Skip to main content

ABOV3 Python SDK - Genesis CodeForger Edition

PyPI version Python versions Documentation

The official Python SDK for ABOV3 AI - Genesis CodeForger Edition.

Official Website: https://www.abov3.ai ABOV3 Team: https://www.abov3.com

Installation

pip install abov3-ai

Quick Start

from abov3 import Abov3Client

# Initialize the client
client = Abov3Client(
    api_key="your-api-key",
    base_url="https://api.abov3.ai"  # Optional, defaults to production
)

# Create a session
session = await client.sessions.create(
    model="claude-3-opus",
    system_prompt="You are a helpful coding assistant"
)

# Send a message
response = await client.messages.create(
    session_id=session.id,
    content="Write a Python function to calculate fibonacci numbers"
)

print(response.content)

What's New in v0.1.9

Repository Migration

  • Migrated from personal repository to official ABOV3AI organization
  • Updated all documentation URLs to point to https://www.abov3.ai/docs
  • Improved publishing workflow with GitHub Actions

Previous Updates (v0.1.4)

TUI Configuration Management

The TUI now includes comprehensive configuration management commands:

  • Interactive configuration dialogs with form inputs
  • Provider management (add, edit, enable/disable, remove)
  • MCP server configuration
  • System health checks and validation
  • Scrollable configuration viewer

Features Update

  • Real-time configuration updates
  • Form-based input for adding providers and MCP servers
  • Health diagnostics with config doctor command
  • Configuration validation with detailed error reporting

Features

  • 🚀 Full API Coverage - Complete access to all ABOV3 AI capabilities
  • 🔒 Type Safety - Full type hints and runtime validation with Pydantic
  • ⚡ Async Support - Built on httpx for high-performance async operations
  • 🔄 Auto Retry - Automatic retry with exponential backoff
  • 📊 Streaming - Support for streaming responses
  • 🔧 Configuration API - Manage ABOV3 configurations programmatically (v0.1.1+)
  • 🧪 Well Tested - Comprehensive test coverage

Streaming Responses

async with client.messages.stream(
    session_id=session.id,
    content="Generate a long story"
) as stream:
    async for chunk in stream:
        print(chunk.content, end="")

Error Handling

from abov3.exceptions import Abov3Error, RateLimitError

try:
    response = await client.messages.create(...)
except RateLimitError as e:
    print(f"Rate limited: {e}")
    # Wait and retry
except Abov3Error as e:
    print(f"API error: {e}")

Configuration

Environment Variables

export ABOV3_API_KEY="your-api-key"
export ABOV3_BASE_URL="https://api.abov3.ai"  # Optional

Code Configuration

client = Abov3Client(
    api_key="your-api-key",
    timeout=30.0,  # Request timeout in seconds
    max_retries=3,  # Maximum retry attempts
    proxy="http://proxy.example.com:8080"  # Optional proxy
)

Available Models

  • claude-3-opus - Most capable model for complex tasks
  • claude-3-sonnet - Balanced performance and speed
  • gpt-4-turbo - OpenAI's most capable model
  • gpt-3.5-turbo - Fast and cost-effective

API Reference

Sessions

# Create a session
session = await client.sessions.create(model="claude-3-opus")

# Get session
session = await client.sessions.get(session_id)

# List sessions
sessions = await client.sessions.list(limit=10)

# Delete session
await client.sessions.delete(session_id)

Messages

# Send message
message = await client.messages.create(
    session_id=session_id,
    content="Your message here"
)

# Stream message
async with client.messages.stream(...) as stream:
    async for chunk in stream:
        process(chunk)

Files

# Upload file
file = await client.files.upload(
    file_path="./document.pdf",
    purpose="analysis"
)

# List files
files = await client.files.list()

# Delete file
await client.files.delete(file_id)

Development

Setup Development Environment

# Clone the repository
git clone https://github.com/ABOV3AI/abov3-sdk-python.git
cd abov3-sdk-python

# Install development dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Format code
black src tests
ruff check src tests

# Type checking
mypy src

Support

License

MIT License - see LICENSE file for details.

About ABOV3

ABOV3 AI is an advanced code generation framework that revolutionizes how developers interact with AI. Visit abov3.ai to learn more.

Metadata

Release files for abov3-ai 0.1.12

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for abov3-ai 0.1.12
File Size Uploaded Provenance
abov3_ai-0.1.12.tar.gz 7.7 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for abov3-ai 0.1.12
File Interpreter ABI Platform
abov3_ai-0.1.12-py3-none-any.whl Python 3 none any Details

Total release size: 16.6 kB

Release files / abov3_ai-0.1.12.tar.gz

Download URL abov3_ai-0.1.12.tar.gz
Size 7.7 kB
Tags Source
SHA-256 checksum
How to use checksums
9968483ea8a2da14a8ea5d4b0c6ae09a7d725827e2b0392bf11ef74ffc7cea26
BLAKE2b-256 checksum
How to use checksums
89b3da6ad8238e91139f8039c5e57c4fa135590d17ab1317088a7b729b0fd0fa
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.13.7

Release files / abov3_ai-0.1.12-py3-none-any.whl

Download URL abov3_ai-0.1.12-py3-none-any.whl
Size 8.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
88ead0c469e50629179aae396151237566fd80f38d1754dd56332640aae31ce6
BLAKE2b-256 checksum
How to use checksums
c1f67979bd5e1fc5391ed5665515d4f4bb1d1e96d942e5c1c3247b701028cb56
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.13.7

Security for abov3-ai 0.1.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page