justembed 0.1.0a1

A semantic engine that just works - offline-first semantic search for everyday laptops

JustEmbed

A semantic engine that just works.

Offline-first semantic search for everyday laptops.

---

⚠️ Alpha Release

This is v0.1.0a1

Full functionality coming in v0.1.0 (expected: February 2026).

---

What is JustEmbed?

JustEmbed is an offline-first semantic search library designed for everyday laptops. No cloud. No API keys. No telemetry. Just embed your documents and search.

Philosophy

• One model only: multilingual-e5-small (100+ languages)
• Offline-first: Zero network dependencies
• Just works: No configuration, no choices, no surprises
• Hardware-aware: Automatic limits based on your laptop
• Privacy-first: Everything stays on your machine

---

Planned Features (v0.1.0)

import justembed as je

# Load documents
je.load("docs/")

# Generate embeddings
je.embed()

# Search semantically
results = je.search("fruits that are red in color")

# Check status
je.status()

Core Features

• ✅ Single model (multilingual-e5-small.onnx)
• ✅ Offline-first (zero network dependencies)
• ✅ Python 3.8+ support
• ✅ Polars-based storage (Parquet files)
• ✅ Hardware-aware limits (2-3s soft, 10s hard)
• ✅ Text-only input
• ✅ Simple API (5 functions)

---

Installation

pip install justembed

Note: v0.1.0a1 is a placeholder release. Full functionality coming soon!

---

Requirements

• Python 3.8+
• ~340MB disk space (model + dependencies)
• 4GB+ RAM recommended

---

Dependencies

• onnxruntime - ONNX inference
• tokenizers - Tokenization (standalone, not transformers!)
• numpy - Array operations
• polars - DataFrame operations
• pyarrow - Parquet I/O
• psutil - Hardware detection

No pandas. No transformers. No network dependencies.

---

Roadmap

v0.1.0a1 (Current) - Name Reservation

• ✅ Package name locked on PyPI
• ✅ Basic structure
• ⏳ Placeholder functions

v0.1.0 (February 2026) - First Release

• ⏳ Full implementation
• ⏳ Working examples
• ⏳ Documentation
• ⏳ Tests

v0.2.0 (Future)

• ⏳ Query caching
• ⏳ Batch operations
• ⏳ Advanced search options

---

Why "JustEmbed"?

Because that's all you need to do:

1. Just embed your documents
2. Just search with natural language
3. Just works - no configuration needed

---

Design Decisions

One Model Only

We use multilingual-e5-small.onnx (384 dimensions, 100+ languages). No model zoo. No choices. No confusion.

Offline-First

Zero network dependencies. Everything runs locally. No telemetry. No surprises.

Hardware-Aware

Automatic limits based on your laptop's capabilities. Soft limit: 2-3s. Hard limit: 10s.

Polars, Not Pandas

We use Polars for speed and efficiency. No pandas dependency.

Tokenizers, Not Transformers

We use the standalone tokenizers library (3MB) instead of transformers (40MB). 93% smaller!

---

Target Users

• Non-ML engineers learning AI for the first time
• Business users in paranoid/restricted environments
• Developers who need offline semantic search
• Anyone who wants a safe sandbox to experiment

---

License

MIT License - see LICENSE file for details.

---

Author

Krishnamoorthy Sankaran

---

Links

• GitHub: https://github.com/sekarkrishna/justembed
• PyPI: https://pypi.org/project/justembed/
• Issues: https://github.com/sekarkrishna/justembed/issues

---

Status

🚧 Under Active Development 🚧

This is an alpha release to reserve the package name. Full functionality coming in v0.1.0.

Stay tuned!

---

JustEmbed - A semantic engine that just works.