opus-20240229
      api_base: YOUR_SUPERAGENT_PROXY_URL  # Replace with your Superagent proxy
      api_key: "os.environ/ANTHROPIC_API_KEY"

  - model_name: grok-3
    litellm_params:
      model: xai/grok-3
      api_base: YOUR_SUPERAGENT_PROXY_URL  # Replace with your Superagent proxy
      api_key: "os.environ/XAI_API_KEY"

# Install LiteLLM
pip install 'litellm[proxy]'

# Start the proxy with your config
litellm --config config.yaml

# The proxy will run on http://0.0.0.0:4000

import openai

# Connect to your LiteLLM proxy (now protected by Superagent)
client = openai.OpenAI(
    api_key="anything",  # LiteLLM proxy doesn't require authentication by default
    base_url="http://localhost:4000"  # Your LiteLLM proxy URL
)

# Use any configured model
response = client.chat.completions.create(
    model="gpt-4o",  # Model name from your config
    messages=[{"role": "user", "content": "Hello world"}]
)

import OpenAI from 'openai';

// Connect to your protected LiteLLM proxy
const client = new OpenAI({
  apiKey: 'anything', // LiteLLM proxy authentication
  baseURL: 'http://localhost:4000', // Your LiteLLM proxy URL
});

// Use any configured model
const response = await client.chat.completions.create({
  model: 'claude-3-opus', // Model name from your config
  messages: [{ role: 'user', content: 'Hello world' }],
});

model_list:
  # Multiple OpenAI deployments through Superagent
  - model_name: gpt-4o
    litellm_params:
      model: openai/gpt-4o
      api_base: YOUR_SUPERAGENT_PROXY_URL_1
      api_key: "os.environ/OPENAI_API_KEY"
  
  - model_name: gpt-4o  # Same model name for load balancing
    litellm_params:
      model: openai/gpt-4o
      api_base: YOUR_SUPERAGENT_PROXY_URL_2
      api_key: "os.environ/OPENAI_API_KEY"

router_settings:
  routing_strategy: "simple-shuffle"  # Load balance between deployments
  fallbacks: [{"claude-3-opus": ["gpt-4o"]}]  # Fallback routing

from litellm import completion

# Streaming through Superagent proxy
response = completion(
    model="openai/gpt-4o",
    messages=[{"content": "Write a story", "role": "user"}],
    api_base="YOUR_SUPERAGENT_PROXY_URL",
    stream=True
)

for chunk in response:
    if hasattr(chunk.choices[0].delta, 'content') and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

FROM ghcr.io/berriai/litellm:main-latest

# Copy your config
COPY config.yaml /app/config.yaml

# Expose port
EXPOSE 4000

# Start with config
CMD ["--config", "/app/config.yaml"]