premai 0.0.2

The Prem Python SDK is a Python library for interacting with [premai-saas](app.premai.io)

🚀 Prem Python SDK

The Prem Python SDK is a Python library for interacting with the Prem API

Table of Contents

1. Installation
2. Usage
1. Getting Started
2. Completions
3. Embeddings
4. DataPoints

Installation

From Source

1. Clone the Prem Python SDK repository:

   git clone https://github.com/premAI-io/prem-python-sdk.git
   

2. Install the SDK

   cd prem-python-sdk
   python -m venv venv
   source venv/bin/activate
   pip install .
   

From PyPI

You can also install the Prem Python SDK directly from PyPI.

python -m venv venv
source venv/bin/activate
pip install premai

Usage

Getting Started

To use the Prem Python SDK, you need to obtain an API key from the Prem platform. You can then create a Prem instance to make requests to the API.

from prem import Prem

api_key = "YOUR_API_KEY"
base_url = "https://api.prem.com"  # Update with the base URL of the Prem API

client = Prem(api_key=api_key, base_url=base_url)

Completions

The completions module allows you to generate completions based on user input. Here's an example:

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who won the world series in 2020?"},
]
model = "gpt-3.5-turbo"

# Create completion
response = client.completions.create(project_id=1, messages=messages, model=model, stream=False)
print(response)

Embeddings

The embeddings module enables you to create embeddings for given input. Example:

input_text = "What is a transformer?"
model = "text-embedding-ada-002"

# Create embeddings
response = client.embeddings.create(project_id=1, input=input_text, model=model)
print(response)

Data Points

The datapoints module allows you to manage data points, including creating, updating, retrieving, and deleting. Example:

input_text = "What is a transformer?"
output_text = "A transformer is a deep learning model that uses self-attention."

# Create 10 data points
for _ in range(10):
    data_point = client.datapoints.create(project_id=1, input=input_text, output=output_text, positive=True)

# Update the last data point
patched_data_point = client.datapoints.update(datapoint_id=data_point.id, data={"positive": False})

# Retrieve the updated data point
print(client.datapoints.retrieve(datapoint_id=data_point.id))

# Delete the updated data point
client.datapoints.delete(datapoint_id=data_point.id)

# List all data points
datapoints = client.datapoints.list(project_id=1)
print("Total number of datapoints:", len(datapoints))
for datapoint in datapoints:
    print("Deleted data point with ID:", datapoint.id)
    client.datapoints.delete(datapoint_id=datapoint.id)