Local Directory RAG

A simple tool for Retrieval-Augmented Generation (RAG) using documents from your local filesystem.

Overview

Local Directory RAG allows you to:

Create vector embeddings from your local documents (PDF, TXT)
Query these documents using natural language, leveraging OpenAI's language models

Requirements

Python 3.13 or higher
OpenAI API key and other parameters (set in your .env file)

Installation

This project uses Poetry for dependency management.

Install Poetry by following the instructions in the official documentation.

Quick installation methods:

# For Linux, macOS, Windows (WSL)
curl -sSL https://install.python-poetry.org | python3 -

# For Windows PowerShell
(Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -

Install Project Dependencies

# Clone the repository
git clone https://github.com/sualeh/local-dir-rag.git
cd local-dir-rag

Install dependencies using Poetry

poetry install --extras "dev"
poetry show --tree

Configuration

Copy the ".env.example" file as ".env" in the project root. Update it with your OpenAI API key, location of your documents, and where you would like the vector database to be created.

Usage

Create Vector Database

poetry run python -m local_dir_rag.main embed --docs-directory /path/to/docs --vector-db-path /path/to/vector_db

Query Documents

poetry run python -m local_dir_rag.main query --vector-db-path /path/to/vector_db

Development and Testing

Install dependencies, as above.

Run all tests:

poetry run pytest

Or, run a single test:

poetry run pytest tests/test_document_loader.py::test_load_document

Docker Compose Usage

You can also use Docker Compose for easier management of the Local RAG container:

Clone the project, as described above.
Configure the ".env" file as described above.

Run the application using Docker Compose:

# For embedding documents
docker-compose run local-dir-rag embed

# For querying documents
docker-compose run local-dir-rag query

You can also pass additional arguments:

docker-compose run local-dir-rag embed --docs-directory /data/docs --vector-db-path /data/vector_db

This approach simplifies volume mounting and environment variable management, especially when working with the tool regularly.

Download files

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

Source Distribution

local_dir_rag-0.4.0.tar.gz (6.3 kB view details)

Uploaded May 7, 2025 Source

Built Distribution

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

local_dir_rag-0.4.0-py3-none-any.whl (9.5 kB view details)

Uploaded May 7, 2025 Python 3

File details

Details for the file local_dir_rag-0.4.0.tar.gz.

File metadata

Download URL: local_dir_rag-0.4.0.tar.gz
Upload date: May 7, 2025
Size: 6.3 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for local_dir_rag-0.4.0.tar.gz
Algorithm	Hash digest
SHA256	`1256c637a07737b788dda63603b3990e20419b2546a37877f4c424f72269519c`
MD5	`159948fff6b119215343c1dadb83a94b`
BLAKE2b-256	`288b001219996068f3463580b9be290076d3693e98e4d11943abc2df8cbf18e0`

See more details on using hashes here.

Provenance

The following attestation bundles were made for local_dir_rag-0.4.0.tar.gz:

Publisher: publish-pypi.yml on sualeh/local-dir-rag

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: local_dir_rag-0.4.0.tar.gz
- Subject digest: 1256c637a07737b788dda63603b3990e20419b2546a37877f4c424f72269519c
- Sigstore transparency entry: 208214882
- Sigstore integration time: May 7, 2025
Source repository:
- Permalink: sualeh/local-dir-rag@684673052e2cb2bbb5c939de8306dca57efd474a
- Branch / Tag: refs/tags/v0.4.0
- Owner: https://github.com/sualeh
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish-pypi.yml@684673052e2cb2bbb5c939de8306dca57efd474a
- Trigger Event: push