# Using only Rasa NLU in Python3.8 Script

**URL:** <https://forum.rasa.com/t/using-only-rasa-nlu-in-python3-8-script/54275>\
**Category:** Rasa Open Source\
**Created:** [July 12, 2022, 2:15pm UTC](https://forum.rasa.com/t/using-only-rasa-nlu-in-python3-8-script/54275 "2022-07-12T14:15:24Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![0815idiot](https://avatars.discourse-cdn.com/v4/letter/0/ba9def/32.png) [@0815idiot](https://forum.rasa.com/u/0815idiot)\
**Post date:** [July 17, 2022, 12:07pm UTC](https://forum.rasa.com/t/using-only-rasa-nlu-in-python3-8-script/54275/2 "2022-07-17T12:07:08Z")

</div>

I got it working with the following example code:

```auto
#!/bin/bash
rasa train nlu --config config.yml --nlu nlu.yml --out ./ --fixed-model-name rasaModel

```

and

```auto
#python3
from rasa.core.agent import Agent
import asyncio
import json

model_path = "rasaModel.tar.gz"
agent = Agent.load(model_path)

print("NLU model loaded. Type a message and press enter to parse it.")
while True:
    print("Next message:")
    try:
        message = input().strip()
    except (EOFError, KeyboardInterrupt):
        print("Wrapping up command line chat...")
        break

    result = asyncio.run(agent.parse_message(message))
    print(json.dumps(result, indent=2))

```

---

_[View the full topic](https://forum.rasa.com/t/using-only-rasa-nlu-in-python3-8-script/54275)._