Completions

Chat and text completions using PraisonAI capabilities

Overview

The completions capability provides access to chat and text completion APIs through LiteLLM, supporting multiple providers.

Python Usage

Chat Completion

from praisonai.capabilities import chat_completion

result = chat_completion(
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is 2 + 2?"}
    ],
    model="gpt-4o-mini",
    max_tokens=100
)

print(result.content)  # "4"
print(result.model)    # "gpt-4o-mini-2024-07-18"
print(result.usage)    # {'prompt_tokens': 30, 'completion_tokens': 2, ...}

Text Completion (Legacy)

from praisonai.capabilities import text_completion

result = text_completion(
    prompt="The capital of France is",
    model="gpt-3.5-turbo-instruct",
    max_tokens=10
)

print(result.content)  # " Paris"

Async Usage

import asyncio
from praisonai.capabilities import achat_completion

async def main():
    result = await achat_completion(
        messages=[{"role": "user", "content": "Hello"}],
        model="gpt-4o-mini"
    )
    print(result.content)

asyncio.run(main())

Parameters

Parameter	Type	Default	Description
messages	List[Dict]	Required	List of message objects
model	str	”gpt-4o-mini”	Model to use
temperature	float	1.0	Sampling temperature
max_tokens	int	None	Maximum tokens to generate
tools	List[Dict]	None	List of tools
timeout	float	600.0	Request timeout in seconds
api_key	str	None	API key override

Result Object

The CompletionResult object contains:

• id: Response ID
• content: Generated text
• role: Message role (“assistant”)
• model: Model used
• finish_reason: Why generation stopped
• usage: Token usage statistics
• tool_calls: Any tool calls made