> ## Documentation Index
> Fetch the complete documentation index at: https://docs.slai.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Deploying an ML Model

> A short tutorial on building a sentiment analysis model and deploying it as a REST API with Beam

### Define the environment

The first thing we'll do is define the environment that our app will run on. For
this example, we're building a Sentiment Analysis model using Huggingface.

First, create a file with your Beam App definition. You can name this whatever
you want. In this example, we'll call it `app.py`.

```python app.py theme={null}
import beam

app = beam.App(
    name="sentiment-analysis-app",
    cpu=4,
    memory="4Gi",
    gpu=0,
    python_version="python3.8",
    python_packages=["transformers", "torch", "numpy"],
)
```

### Invoking the Huggingface Model

Now, we'll write some code to predict the sentiment of a given text prompt.
Create a new file. Again, you can name this whatever you want. We'll name ours
`inference.py`

Our function takes keyword arguments, as `(**inputs)`.

```python inference.py theme={null}
from transformers import pipeline

def predict_sentiment(**inputs):
    model = pipeline(
        "sentiment-analysis", model="siebert/sentiment-roberta-large-english"
    )
    result = model(inputs["text"], truncation=True, top_k=1)
    prediction = {i["label"]: i["score"] for i in result}

    print(prediction)

    return {"prediction": prediction}
```

### Setting a REST API Trigger

To deploy the API, we'll create a REST API **Trigger** in our `app.py`.

Our trigger requires three things:

* **Inputs -** *the name and type of all* ***inputs*** *to the API*

* **Outputs** - *the name and type of all* ***outputs*** *returned from the
  API*

* **Handler** - *the file and function to be invoked when the API is called*

Add the following lines to your `app.py` file:

```python app.py theme={null}
app.Trigger.RestAPI(
    inputs={"text": beam.Types.String()},
    outputs={"prediction": beam.Types.String()},
    handler="inference.py:predict_sentiment",
)
```

### (Optional) Caching Model on Disk

For performance reasons, you want to store the model on disk rather than downloading it from HuggingFace for each request.

Create a **[Persistent Volume](/beam/data/persistent-volumes)** to store the model weights.

Add the following lines to your `app.py`:

```python app.py theme={null}
app.Mount.PersistentVolume(app_path="./cached_models", name="cached_model")
os.environ["TRANSFORMERS_CACHE"] = "/workspace/cached_models"
```

The complete `app.py` file will look like this:

```python app.py theme={null}
import os
import beam

app = beam.App(
    name="sentiment-analysis",
    cpu=4,
    memory="4Gi",
    gpu=0,
    python_version="python3.9",
    python_packages=["transformers", "torch"],
)

app.Trigger.RestAPI(
    inputs={"text": beam.Types.String()},
    outputs={"prediction": beam.Types.String()},
    handler="inference.py:predict_sentiment",
)

app.Mount.PersistentVolume(app_path="./cached_models", name="cached_model")
os.environ["TRANSFORMERS_CACHE"] = "/workspace/cached_models"
```

### Deploying the app

To deploy the model, enter your terminal and `cd` to the directory you're
working on.

Then, run the following:

```
beam deploy app.py
```

Once you deploy, you'll see the following console output:

<img src="https://mintcdn.com/slai-docs/0GTBstnyDK-8Z9OV/img/beam/getting-started/call-api.png?fit=max&auto=format&n=0GTBstnyDK-8Z9OV&q=85&s=fc5ee9c2e9a6e55b65693435cad5e0fa" alt="" width="1017" height="500" data-path="img/beam/getting-started/call-api.png" />

At the bottom of the console, you'll see a URL for invoking your function.
Here's what a cURL request would look like:

```bash theme={null}
  curl -X POST --compressed "https://beam.slai.io/kajru" \
   -H 'Accept: */*' \
   -H 'Accept-Encoding: gzip, deflate' \
   -H 'Authorization: Basic YWJmNWVhYjhjY2VkZTQ3ZDJmZWU4NTYyNTliYWU3NDA6ZTE0ZTE0MTY0M2NmYzkxNDdkMDM1MzZkNDdjYzRkMGI=' \
   -H 'Connection: keep-alive' \
   -H 'Content-Type: application/json' \
   -d '{"text": "If we override the bandwidth, we can get to the SMTP capacitor through the cross-platform RSS alarm!"}'
```

<Note>
  **The requests are authenticated with basic auth.** Your username is your ClientID, and password is your Client Secret.
</Note>

Congrats - you just deployed your first function on Beam!