pinetext 0.2.2

PineText

PineText

A lightweight assistant built using Pinecone that helps create RAG-based chat applications for reasoning over documents, retrieving relevant context, and providing grounded answers.

Getting Started

Use uv to add and manage PineText as a dependency in your project, or install it directly via uv pip install or pip install. See the Installation section of the documentation for full installation instructions and more details.

uv add pinetext

It can be embedded in and run directly from your application.

# app.py
from pinetext import PineText

def main():
    pt = PineText(data_dir="./data")
    pt.run()

It can also be launched from the command line using the provided CLI without modifying the source code.

pinetext

Or in an ephemeral, isolated environment using uvx. Check out the Using tools guide for more details.

uvx pinetext

Configuration

Place documents in the data folder and make sure to set PINECONE_API_KEY and the assistant name before starting PineText.

export PINETEXT_PINECONE__API_KEY=your-api-key
export PINETEXT_PINECONE__ASSISTANT=assistant-name
export PINETEXT_PINECONE__DATA_DIR=data
export PINETEXT_PINECONE__MODEL=o4-mini

These settings can also be specified in a .env file in the working directory.

pinetext_pinecone__api_key=your-api-key
pinetext_pinecone__assistant=assistant-name
pinetext_pinecone__data_dir=data
pinetext_pinecone__model=o4-mini

Docker

The PineText CLI can be deployed as a Docker container as follows:

docker run -it \
  --name pinetext \
  --env-file .env \
  -v $(pwd)/data:/app/data
  ghcr.io/ezhuk/pinetext:latest

Or using Docker Compose:

docker compose up

License

The server is licensed under the MIT License.