artifex 0.3.0

Create your private AI model with no training data or GPUs 🤖🚀.

Documentation · Tutorial

💸 Cut chatbot costs by up to 40% • 📊 No training data needed • 🌱 No GPU needed

Artifex is a Python library that generates small, fast, task-specific AI models (e.g. intent classifiers, guardrails, text-to-SQL converters...) that you can run locally — without any training data or GPU required.

It can be used to reduce chatbot costs by up to 40%, by offloading common tasks, especially guardrails, to small models that you can run locally on CPU, instead of relying on expensive APIs.

🔥 Features

• 💸 Cut chatbot costs by 40%: Offload chatbot tasks to local models and reduce the number of paid API calls.
• 📊 No training data needed: Uses smart prompting and synthetic generation under the hood.
• 🌱 No GPU needed: All models are designed to run efficiently on CPU.
• 🔒 Keep ownership of your models: Keep exclusive ownership of the models you generate.
• 🔧 Prebuilt templates for common tasks:
  • Guardrail
  • Intent Classifier
  • More coming soon! Suggest a task or vote one up

🚀 Quick Start

Install with pip:

pip install artifex

from artifex import Artifex

guardrail = Artifex().guardrail

guardrail.train(
    instructions=[
        "Soft medical advice is allowed, but it should be general and not specific to any individual.",
        "Anything that is about cosmetic products, including available products or their usage, is allowed.",
        "Anything else, including hard medical advice, is not allowed under any circumstances.",
    ]
)

print(guardrail("Take 500mg of vitamin C daily to boost your immune system during cold season."))
# ➜ "unsafe"

🧰 Supported Tasks (more coming soon) — suggest one or vote one up

We continue to add new models to Artifex, so stay tuned for updates! Currently, you can generate the following models:

• 🛡️ Chatbot Guardrail: Flags unsafe, harmful, or off-topic messages.
• 🗂️ Intent Classifier: Maps text to intents, such as "product_inquiry", "send_email"...
• 📝 Got Suggestions? If there is a specific task you'd like to perform with Artifex, write it in the discussion or vote up any suggestion

🧪 Examples

🛡️ Guardrail Example — try the tutorial:

from artifex import Artifex

guardrail = Artifex().guardrail

guardrail.train(
    instructions=[
        "Soft medical advice is allowed, but it should be general and not specific to any individual.",
        "Anything that is about cosmetic products, including available products or their usage, is allowed.",
        "Anything else, including hard medical advice, is not allowed under any circumstances.",
    ]
)

# Hard medical advice, should be classified as unsafe
print(guardrail("Take 500mg of vitamin C daily to boost your immune system during cold season."))
# ➜ "unsafe"

# Cosmetic product usage, should be classified as safe
print(guardrail("This facial scrub exfoliates the skin, removing dead skin cells."))
# ➜ "safe"

🗂️ Intent Classifier Example — try the tutorial:

from artifex import Artifex

intent_classifier = Artifex().intent_classifier

intent_classifier.train(
    classes={
        "send_email": "Intent to send an email to someone",
        "reply_email": "Intent to reply to an email that was received",
        "schedule_meeting": "Intent to schedule a meeting with someone",
        "cancel_meeting": "Intent to cancel a meeting which was previously scheduled",
        "reschedule_meeting": "Intent to reschedule a meeting which was previously scheduled",
    }
)

print(intent_classifier("I need to set up a meeting with Sarah to discuss the upcoming delivery. Can you help me do that?"))
# ➜ "schedule_meeting"

print(intent_classifier("I fell ill and I'll have to cancel my meeting with the team. Please go ahead and do it for me."))
# ➜ "cancel_meeting"

print(intent_classifier("I fell ill and I'll have to postpone my meeting with the team. Please go ahead and do it for me."))
# ➜ "reschedule_meeting"

🧩 Plug-and-Play Deployment

• Integrate with FastAPI, Flask, Streamlit, or Gradio
• No external dependencies on OpenAI or GPU runtimes

🤝 Contributing

Contributions welcome! Whether it's a new task module, improvement, or bug fix — we’d love your help. Not ready to contribute code? You can also help by suggesting a new task or voting up any suggestion.

git clone https://github.com/tanaos/artifex.git
cd artifex
pip install -e .

🔗 Tutorials & Demos

Guardrail Model

1. Tutorial — create a Guardrail Model with Artifex
2. Demo — try a Guardrail Model trained with Artifex
3. HF page — see a Guardrail Model trained with Artifex

Intent Classifier Model

1. Tutorial — create an Intent Classifier Model with Artifex

📚 Documentation & Support

• Full documentation: https://docs.tanaos.com/artifex
• Contact: [e-mail]