​
Installation

Install the latest version of the Praxos Python SDK: 
pip install -U praxos-python
Current Version: 0.3.2+ Python Compatibility: Python 3.8+ Dependencies: pydantic, httpx For development installation from source: 
git clone https://github.com/praxos/praxos-python
cd praxos-python
pip install -e .

​
Getting Started

To start using the Praxos client, you’ll need to initialize it with your API key: 
from praxos_python import SyncClient

client = SyncClient(api_key="your-api-key")

​
Configuration Options

The client accepts several configuration options:
  • api_key (required): Your Praxos API key
  • base_url (optional): Custom base URL for the API (default: “https://api.praxos.ai/”)
  • params (optional): Additional query parameters to include in all requests
  • timeout (optional): Request timeout in seconds (default: 10.0)
# Advanced client configuration
client = SyncClient(
    api_key="prx_your_api_key_here",
    base_url="https://api.praxos.ai/",
    timeout=30.0,
    params={"version": "v1"}  # Optional global parameters
)

​
API Key Validation

The client includes built-in API key validation: 
# Validate your API key
try:
    is_valid = client.validate_api_key()
    print(f"API key is valid: {is_valid}")
except APIKeyInvalidError:
    print("Invalid API key - please check your credentials")

​
Environment Management

​
Creating an Environment

# Create a new environment
environment = client.create_environment(name="my-environment")

# Create an environment with description and ontologies
environment = client.create_environment(
    name="my-environment",
    description="Environment for processing customer data",
    ontologies=["customer-ontology-id"]  # List of ontology IDs or SyncOntology objects
)

​
Retrieving Environments

# Get all environments
environments = client.get_environments()

# Get a specific environment by ID
environment = client.get_environment(id="env-123")

# Get a specific environment by name
environment = client.get_environment(name="my-environment")

​
Ontology Management

Ontologies define the structure and types of data that your environment can process. They use Pydantic models to define schemas for entity extraction and validation.

​
Creating an Ontology

from pydantic import BaseModel, Field
from typing import Optional

# Define your data schemas using Pydantic models
class Person(BaseModel):
    name: str = Field(description="Full name of the person")
    age: Optional[int] = Field(description="Age in years")
    email: Optional[str] = Field(description="Email address")

class Organization(BaseModel):
    name: str = Field(description="Organization name")
    industry: Optional[str] = Field(description="Industry sector")
    employees: Optional[int] = Field(description="Number of employees")

# Create an ontology with multiple schemas
ontology = client.create_ontology(
    name="business-ontology",
    description="Ontology for business entities",
    schemas=[Person, Organization]
)

​
Retrieving Ontologies

# Get all ontologies
ontologies = client.get_ontologies()

# Get a specific ontology by ID
ontology = client.get_ontology(id="onto-123")

# Get a specific ontology by name
ontology = client.get_ontology(name="business-ontology")

​
Error Handling

The client includes built-in error handling for common API issues:
  • APIError: General API errors
  • APIKeyInvalidError: Invalid API key errors
Example error handling: 
from praxos_python.exceptions import APIError, APIKeyInvalidError

try:
    environment = client.create_environment(name="my-environment")
except APIKeyInvalidError:
    print("Invalid API key")
except APIError as e:
    print(f"API error: {e.message}")

​
Additional Imports

The SDK provides several model classes and utilities that you can import: 
from praxos_python import (
    SyncClient,
    SyncEnvironment, 
    SyncSource,
    SyncOntology,
    APIError
)

# For message handling in conversations
from praxos_python.types import Message

# For search result handling
from praxos_python.models import Context

​
Resource Management

The client implements Python’s context manager protocol, allowing you to use it with the with statement: 
with SyncClient(api_key="your-api-key") as client:
    environment = client.create_environment(name="my-environment")
    # Client will be automatically closed when exiting the context