This project provides a straightforward Python script to enable ChatGPT to query personal files. It's designed for users who want to leverage large language models on their own data without complex setup. The primary benefit is enabling conversational access to private documents.

How It Works

The script utilizes the Langchain library for orchestrating LLM interactions and data retrieval. It employs ChromaDB as a vector store for indexing and searching document embeddings, and unstructured for parsing various file types. This approach allows for efficient semantic search over user-provided files, enabling ChatGPT to answer questions based on their content.

Quick Start & Requirements

• Install: pip install langchain openai chromadb tiktoken unstructured
• Prerequisites: OpenAI API key, Python 3.x. Place data files in the data/ directory.
• Setup: Modify constants.py.default to constants.py with your API key.

Highlighted Details

• Supports querying .txt and .pdf files.
• Demonstrates usage with example commands for retrieving information from files.
• Relies on Langchain for LLM orchestration and data handling.

Maintenance & Community

No specific community channels, contributors, or roadmap are mentioned in the provided README.

Licensing & Compatibility

The README does not specify a license. Compatibility for commercial or closed-source use is not detailed.

Limitations & Caveats

The script currently only explicitly demonstrates support for .txt and .pdf file types. The lack of a specified license and detailed community information may impact long-term viability and commercial adoption.