Refactored base class config for llms (#3241)

mem0/llms/vllm.py

@@ -1,16 +1,36 @@
 import json
 import os
-from typing import Dict, List, Optional
+from typing import Dict, List, Optional, Union
 
 from openai import OpenAI
 
 from mem0.configs.llms.base import BaseLlmConfig
+from mem0.configs.llms.vllm import VllmConfig
 from mem0.llms.base import LLMBase
 from mem0.memory.utils import extract_json
 
 
 class VllmLLM(LLMBase):
-    def __init__(self, config: Optional[BaseLlmConfig] = None):
+    def __init__(self, config: Optional[Union[BaseLlmConfig, VllmConfig, Dict]] = None):
+        # Convert to VllmConfig if needed
+        if config is None:
+            config = VllmConfig()
+        elif isinstance(config, dict):
+            config = VllmConfig(**config)
+        elif isinstance(config, BaseLlmConfig) and not isinstance(config, VllmConfig):
+            # Convert BaseLlmConfig to VllmConfig
+            config = VllmConfig(
+                model=config.model,
+                temperature=config.temperature,
+                api_key=config.api_key,
+                max_tokens=config.max_tokens,
+                top_p=config.top_p,
+                top_k=config.top_k,
+                enable_vision=config.enable_vision,
+                vision_details=config.vision_details,
+                http_client_proxies=config.http_client,
+            )
+
         super().__init__(config)
 
         if not self.config.model:
@@ -18,8 +38,7 @@ class VllmLLM(LLMBase):
 
         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)
+        self.client = OpenAI(api_key=self.config.api_key, base_url=base_url)
 
     def _parse_response(self, response, tools):
         """
@@ -57,6 +76,7 @@ class VllmLLM(LLMBase):
         response_format=None,
         tools: Optional[List[Dict]] = None,
         tool_choice: str = "auto",
+        **kwargs,
     ):
         """
         Generate a response based on the given messages using vLLM.
@@ -66,20 +86,19 @@ class VllmLLM(LLMBase):
             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".
+            **kwargs: Additional vLLM-specific parameters.
 
         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
+        # Get common parameters
+        params = self._get_common_params(**kwargs)
+        params.update(
+            {
+                "model": self.config.model,
+                "messages": messages,
+            }
+        )
 
         if tools:
             params["tools"] = tools