thoughtdb 0.1.0

ThoughtDB is a mix between relational and vector database for efficient data retrieval

ThoughtDB

ThoughtDB is a mix between relational and vector database for efficient data retrieval

Installation

Windows

python -m venv .venv
.\.venv\Scripts\activate
pip install poetry

MacOS / Linux

python3 -m venv .venv
source ./.venv/bin/activate
pip install poetry

poetry run python app.py 0.0.0.0:8003

Text Embedding Models

Download the following model or model of your choice in GGUF format into the models_db folder

https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF/resolve/main/nomic-embed-text-v1.5.Q4_K_M.gguf?download=true

Data Structure

The following is the layout for the ThoughtDB data structure. As we are in Alpha phase this structure may change as we optimize things.

• Organizations
  • Collections
    • Conversations
      • Sessions
      • History
      • Summaries
    • Document Types
      • Documents
        • Chapters
        • Paragraphs
        • Sentences
        • Words

Overview

Installing

Installation should be simple

Pip

pip install thoughtdb

Poetry

poetry add thoughtdb

Creating a new database

Currently, we only support Sqlite3, all the dependencies should be installed by pip or poetry.

from thoughtdb.src.app import VectorStore

Building

python3 -m pip install --upgrade build
python3 -m build
python3 -m pip install --upgrade twine
python3 -m twine upload --repository testpypi dist/*