Skip to main content

Red Hat Oracle

AI-powered knowledge assistant for Red Hat engineering teams. Ingests GitHub/GitLab repositories, Jira issues, GitLab Pages, public web docs, and Slack conversations, indexes them in a ChromaDB vector store, and provides RAG-based chat via local or cloud LLMs.

Prerequisites

  • Python 3.11+
  • Ollama running locally (recommended LLM backend)
  • Git (for cloning source repos)

Installation

# Clone the repo
git clone git@github.com:dmzoneill/redhat-oracle.git
cd redhat-oracle

# Create a virtual environment
python3 -m venv .venv
source .venv/bin/activate

# Install in development mode (with dev dependencies)
pip install -e ".[dev]"

# Or install without dev dependencies
pip install -e .

Configuration

Copy and edit the sample config:

cp oracle.yaml ~/.config/redhat-oracle/oracle.yaml

Config files are loaded and merged in order (higher precedence wins):

  1. /etc/redhat-oracle/oracle.yaml (system)
  2. ~/.config/redhat-oracle/oracle.yaml (user)
  3. ./oracle.yaml (project)

Secrets

Tokens are never stored in config files. Set them as environment variables:

export ORACLE_GITHUB_TOKEN="ghp_..."
export ORACLE_GITLAB_TOKEN="glpat-..."
export ORACLE_SLACK_TOKEN="xoxb-..."
export ORACLE_JIRA_TOKEN="..."
export OPENAI_API_KEY="sk-..."        # optional, if using OpenAI
export ANTHROPIC_API_KEY="sk-ant-..." # optional, if using Anthropic

Usage

CLI

oracle            # Start interactive chat
oracle sync       # Sync all configured sources
oracle status     # Show index status

GUI (optional)

pip install -e ".[gui]"
oracle --gui

Development

# Run tests
make test

# Lint
make lint

# Type check
make typecheck

# Build distribution
make build

Or run commands directly:

pytest tests/
ruff check src/ tests/
mypy src/

Architecture

Module Purpose
core/config.py YAML config loading with Pydantic validation
core/sources/ Data source connectors (GitHub, GitLab, Slack, Jira, Pages, Web)
core/vectordb/ ChromaDB vector store, AST-aware chunking, change tracking
core/rag.py RAG pipeline: embed query, search, assemble context, stream LLM
core/cache.py Response caching
cli/app.py Click + prompt-toolkit + Rich terminal UI
gui/app.py PySide6 (Qt) desktop GUI

License

MIT

Metadata

Release files for redhat-oracle 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for redhat-oracle 0.1.2
File Size Uploaded Provenance Actions
redhat_oracle-0.1.2.tar.gz 91.1 kB Without provenance Details for redhat_oracle-0.1.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for redhat-oracle 0.1.2
File Interpreter ABI Platform Actions
redhat_oracle-0.1.2-py3-none-any.whl Python 3 none any Details for redhat_oracle-0.1.2-py3-none-any.whl

Total release size: 165.6 kB

Release files / redhat_oracle-0.1.2.tar.gz

Download URL redhat_oracle-0.1.2.tar.gz
Size 91.1 kB
Tags Source
SHA-256 checksum
How to use checksums
d4d682009164be8f460c82870effc2ca7b467dad66b004f6a20c90c28970f35a
BLAKE2b-256 checksum
How to use checksums
bf105a2354b6055739753317de611b13cb33b80b0d501d7a9ad546a5e742bab4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.3

Release files / redhat_oracle-0.1.2-py3-none-any.whl

Download URL redhat_oracle-0.1.2-py3-none-any.whl
Size 74.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
bf87873793f07a757eadd0339ee94f135aed2b580856128eae292f79f5122632
BLAKE2b-256 checksum
How to use checksums
1ffd74a877d8291da65de7c3ea7987ea93797c0cce4ffa085f92bef944183681
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.3

Security for redhat-oracle 0.1.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page