57 lines
1.6 KiB
Python
57 lines
1.6 KiB
Python
from typing import Iterator, Optional
|
|
import openai
|
|
import json
|
|
|
|
from .llm_engine import LlmEngine
|
|
|
|
class OpenAILlmEngine(LlmEngine):
|
|
"""
|
|
LLM Engine implementation using OpenAI's API.
|
|
Supports streaming responses from chat completion models.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
model: str,
|
|
api_key: str,
|
|
):
|
|
"""
|
|
Initialize the OpenAI LLM Engine.
|
|
|
|
Args:
|
|
model: OpenAI model to use (default: gpt-4)
|
|
api_key: OpenAI API key. If None, will try to read from OPENAI_API_KEY env var
|
|
"""
|
|
self._model = model
|
|
|
|
# Initialize OpenAI client
|
|
self.client = openai.Client(
|
|
api_key=api_key,
|
|
)
|
|
|
|
def infer(self, system_prompt: str, main_context: str) -> Iterator[str]:
|
|
"""
|
|
Run inference using the system prompt and main context.
|
|
|
|
Args:
|
|
system_prompt: The system prompt string
|
|
main_context: The main context string after templating
|
|
|
|
Returns:
|
|
Iterator[str]: An iterator that yields the generated text in chunks.
|
|
"""
|
|
messages = [
|
|
{"role": "system", "content": system_prompt},
|
|
{"role": "user", "content": main_context}
|
|
]
|
|
|
|
stream = self.client.chat.completions.create(
|
|
model=self._model,
|
|
messages=messages,
|
|
stream=True,
|
|
temperature=0.3,
|
|
)
|
|
|
|
for chunk in stream:
|
|
if content := chunk.choices[0].delta.content:
|
|
yield content |