# Error connecting to lm studio
**URL:**
**Author:**  [@oasf2012](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Foasf2012)%5C
**Post date:** [February 9, 2025, 2:33am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ferror-connecting-to-lm-studio%2F139792%2F1 "2025-02-09T02:33:41Z")
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](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()
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [February 9, 2025, 8:50am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ferror-connecting-to-lm-studio%2F139792%2F2 "2025-02-09T08:50:03Z")
I don’t know much about LM Studio, but I found a case study of a similar error.
>
>
> 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.
---
**Author:**  [@bayerth](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fbayerth)%5C
**Post date:** [February 12, 2026, 9:12am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ferror-connecting-to-lm-studio%2F139792%2F3 "2026-02-12T09:12:33Z")
Try it by using OpenAI client:
```auto
from openai import OpenAI
client = OpenAI(
base_url="http://localhost:1234/v1",
api_key="if necessary "
)
message = [{"role": "user", "content": "Hello"}]
response = client.chat.completions.create(
temperature=1,
messages=message,
model="qwen/qwen3-4b-2507",
seed=42
)
print(response.choices[0].message.content)
```