AI Model Providers

import openai

# Initialize the client
client = openai.OpenAI(api_key="your-api-key")

# Create an agent function that can process inputs and generate responses
def agent_process(user_input, context=None):
    messages = []
    
    # System message to define agent behavior
    messages.append({
        "role": "system", 
        "content": "You are an AI research assistant designed to help with information gathering."
    })
    
    # Add conversation context if available
    if context:
        messages.extend(context)
    
    # Add user input
    messages.append({"role": "user", "content": user_input})
    
    # Call the API
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=messages,
        temperature=0.7
    )
    
    return response.choices[0].message.content

# Example usage
result = agent_process("Find recent research papers on climate change mitigation.")
print(result)

import anthropic

# Initialize the client
client = anthropic.Anthropic(api_key="your-api-key")

# Create an agent function that can process inputs and generate responses
def agent_process(user_input, conversation_history=None):
    # Prepare the messages
    messages = []
    
    # Add conversation history if available
    if conversation_history:
        messages.extend(conversation_history)
    
    # Add the user's new message
    messages.append({"role": "user", "content": user_input})
    
    # Call the API
    response = client.messages.create(
        model="claude-3-opus-20240229",
        max_tokens=1000,
        messages=messages,
        temperature=0.7
    )
    
    # Return the response
    return response.content[0].text

# Example usage
result = agent_process("Analyze the potential impact of quantum computing on cryptography.")
print(result)

import mistralai
from mistralai.client import MistralClient
from mistralai.models.chat_completion import ChatMessage

# Initialize the client
client = MistralClient(api_key="your-api-key")

# Create an agent function that can process inputs and generate responses
def agent_process(user_input, chat_history=None):
    messages = []
    
    # System message to define agent behavior
    messages.append(ChatMessage(
        role="system",
        content="You are an AI assistant that helps users with research and analysis."
    ))
    
    # Add conversation history if available
    if chat_history:
        messages.extend(chat_history)
    
    # Add the user's message
    messages.append(ChatMessage(role="user", content=user_input))
    
    # Call the API
    response = client.chat(
        model="mistral-large-latest",
        messages=messages,
        temperature=0.7,
        max_tokens=1000
    )
    
    # Return the response
    return response.choices[0].message.content

# Example usage
result = agent_process("Explain the concept of transformers in machine learning.")
print(result)