92 lines
2.9 KiB
Python
92 lines
2.9 KiB
Python
import json
|
|
import os
|
|
from typing import Dict, List, Optional
|
|
|
|
from openai import OpenAI
|
|
|
|
from openai import OpenAI
|
|
|
|
from mem0.configs.llms.base import BaseLlmConfig
|
|
from mem0.llms.base import LLMBase
|
|
from mem0.memory.utils import extract_json
|
|
|
|
|
|
class VllmLLM(LLMBase):
|
|
def __init__(self, config: Optional[BaseLlmConfig] = None):
|
|
super().__init__(config)
|
|
|
|
if not self.config.model:
|
|
self.config.model = "Qwen/Qwen2.5-32B-Instruct"
|
|
|
|
self.config.api_key = self.config.api_key or os.getenv("VLLM_API_KEY") or "vllm-api-key"
|
|
base_url = self.config.vllm_base_url or os.getenv("VLLM_BASE_URL")
|
|
|
|
self.client = OpenAI(base_url=base_url, api_key=self.config.api_key)
|
|
|
|
def _parse_response(self, response, tools):
|
|
"""
|
|
Process the response based on whether tools are used or not.
|
|
|
|
Args:
|
|
response: The raw response from API.
|
|
tools: The list of tools provided in the request.
|
|
|
|
Returns:
|
|
str or dict: The processed response.
|
|
"""
|
|
if tools:
|
|
processed_response = {
|
|
"content": response.choices[0].message.content,
|
|
"tool_calls": [],
|
|
}
|
|
|
|
if response.choices[0].message.tool_calls:
|
|
for tool_call in response.choices[0].message.tool_calls:
|
|
processed_response["tool_calls"].append(
|
|
{
|
|
"name": tool_call.function.name,
|
|
"arguments": json.loads(extract_json(tool_call.function.arguments)),
|
|
}
|
|
)
|
|
|
|
return processed_response
|
|
else:
|
|
return response.choices[0].message.content
|
|
|
|
def generate_response(
|
|
self,
|
|
messages: List[Dict[str, str]],
|
|
response_format=None,
|
|
tools: Optional[List[Dict]] = None,
|
|
tool_choice: str = "auto",
|
|
):
|
|
"""
|
|
Generate a response based on the given messages using vLLM.
|
|
|
|
Args:
|
|
messages (list): List of message dicts containing 'role' and 'content'.
|
|
response_format (str or object, optional): Format of the response. Defaults to "text".
|
|
tools (list, optional): List of tools that the model can call. Defaults to None.
|
|
tool_choice (str, optional): Tool choice method. Defaults to "auto".
|
|
|
|
Returns:
|
|
str: The generated response.
|
|
"""
|
|
params = {
|
|
"model": self.config.model,
|
|
"messages": messages,
|
|
"temperature": self.config.temperature,
|
|
"max_tokens": self.config.max_tokens,
|
|
"top_p": self.config.top_p,
|
|
}
|
|
|
|
if response_format:
|
|
params["response_format"] = response_format
|
|
|
|
if tools:
|
|
params["tools"] = tools
|
|
params["tool_choice"] = tool_choice
|
|
|
|
response = self.client.chat.completions.create(**params)
|
|
return self._parse_response(response, tools)
|