Skip to main content

A tri-layer memory framework for LLM solutions.

Project description

Grizabella

A tri-layer memory framework for LLM solutions.

Docs License: MIT

Overview

Grizabella is a sophisticated memory layer designed for Large Language Model (LLM) solutions. It provides a unified interface to manage and query data across relational, vector, and graph databases, enabling complex memory and knowledge retrieval for AI applications.

Key Features

  • Tri-layer Storage: Integrates SQLite (relational), LanceDB (vector), and Kuzu (graph) for comprehensive data management.
  • Unified Python API: Offers a simple and consistent Python interface to interact with all three database layers.
  • Complex Query Engine: Allows for sophisticated queries that can span across the different data storage paradigms.
  • PySide6 UI: Includes an optional desktop application for visualizing and managing data.
  • MCP Server: Can operate as a Model Context Protocol (MCP) server, allowing other tools to leverage its memory capabilities.

Quick Links

Quick Installation

For production use (once published):

pip install grizabella

For development:

git clone https://github.com/example/grizabella.git
cd grizabella
poetry install

Basic Usage Snippet

from grizabella import Grizabella

# Initialize Grizabella (connects to default in-memory databases)
gz = Grizabella()

# Define an object type (implicitly creates a table/node type)
gz.create_object_type("document", {"text": str, "source": str})

# Add an object
doc1 = gz.add_object(
    object_type="document",
    data={"text": "This is the first document.", "source": "manual"},
    vector_data={"text": "This is the first document."} # Data for embedding
)

print(f"Added document with ID: {doc1.id}")

# Further operations (querying, adding relations, etc.) would go here.

Contributing

Contributions are welcome! Please see CONTRIBUTING.md (to be added) for guidelines on how to contribute to Grizabella.

License

Grizabella is licensed under the MIT License. See the LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

grizabella-0.1.0b2.tar.gz (132.5 kB view details)

Uploaded Source

Built Distribution

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

grizabella-0.1.0b2-py3-none-any.whl (162.6 kB view details)

Uploaded Python 3

File details

Details for the file grizabella-0.1.0b2.tar.gz.

File metadata

  • Download URL: grizabella-0.1.0b2.tar.gz
  • Upload date:
  • Size: 132.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.1.3 CPython/3.13.3 Linux/6.14.0-15-generic

File hashes

Hashes for grizabella-0.1.0b2.tar.gz
Algorithm Hash digest
SHA256 c71f43ee8472a40bd0bce8f5bde86d21639747366f0329acd63b2a28d3c4dfaf
MD5 2363cd1679e9135d6e0bdf79eed0fc4d
BLAKE2b-256 04280fe2d17a8e9db331a0cc1d16e1980a2c7dd32769e1d41ccf3e7ceb02670f

See more details on using hashes here.

File details

Details for the file grizabella-0.1.0b2-py3-none-any.whl.

File metadata

  • Download URL: grizabella-0.1.0b2-py3-none-any.whl
  • Upload date:
  • Size: 162.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.1.3 CPython/3.13.3 Linux/6.14.0-15-generic

File hashes

Hashes for grizabella-0.1.0b2-py3-none-any.whl
Algorithm Hash digest
SHA256 27429e4ab64a8617c2a255e445965193f6dfebea708a4e5f3e23cac557bfc732
MD5 e4e81ce6f0d20dbee471a7de6327e380
BLAKE2b-256 252436230d4bbc54a6ea83d0b5f02d2986e4e43cdae49f016b09ba2806ac6591

See more details on using hashes here.

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