zipstream-ai 1.0.1

Stream, Parse, and Chat with Compressed Datasets Using LLMs

zipstream-ai is a Python package that lets you interact with .zip and .tar.gz files directly—no need to extract them manually. It integrates archive streaming, format detection, data parsing (e.g., CSV, JSON), and natural language querying with LLMs like Gemini, all through a unified interface.

Installation

Option 1: Install from PyPI (Recommended)

pip install zipstream-ai

Option 2: Install from Conda

# Install from conda
conda install -c pranav_motarwar zipstream-ai

# Install PyPI-only dependencies (required)
pip install openai typer python-dotenv google-generativeai

Note: The conda package includes core dependencies, but you'll need to install PyPI-only dependencies (openai, typer, python-dotenv, google-generativeai) separately via pip.

Features

Use Case Examples

1. Load & Explore ZIP

from zipstream_ai import ZipStreamReader

reader = ZipStreamReader("dataset.zip")
print(reader.list_files())

2. Parse CSV from ZIP

from zipstream_ai import FileParser

parser = FileParser(reader)
df = parser.load("data.csv")
print(df.head())

3. Ask Questions with Gemini

from zipstream_ai import ask

response = ask(df, "Which 3 rows have the highest 'score'?")
print(response)

Why zipstream-ai?

Architecture Diagram

         ┌──────────────┐
         │  .zip/.tar   │
         └────┬─────────┘
              │
   ┌──────────▼──────────┐
   │  ZipStreamReader    │
   └──────────┬──────────┘
              │
     ┌────────▼────────┐
     │   FileParser    │────>  pd.DataFrame
     └────────┬────────┘
              │
     ┌────────▼────────┐
     │     ask()       │────> Gemini LLM Output
     └─────────────────┘