Metadata-Version: 2.1
Name: incribo
Version: 0.1.2
Summary: Generate stateful embeddings for your AI
Author: Uma Venugopal
Author-email: uma@incribo.com
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy>=1.9.0
Requires-Dist: matplotlib>=3.9.1
Requires-Dist: sentence-transformers>=3.0.1
Requires-Dist: torch>=2.4.0
Requires-Dist: incribo>=0.1.2
Provides-Extra: dev
Requires-Dist: pytest>=8.3.2; extra == "dev"
Requires-Dist: twine>=5.1.1; extra == "dev"

incribo

Incribo lets you add state to your embeddings. Using it, you can track how embeddings change over time, compare different embeddings to see their similarities and stream new data to update embeddings on the fly.

- Real-time Embedding Updates: Efficient handling of evolving, dynamic data.
- Compare embedding qualities: Compare different embeddings and evaluate their quality using customizable metrics.
- Versioning & Control: Create multiple versions of embeddings and track them over time with rollback abilities.
- Streaming data: Stream data from multiple sources.
- Cross-Platform Compatibility: Hassle-free hosted solution.

🔧 Quick install
#Download the Python package
pip install incribo

✨ Basic Usage
Before we get started, it is advised to setup a virtual environment to work in. Next, add your embedding model and generate stateful embeddings with Incribo like so -
from incribo import Embedding

# Create a new embedding and add an associated model for better identification
emb = Embedding([1.0, 2.0, 3.0], "bert-base-uncased")

# Get the vector
vector = emb.get_vector()
print(f"Embedding vector: {vector}")

# Get the model name
model = emb.get_model()
print(f"Model: {model}")

# print the Embedding object 
print(emb)


📖 Documentation
For detailed usage instructions and example use cases, visit our documentation at docs.incribo.com.


🌐 Contributing
Drop us an email to report a bug, or request a feature here: info@incribo.com

🤝 Connect with the founders 1:1
Connect with us here: https://cal.com/uma08/30min

💪 Community
Join our growing community around the world, for help, ideas, and everything on AI and beyond:

Chat with us on Discord.
Follow us on Twitter.
Connect with us on LinkedIn.


License
This project is licensed under the Apache 2.0 License - see the LICENSE file for details.
