Metadata-Version: 2.1
Name: inferless
Version: 0.1.5
Summary: 
Author: Inferless
Requires-Python: >=3.8,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: requests (>=2.31.0,<3.0.0)
Description-Content-Type: text/markdown

# Python Client to call Inferless API

## Installation
```console
$ pip install inferless
```

## Usage
This client can be used to call Inferless API from your python code. It supports both synchronous and asynchronous calls.
### Constants
Fetch the URL and API_KEY from the Inferless console https://console-dev.inferless.com/
```python
URL = "<url>"
API_KEY = "<api_key>"
data = { "inputs" : 
          [
              {
                "name": "prompt",
                "shape": [
                  1
                ],
                "datatype": "BYTES",
                "data": [
                  "Once upon a time"
                ]
              }
          ]
        }
```

### Synchrounous call
An example to call Inferless API synchronously
```python
import inferless
import datetime
def main():
    t1 = datetime.datetime.now()
    data = inferless.call(URL, API_KEY, data)
    t2 = datetime.datetime.now()
    print(f"time taken: {t2-t1}")

main()
```
Output
```console
time taken: 0:00:05.218835
```
For a particular url, the synchronous call took approximately 5 seconds to complete.

### Parallel call with callback
This library also supports parallel calls to Inferless API. The following example shows how to call Inferless API in parallel with a callback function.
```python
import inferless
import datetime

def callback_func(e, response):
    # e is the error object
    # response is the response object
    with open("response.json", "w") as f:
        f.write(json.dumps(response))
    

t1 = datetime.now()
inferless.parallel_call(URL, KEY, DATA, callback_func)
t2 = datetime.now()
print(t2 - t1)
```
Output
```console
time taken: 0:00:00.000141
```
It can be seen that the program exits without waiting for the response. The response is written to a file by the callback function after it is received.

