mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 23:58:34 +00:00

Files

Devin AI c96ae80121 Fix CI failures: correct context window ratio and remove unused imports

- Fix test expectations to use 0.85 ratio instead of 0.75 (matches CONTEXT_WINDOW_USAGE_RATIO)
- Remove unused imports (pytest, Mock) from test file
- Add context window size warning for large models (>100K tokens)
- Update documentation with performance considerations and rate limiting best practices
- Address code review feedback from João regarding validation and error handling

Co-Authored-By: João <joao@crewai.com>

2025-06-04 10:15:30 +00:00

6.5 KiB

Raw Blame History

AI/ML API Integration with CrewAI

CrewAI now supports AI/ML API as a provider, giving you access to 300+ AI models through their platform. AI/ML API provides a unified interface to models from various providers including Meta (Llama), Anthropic (Claude), Mistral, Qwen, and more.

Setup

Get your API key from AI/ML API
Set your API key as an environment variable:

export AIML_API_KEY="your-api-key-here"

Usage

AI/ML API models use the openai/ prefix for compatibility with LiteLLM. Here are some examples:

Basic Usage

from crewai import Agent, LLM

# Use Llama 3.1 70B through AI/ML API
llm = LLM(
    model="openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
    api_key="your-aiml-api-key"  # or set AIML_API_KEY env var
)

agent = Agent(
    role="Research Assistant",
    goal="Help with research tasks",
    backstory="You are an expert researcher with access to advanced AI capabilities",
    llm=llm
)

Available Models

Popular models available through AI/ML API:

Llama Models

openai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo - Largest Llama model
openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo - High performance
openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo - Fast and efficient
openai/meta-llama/Meta-Llama-3.2-90B-Vision-Instruct-Turbo - Vision capabilities

Claude Models

openai/anthropic/claude-3-5-sonnet-20241022 - Latest Claude Sonnet
openai/anthropic/claude-3-5-haiku-20241022 - Fast Claude model
openai/anthropic/claude-3-opus-20240229 - Most capable Claude

Other Models

openai/mistralai/Mixtral-8x7B-Instruct-v0.1 - Mistral's mixture of experts
openai/Qwen/Qwen2.5-72B-Instruct-Turbo - Qwen's large model
openai/deepseek-ai/DeepSeek-V2.5 - DeepSeek's latest model

Complete Example

from crewai import Agent, Task, Crew, LLM

# Configure AI/ML API LLM
llm = LLM(
    model="openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
    api_key="your-aiml-api-key"
)

# Create an agent with AI/ML API model
researcher = Agent(
    role="AI Research Specialist",
    goal="Analyze AI trends and provide insights",
    backstory="You are an expert in artificial intelligence with deep knowledge of current trends and developments",
    llm=llm
)

# Create a task
research_task = Task(
    description="Research the latest developments in large language models and summarize key findings",
    expected_output="A comprehensive summary of recent LLM developments with key insights",
    agent=researcher
)

# Create and run the crew
crew = Crew(
    agents=[researcher],
    tasks=[research_task]
)

result = crew.kickoff()
print(result)

Environment Configuration

You can configure AI/ML API in several ways:

# Method 1: Direct API key
llm = LLM(
    model="openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
    api_key="your-aiml-api-key"
)

# Method 2: Environment variable (recommended)
# Set AIML_API_KEY in your environment
llm = LLM(model="openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo")

# Method 3: Base URL configuration (if needed)
llm = LLM(
    model="openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
    base_url="https://api.aimlapi.com/v1",
    api_key="your-aiml-api-key"
)

Features

AI/ML API models through CrewAI support:

Function Calling: Most models support tool usage and function calling
Streaming: Real-time response streaming for better user experience
Context Windows: Optimized context window management for each model
Vision Models: Some models support image understanding capabilities
Structured Output: JSON and Pydantic model output formatting

Model Selection Guide

Choose the right model for your use case:

For complex reasoning: Use Llama 3.1 405B or Claude 3.5 Sonnet
For balanced performance: Use Llama 3.1 70B or Claude 3.5 Haiku
For speed and efficiency: Use Llama 3.1 8B or smaller models
For vision tasks: Use Llama 3.2 Vision models
For coding: Consider DeepSeek or specialized coding models

Performance Considerations

Context Window Management

AI/ML API models support large context windows, but be mindful of:

Memory Usage: Large context windows (>100K tokens) may require significant memory
Processing Time: Larger contexts take longer to process
Cost Impact: Most providers charge based on token usage

Rate Limiting Best Practices

AI/ML API implements rate limiting to ensure fair usage:

Implement Retry Logic: Use exponential backoff for rate limit errors
Monitor Usage: Track your API usage through the AI/ML API dashboard
Batch Requests: Group multiple requests when possible to optimize throughput
Cache Results: Store frequently used responses to reduce API calls

import time
from crewai import LLM

def create_llm_with_retry(model_name, max_retries=3):
    for attempt in range(max_retries):
        try:
            return LLM(model=model_name)
        except Exception as e:
            if "rate limit" in str(e).lower() and attempt < max_retries - 1:
                wait_time = 2 ** attempt  # Exponential backoff
                time.sleep(wait_time)
                continue
            raise e

Cost Optimization

Model Selection: Choose appropriate model size for your use case
Context Management: Trim unnecessary context to reduce token usage
Streaming: Use streaming for real-time applications to improve perceived performance

Troubleshooting

Common Issues

Authentication Error: Ensure your AIML_API_KEY is set correctly
Model Not Found: Verify the model name uses the correct openai/ prefix
Rate Limits: AI/ML API has rate limits; implement appropriate retry logic
Context Length: Monitor context window usage for optimal performance
Memory Issues: Large context windows may cause memory problems; monitor usage

Getting Help

Check the AI/ML API Documentation
Review model-specific capabilities and limitations
Monitor usage and costs through the AI/ML API dashboard

Migration from Other Providers

If you're migrating from other providers:

# From OpenAI
# OLD: llm = LLM(model="gpt-4")
# NEW: llm = LLM(model="openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo")

# From Anthropic
# OLD: llm = LLM(model="claude-3-sonnet")
# NEW: llm = LLM(model="openai/anthropic/claude-3-5-sonnet-20241022")

The integration maintains full compatibility with CrewAI's existing features while providing access to AI/ML API's extensive model catalog.

6.5 KiB Raw Blame History