# Example

## HTTP

Create HTTP APIs that respond to prediction requests in real-time.

### Implement

```bash
mkdir text-generator && cd text-generator
touch predictor.py requirements.txt text_generator.yaml
```

```python
# predictor.py

from transformers import pipeline

class PythonPredictor:
    def __init__(self, config):
        self.model = pipeline(task="text-generation")

    def predict(self, payload):
        return self.model(payload["text"])[0]
```

```python
# requirements.txt

transformers
torch
```

```yaml
# text_generator.yaml

- name: text-generator
  kind: RealtimeAPI
  predictor:
    type: python
    path: predictor.py
  compute:
    gpu: 1
```

### Deploy

```bash
cortex deploy text_generator.yaml
```

### Monitor

```bash
cortex get text-generator --watch
```

### Stream logs

```bash
cortex logs text-generator
```

### Make a request

```bash
curl http://***.elb.us-west-2.amazonaws.com/text-generator -X POST -H "Content-Type: application/json" -d '{"text": "hello world"}'
```

### Delete

```bash
cortex delete text-generator
```

## gRPC

To make the above API use gRPC as its protocol, make the following changes (the rest of the steps are the same):

### Add protobuf file

Create a `predictor.proto` file in your project's directory:

```
<!-- predictor.proto -->

syntax = "proto3";
package text_generator;

service Predictor {
    rpc Predict (Message) returns (Message);
}

message Message {
    string text = 1;
}
```

Set the `predictor.protobuf_path` field in the API spec to point to the `predictor.proto` file:

```yaml
# text_generator.yaml

- name: text-generator
  kind: RealtimeAPI
  predictor:
    type: python
    path: predictor.py
    protobuf_path: predictor.proto
  compute:
    gpu: 1
```

### Make a gRPC request

```bash
grpcurl -plaintext -proto predictor.proto -d '{"text": "hello-world"}' ***.elb.us-west-2.amazonaws.com:80 text_generator.Predictor/Predict
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.cortexlabs.com/0.32/workloads/realtime-apis/example.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.