I have llm studio installed locally and I’m trying to use the openai to connect to it and I’m getting connection error , here is my code , what is the problem
import openai 
import re 
import getpass
openai.base_url = “http://127.0.0.1:1234 ” 
openai.api_key = “”
def complete(prompt: str) → str: 
try:
    response = openai.chat.completions.create(
        model="deepseek-r1-distill-qwen-7b",  # Ensure this matches your local model's name
        messages=[{"role": "user", "content": prompt}],
        temperature=0.7,  # Adjust as needed
        max_tokens=100  # Limit response length
    )
    return response.choices[0].message.content
except Exception as e:
    print(f"Error: {e}")
    return ""
 
def main(): 
user_input=“is it working” 
result = complete(user_input) 
print(result)
if name  == “main ”: 
main()
             
            
               
               
              1 Like 
            
            
           
          
            
            
              I don’t know much about LM Studio, but I found a case study of a similar error.
  
  
    
  
  
    
    
      
        opened 04:35AM - 15 Jul 24 UTC 
      
        
          closed 04:06PM - 29 Aug 24 UTC 
        
      
     
    
    
   
 
  
    Hi, I tried to use local LLM with lm-studio but it returned me as connection err… or. My sample code is modified from 
https://github.com/zou-group/textgrad/blob/main/textgrad/engine/local_model_openai_api.py
First, it seems that the example code does not work, because prompt is not an argument, but content, for ChatExternalClient.
For the code:
```python
        from openai import OpenAI
        from textgrad.engine.local_model_openai_api import ChatExternalClient
        client = OpenAI(base_url="http://localhost:1234/v1", api_key="lm-studio")
        engine = ChatExternalClient(client=client, model_string="your-model-name")
        print(engine.generate(max_tokens=40, prompt="What is the meaning of life?"))
        ```
I met such an error:
```
st_to, options, remaining_retries, stream, stream_cls)
   1011     log.debug("Raising connection error")
-> 1012     raise APIConnectionError(request=request) from err
   1014 log.debug(
   1015     'HTTP Response: %s %s "%i %s" %s',
   1016     request.method,
   (...)
   1020     response.headers,
   1021 )
APIConnectionError: Connection error.
```
Does this mean I cannot create a client from local machine? Thanks.