Skip to main content

IAToolkit

Project description

IAToolkit

The Open-Source Framework for Building AI Chatbots on Your Private Data.

www.iatoolkit.com

IAToolkit is a comprehensive, Python open-source framework designed for building enterprise-grade AI chatbots and conversational applications. It bridges the gap between the power of Large Language Models (LLMs) and the valuable, private data locked within your organization's databases and documents.

With IAToolkit, you can build production-ready, context-aware chatbots and agents that can query relational databases, perform semantic searches on documents, and connect to your internal APIs in minutes.

Create secure, branded chat interfaces that can reason over your data, answer questions, and execute custom business logic, all powered by leading models from OpenAI, Google Gemini, and more.

🚀 Key Features

  • ⚙️ Configuration-First Architecture

    • Zero-Code Data Integration: Connect your databases with a simple YAML configuration—no coding required. Just declare your data sources, and IAToolkit handles the rest.
    • Declarative Setup: Define everything from database connections, embedding providers, custom tools, and UI branding in a single, intuitive company.yaml file.
  • 🔗 Unified Data Connection

    • Natural Language to SQL: Let your chatbot query relational databases (PostgreSQL, MySQL, SQLite) using everyday language.
    • Semantic Document Search (RAG): Automatically chunk, embed, and search across your private documents (PDFs, Word, etc.) to provide contextually accurate answers.
    • Flexible Embedding Options: Choose between OpenAI or HuggingFace embedding models. Switch providers with a single configuration change—no code modifications needed.
  • 🏢 Enterprise-Ready Multi-Tenancy

    • Deploy isolated "Company" modules, each with its own data sources, tools, context, and branding.
    • Perfect for SaaS products serving multiple clients or for managing different internal departments.
    • Each company gets its own configuration file, ensuring complete isolation and customization.
  • 🎨 Fully Brandable UI

    • Customize the look and feel for each "Company" with its own colors, logos, and even language settings (i18n).
    • Define your brand identity in YAML—from header colors to button styles.
    • Provides a white-labeled experience for your users with zero front-end coding.
  • 🧠 Multi-LLM by Design

    • Provider Agnostic: Switch between OpenAI (GPT-5) and Google (Gemini Pro, Gemini Flash) with a single configuration line.
    • Future-Proof: Easily add support for new LLM providers as they emerge.
    • Per-Company Configuration: Mix and match different LLM providers across companies based on cost, performance, or feature requirements.
  • 🛠️ Powerful Tool System

    • Define custom functions (tools) that your AI can invoke to perform actions—from database queries to API calls.
    • Declare tools in YAML with OpenAPI-style schemas.
    • Built-in support for common operations like sql query, excel export, sending mail with easy extensibility for custom business logic.
  • 🔒 Security & Observability Built-In

    • Integrated user authentication, API key management, and secure session handling out of the box.
    • Full traceability with detailed logging of all queries, function calls, token usage, and costs.
    • Production-ready security features including CORS configuration and environment-based secrets management.
  • 👨‍💻 Developer-First Experience

    • Built with a clean Dependency Injection architecture for maximum testability and maintainability.
    • High-quality codebase with 90%+ test coverage.
    • Comprehensive documentation and working examples to get you started quickly.

💡 Why IAToolkit?

Build in Minutes, Not Months: Traditional AI chatbot development requires months of infrastructure setup, security hardening, and complex integrations. IAToolkit provides all of this out-of-the-box, letting you focus on your business logic and user experience.

Configuration Over Code: Most AI frameworks force you to write extensive boilerplate code. With IAToolkit, you describe what you want in YAML, and the framework does the heavy lifting. Connect databases, configure embeddings, define tools—all declaratively.

Multi-Tenant by Design: Whether you're building a SaaS product for multiple clients or managing different departments within your organization, IAToolkit's Company architecture provides true isolation with shared infrastructure efficiency.

Production-Ready from Day One: No need to retrofit security, logging, or monitoring later. IAToolkit includes enterprise-grade features from the start, so you can deploy confidently.

📚 Documentation

For comprehensive guides, tutorials, and API references, visit our complete documentation:

➡️ Read the Full Documentation

⚡ Quick Start: Try our 'hello world' example

Ready to see it in action? Our Quickstart Guide will walk you through downloading, configuring, and launching your first AI assistant in just a few minutes. It's the best way to experience the toolkit's capabilities firsthand.

➡️ Get Started with the Quickstart Guide

🤝 Contributing

We welcome contributions! Whether it's adding a new feature, improving documentation, or fixing a bug, please feel free to open a pull request.

➡️ Contributing guide

📄 License

IAToolkit is open-source and licensed under the MIT License.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

iatoolkit-0.74.0.tar.gz (260.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

iatoolkit-0.74.0-py3-none-any.whl (307.3 kB view details)

Uploaded Python 3

File details

Details for the file iatoolkit-0.74.0.tar.gz.

File metadata

  • Download URL: iatoolkit-0.74.0.tar.gz
  • Upload date:
  • Size: 260.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for iatoolkit-0.74.0.tar.gz
Algorithm Hash digest
SHA256 8d6dc4d0632e39d2c7b0646ef0276f9d9e8e16ca3810d70128842ca7562f4207
MD5 391f319f4b66cc9a681d4380bf768846
BLAKE2b-256 538584fb04512eec40649e178e2891bb03bfd5194f38fb20fd57ee6e7e92b34f

See more details on using hashes here.

Provenance

The following attestation bundles were made for iatoolkit-0.74.0.tar.gz:

Publisher: publish.yml on flibedinsky/iatoolkit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file iatoolkit-0.74.0-py3-none-any.whl.

File metadata

  • Download URL: iatoolkit-0.74.0-py3-none-any.whl
  • Upload date:
  • Size: 307.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for iatoolkit-0.74.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e37f5339274d0be4443c4e4bc93e5aee1389aba6f72576ab67a97a65195de330
MD5 b84285900a06b18511a32038844bfa78
BLAKE2b-256 e4afbbc7192b88db5e50d0342f6baf8cf3aa99b42f0b0f67365453dd2f325907

See more details on using hashes here.

Provenance

The following attestation bundles were made for iatoolkit-0.74.0-py3-none-any.whl:

Publisher: publish.yml on flibedinsky/iatoolkit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page