smolmodels ✨
Build machine learning models using natural language and minimal code
Quickstart | Features | Installation | Documentation | Benchmarks
smolmodels lets you create machine learning models by describing them in plain language. Simply explain what you want, and the AI-powered system builds a fully functional model through an automated agentic approach.
1. Quickstart
Installation
pip install smolmodels
Two Ways to Use smolmodels
A. Interactive Chat Interface
Launch the interactive chat interface to build models through conversational AI:
# Start the chat interface
smolmodels
This opens a Gradio UI where you can describe your model, upload datasets, and get explanations throughout the process.
B. Library API
import smolmodels as sm
# Define the model
model = sm.Model(
intent="Predict sentiment from news articles",
input_schema={"headline": str, "content": str},
output_schema={"sentiment": str}
)
# Build and train the model
model.build(
datasets=[your_dataset],
provider="openai/gpt-4o-mini",
max_iterations=10
)
# Use the model
prediction = model.predict({
"headline": "New breakthrough in renewable energy",
"content": "Scientists announced a major advancement..."
})
# Save for later use
sm.save_model(model, "sentiment-model")
loaded_model = sm.load_model("sentiment-model.tar.gz")
2. Features
2.1. 💬 Natural Language Model Definition
Define models using plain English descriptions:
model = sm.Model(
intent="Predict housing prices based on features like size, location, etc.",
input_schema={"square_feet": int, "bedrooms": int, "location": str},
output_schema={"price": float}
)
2.2. 🤖 Multi-Agent Architecture
The system uses a team of specialized AI agents to:
- Analyze your requirements and data
- Plan the optimal model solution
- Generate and improve model code
- Test and evaluate performance
- Package the model for deployment
2.3. 🎯 Automated Model Building
Build complete models with a single method call:
model.build(
datasets=[dataset],
provider="openai/gpt-4o-mini", # LLM provider
max_iterations=10, # Max solutions to explore
timeout=1800 # Optional time limit in seconds
)
2.4. 🎲 Data Generation & Schema Inference
Generate synthetic data or infer schemas automatically:
# Generate synthetic data
dataset = sm.DatasetGenerator(
schema={"features": str, "target": int}
)
dataset.generate(500) # Generate 500 samples
# Infer schema from intent
model = sm.Model(intent="Predict customer churn based on usage patterns")
model.build(provider="openai/gpt-4o-mini") # Schema inferred automatically
2.5. 🌐 Multi-Provider Support
Use your preferred LLM provider:
model.build(provider="openai/gpt-4o-mini") # OpenAI
model.build(provider="anthropic/claude-3-opus") # Anthropic
model.build(provider="google/gemini-1.5-pro") # Google
3. Installation
3.1. Installation Options
pip install smolmodels # Standard installation
pip install smolmodels[lightweight] # Minimal dependencies
pip install smolmodels[all] # With deep learning support
3.2. API Keys
# Set your preferred provider's API key
export OPENAI_API_KEY=<your-key>
export ANTHROPIC_API_KEY=<your-key>
export GEMINI_API_KEY=<your-key>
3.3. Command Line Interface
# Build a model
smolmodels build --intent "Predict customer churn" \
--dataset customer_data.csv \
--provider openai/gpt-4o-mini \
--output churn_model.tar.gz
# Make predictions
smolmodels predict churn_model.tar.gz --input-values usage=high spend=1200 tenure=24
# Show model details
smolmodels info churn_model.tar.gz
4. Documentation
For full documentation, visit docs.plexe.ai.
5. Benchmarks
Evaluated on 20 OpenML benchmarks and 12 Kaggle competitions, showing higher performance in 12/20 datasets. Full results at plexe-ai/plexe-results.
6. Docker Deployment
Deploy as a platform with API and web UI:
git clone https://github.com/plexe-ai/smolmodels.git
cd smolmodels/docker
cp .env.example .env # Add your API key
docker-compose up -d
Access at:
- API: http://localhost:8000
- Web UI: http://localhost:8501
7. Contributing
See CONTRIBUTING.md for guidelines. Join our Discord to connect with the team.
8. License
1 maintainer
Metadata
1 maintainer
Release files for smolmodels 0.15.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| smolmodels-0.15.0.tar.gz | 86.7 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| smolmodels-0.15.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 219.5 kB
Release files / smolmodels-0.15.0.tar.gz
| Download URL | smolmodels-0.15.0.tar.gz |
|---|---|
| Size | 86.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ade8a6fd89c2e354e529a7971792c9a40485c36747bac22eced230642d8e656e
|
|
BLAKE2b-256 checksum How to use checksums |
0efcee71ae8e8ee32a74f41ed067509ccc588d360b9a28a2c9c96ef5a3706c7a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.1.2 CPython/3.12.10 Linux/6.8.0-1021-azure
|
Release files / smolmodels-0.15.0-py3-none-any.whl
| Download URL | smolmodels-0.15.0-py3-none-any.whl |
|---|---|
| Size | 132.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c0df72053fa3553b43e7fa7142f2caa3bfb330480fbc43c9da701c193ff61a7f
|
|
BLAKE2b-256 checksum How to use checksums |
8d3feb5b67d1b9772834ff7ab6a6c75004c5cde8c17f4ce772109697314087b0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.1.2 CPython/3.12.10 Linux/6.8.0-1021-azure
|
Security for smolmodels 0.15.0
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.
