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

  • 🔗 Unified Data Connection

    • Natural Language to SQL: Let your chatbot query relational databases (PostgreSQL, MySQL, SQLite) using everyday language.
    • Semantic Document Search: Automatically chunk, embed, and search across your private documents (PDFs, Word, etc.) to provide contextually accurate answers.
  • 🏢 Enterprise-Ready Multi-Tenancy

    • Deploy isolated "Company" modules, each with its own data, tools, and context.
    • Perfect for SaaS products or internal departmental agents.
  • 🎨 Fully Brandable UI

    • Customize the look and feel for each "Company" with its own logos, colors, and even language settings (i18n).
    • Provides a white-labeled experience for your users.
  • 🧠 LLM Agnostic

    • Switch between OpenAI (GPT-*) and Google (Gemini-*) with a single line change in your configuration.
    • No code refactoring needed.
  • 🛠️ Developer-First Experience

    • Built with a clean Dependency Injection architecture.
    • High-quality code base with 90%+ test coverage.
  • 🔒 Security & Observability Built-In

    • Comes with integrated user authentication, API keys, and secure session handling out of the box.
    • Full traceability with detailed logging of all queries, function calls, token usage, and costs.

⚡ 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.

🤝 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.

📄 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-0.71.1.tar.gz (254.2 kB view details)

Uploaded Source

Built Distribution

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

iatoolkit-0.71.1-py3-none-any.whl (303.0 kB view details)

Uploaded Python 3

File details

Details for the file iatoolkit-0.71.1.tar.gz.

File metadata

  • Download URL: iatoolkit-0.71.1.tar.gz
  • Upload date:
  • Size: 254.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for iatoolkit-0.71.1.tar.gz
Algorithm Hash digest
SHA256 63e2cbce4d33dd0f3a8b07751231228e420ec8575296f157198411424b411daf
MD5 437f51422b261513a8caeeb9919c9811
BLAKE2b-256 37bac82d70b98ab54ed444857dd08f207e105a58b27c7ce631c69cd2ba47b531

See more details on using hashes here.

Provenance

The following attestation bundles were made for iatoolkit-0.71.1.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-0.71.1-py3-none-any.whl.

File metadata

  • Download URL: iatoolkit-0.71.1-py3-none-any.whl
  • Upload date:
  • Size: 303.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for iatoolkit-0.71.1-py3-none-any.whl
Algorithm Hash digest
SHA256 69cf4a10304b76151a886a05516c421c2dfa4edc783ab721d94fa01f04567c8c
MD5 a31ff391c6b046a3208cf846b32fa1f6
BLAKE2b-256 0284b766fc1d11f4fc26d68d17ff2418f1a195683722c0b33e563d545a754af7

See more details on using hashes here.

Provenance

The following attestation bundles were made for iatoolkit-0.71.1-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