LLM Settings

import os
from smallestai.atoms.crew.clients.openai import OpenAIClient
self.llm = OpenAIClient(
    model="gpt-4o-mini",
    temperature=0.7,
    api_key=os.getenv("OPENAI_API_KEY")
)

# Consistent support agent
self.llm = OpenAIClient(model="gpt-4o-mini", temperature=0.3)
# Engaging sales agent
self.llm = OpenAIClient(model="gpt-4o-mini", temperature=0.8)

import os
from smallestai.atoms.crew.clients.openai import OpenAIClient
# Example: Using Groq
self.llm = OpenAIClient(
    model="llama-3.1-70b-versatile",
    base_url="https://api.groq.com/openai/v1",
    api_key=os.getenv("GROQ_API_KEY")
)

async def generate_response(self):
    response = await self.llm.chat(
        messages=self.context.messages,
        stream=True
    )
    
    async for chunk in response:
        if chunk.content:
            yield chunk.content

response = await self.llm.chat(
    messages=self.context.messages,
    stream=True,
    tools=self.tool_registry.get_schemas()
)

from openai import RateLimitError, APIError
async def generate_response(self):
    try:
        response = await self.llm.chat(
            messages=self.context.messages,
            stream=True
        )
        async for chunk in response:
            if chunk.content:
                yield chunk.content
                
    except RateLimitError:
        yield "I'm experiencing high demand. Please try again."
        
    except APIError as e:
        logger.error(f"LLM error: {e}")
        yield "I'm having trouble. Let me try again."

from smallestai.atoms.models import CreateAgentRequest
agent = CreateAgentRequest(
    name="SupportAgent",
    synthesizer={
        "provider": "smallest",  # Use Waves
        "model": "waves_lightning_v3_1",
        "voice_id": "zorin",     # Male, professional
        "speed": 1.0
    },
    # ... other config
)