Feat: fix stream output and add openai stream (#276)

feat:add openai stream

Author: fridayL

src/memos/mem_os/product.py

@@ -1024,7 +1024,7 @@ def chat_with_references(
             elif self.config.chat_model.backend == "vllm":
                 response_stream = self.chat_llm.generate_stream(current_messages)
         else:
-            if self.config.chat_model.backend in ["huggingface", "vllm"]:
+            if self.config.chat_model.backend in ["huggingface", "vllm", "openai"]:
                 response_stream = self.chat_llm.generate_stream(current_messages)
             else:
                 response_stream = self.chat_llm.generate(current_messages)
@@ -1041,7 +1041,7 @@ def chat_with_references(
         full_response = ""
         token_count = 0
         # Use tiktoken for proper token-based chunking
-        if self.config.chat_model.backend not in ["huggingface", "vllm"]:
+        if self.config.chat_model.backend not in ["huggingface", "vllm", "openai"]:
             # For non-huggingface backends, we need to collect the full response first
             full_response_text = ""
             for chunk in response_stream: