fix(llms/vllm): honor VLLM_BASE_URL instead of always using localhost (#6897)

mem0/configs/llms/vllm.py

@@ -1,3 +1,4 @@
+import os
 from typing import Optional
 
 from mem0.configs.llms.base import BaseLlmConfig
@@ -53,4 +54,4 @@ class VllmConfig(BaseLlmConfig):
         )
 
         # vLLM-specific parameters
-        self.vllm_base_url = vllm_base_url or "http://localhost:8000/v1"
+        self.vllm_base_url = vllm_base_url or os.getenv("VLLM_BASE_URL") or "http://localhost:8000/v1"

mem0/llms/vllm.py

@@ -37,8 +37,7 @@ class VllmLLM(LLMBase):
             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(api_key=self.config.api_key, base_url=base_url)
+        self.client = OpenAI(api_key=self.config.api_key, base_url=self.config.vllm_base_url)
 
     def _parse_response(self, response, tools):
         """