redhat-oracle 0.1.0__tar.gz

redhat_oracle-0.1.0/.github/workflows/main.yml

@@ -0,0 +1,22 @@
+name: CI/CD Pipeline
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions: write-all
+
+jobs:
+  pipeline:
+    uses: dmzoneill/dmzoneill/.github/workflows/dispatch.yaml@main
+    with:
+      pypi-extension: "true"
+      test-ready: "true"
+      VALIDATE_PYTHON_BLACK: "false"
+      VALIDATE_PYTHON_FLAKE8: "false"
+      VALIDATE_PYTHON_ISORT: "false"
+      VALIDATE_PYTHON_MYPY: "false"
+      VALIDATE_PYTHON_PYLINT: "false"
+    secrets: inherit

redhat_oracle-0.1.0/.gitignore

@@ -0,0 +1,61 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.egg-info/
+*.egg
+dist/
+build/
+*.whl
+
+# Virtual environments
+.venv/
+venv/
+env/
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.mypy_cache/
+.ruff_cache/
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Project data (local runtime artifacts, not under src/)
+/repos/
+/vectordb/
+/sessions/
+/logs/
+# AI tool configurations
+.claude/
+.cursor/
+.codex/
+.opencode/
+.gemini/
+.aider*
+.cody/
+.tabnine/
+.windsurf/
+.devai/
+.bolt/
+.v0/
+.lovable/
+.codeium/
+CLAUDE.md
+GEMINI.md
+.cursorrules
+.cursorignore
+opencode.json
+copilot-instructions.md
+.github/copilot-instructions.md
+.github/hooks/

redhat_oracle-0.1.0/Makefile

@@ -0,0 +1,22 @@
+.PHONY: setup test-setup test lint typecheck build clean
+
+setup:
+	pip install -e ".[dev]"
+
+test-setup:
+	@echo "No additional test setup required"
+
+test:
+	pytest tests/
+
+lint:
+	ruff check src/ tests/
+
+typecheck:
+	mypy src/
+
+build:
+	python -m build
+
+clean:
+	rm -rf dist/ build/ src/*.egg-info

redhat_oracle-0.1.0/PKG-INFO

@@ -0,0 +1,152 @@
+Metadata-Version: 2.4
+Name: redhat-oracle
+Version: 0.1.0
+Summary: AI-powered knowledge assistant for Red Hat engineering teams
+Author: Red Hat Oracle Contributors
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/dmzoneill/redhat-oracle
+Project-URL: Repository, https://github.com/dmzoneill/redhat-oracle
+Project-URL: Issues, https://github.com/dmzoneill/redhat-oracle/issues
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: httpx>=0.27
+Requires-Dist: gitpython>=3.1
+Requires-Dist: chromadb>=0.5
+Requires-Dist: sentence-transformers>=3.0
+Requires-Dist: click>=8.1
+Requires-Dist: prompt-toolkit>=3.0
+Requires-Dist: rich>=13.0
+Requires-Dist: platformdirs>=4.0
+Requires-Dist: PySide6>=6.6
+Requires-Dist: pycookiecheat>=0.7
+Requires-Dist: beautifulsoup4>=4.12
+Provides-Extra: gui
+Requires-Dist: PySide6-WebEngine>=6.6; extra == "gui"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.24; extra == "dev"
+Requires-Dist: pytest-xdist>=3.5; extra == "dev"
+Requires-Dist: ruff>=0.8; extra == "dev"
+Requires-Dist: mypy>=1.13; extra == "dev"
+Requires-Dist: types-PyYAML>=6.0; extra == "dev"
+Requires-Dist: build>=1.0; extra == "dev"
+Requires-Dist: twine>=5.0; extra == "dev"
+
+# 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](https://ollama.com/) running locally (recommended LLM backend)
+- Git (for cloning source repos)
+
+## Installation
+
+```bash
+# 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:
+
+```bash
+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:
+
+```bash
+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
+
+```bash
+oracle            # Start interactive chat
+oracle sync       # Sync all configured sources
+oracle status     # Show index status
+```
+
+### GUI (optional)
+
+```bash
+pip install -e ".[gui]"
+oracle --gui
+```
+
+## Development
+
+```bash
+# Run tests
+make test
+
+# Lint
+make lint
+
+# Type check
+make typecheck
+
+# Build distribution
+make build
+```
+
+Or run commands directly:
+
+```bash
+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

redhat_oracle-0.1.0/README.md

@@ -0,0 +1,111 @@
+# 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](https://ollama.com/) running locally (recommended LLM backend)
+- Git (for cloning source repos)
+
+## Installation
+
+```bash
+# 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:
+
+```bash
+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:
+
+```bash
+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
+
+```bash
+oracle            # Start interactive chat
+oracle sync       # Sync all configured sources
+oracle status     # Show index status
+```
+
+### GUI (optional)
+
+```bash
+pip install -e ".[gui]"
+oracle --gui
+```
+
+## Development
+
+```bash
+# Run tests
+make test
+
+# Lint
+make lint
+
+# Type check
+make typecheck
+
+# Build distribution
+make build
+```
+
+Or run commands directly:
+
+```bash
+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

redhat_oracle-0.1.0/checks.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+set -euo pipefail
+
+# Install only ruff and mypy if not available (without full dev dependencies)
+if ! command -v ruff &> /dev/null; then
+    echo "Installing ruff..." >&2
+    pip install --no-cache-dir -q ruff
+fi
+
+if ! command -v mypy &> /dev/null; then
+    echo "Installing mypy..." >&2
+    pip install --no-cache-dir -q mypy types-PyYAML
+fi
+
+echo "Running ruff check..." >&2
+ruff check src/ tests/ >&2
+RUFF_EXIT=$?
+
+echo "Running mypy..." >&2
+mypy src/ >&2
+MYPY_EXIT=$?
+
+if [ $RUFF_EXIT -ne 0 ] || [ $MYPY_EXIT -ne 0 ]; then
+    echo "Checks failed." >&2
+    echo 1
+    exit 1
+fi
+
+echo "All checks passed." >&2
+echo 0
+exit 0

redhat_oracle-0.1.0/oracle.yaml

@@ -0,0 +1,133 @@
+# Red Hat Oracle — Configuration
+#
+# Config files are loaded and merged in order (higher precedence wins):
+#   1. /etc/redhat-oracle/oracle.yaml   (system, Linux/macOS only)
+#   2. ~/.config/redhat-oracle/oracle.yaml  (user)
+#   3. ./oracle.yaml                    (project / working directory)
+#
+# Secrets: Set token fields to null and use environment variables instead:
+#   ORACLE_GITHUB_TOKEN, ORACLE_GITLAB_TOKEN, ORACLE_SLACK_TOKEN
+#   OPENAI_API_KEY, ANTHROPIC_API_KEY
+
+sources:
+  github:
+    token: null # Use ORACLE_GITHUB_TOKEN env var
+    use_ssh: true
+    orgs:
+      - name: RedHatInsights
+        include: [] # Glob patterns; empty = all repos
+        exclude: [] # Glob patterns to skip
+        depth: 1 # Shallow clone (null = full history)
+      - name: ansible
+        include: [] # All repos under github.com/ansible/*
+        exclude: []
+        depth: 1
+
+  gitlab:
+    token: null # Use ORACLE_GITLAB_TOKEN env var
+    use_ssh: true
+    instances:
+      - url: https://gitlab.cee.redhat.com
+        token: null # Instance-specific token override
+        groups:
+          - name: automation-analytics
+          - name: Dataverse
+          - name: service
+          - name: insights-platform
+          - name: releng
+          - name: insights-qe
+
+  slack:
+    token: null # Use ORACLE_SLACK_TOKEN env var (bot/user token)
+    xoxc_token: null # Use ORACLE_SLACK_XOXC_TOKEN env var (Chrome session)
+    d_cookie: null # Use ORACLE_SLACK_D_COOKIE env var (Chrome session)
+    workspace_id: "E030G10V24F"
+    enterprise_id: ""
+    host: redhat.enterprise.slack.com
+    channels: [] # Empty = all accessible channels
+    history_days: 365
+
+  jira:
+    url: https://issues.redhat.com
+    token: null # Use ORACLE_JIRA_TOKEN env var (PAT)
+    projects: [RHCLOUD, AAP, ANSTRAT, INSIGHTS]
+    max_results: 100
+    include_comments: true
+    history_days: 365
+
+  web:
+    urls:
+      - https://ansible.pages.redhat.com
+      - https://clouddot.pages.redhat.com
+      - https://clowder.pages.redhat.com
+      - https://consoledot.pages.redhat.com
+      - https://dataverse.pages.redhat.com
+      - https://insights-qe.pages.redhat.com
+      - https://konflux.pages.redhat.com
+      - https://projects.pages.redhat.com
+      - https://service.pages.redhat.com
+    timeout: 30
+    max_depth: 3 # How many link levels deep to crawl
+    max_pages_per_site: 200 # Max pages to fetch per site
+
+  pages:
+    gitlab_url: https://gitlab.cee.redhat.com
+    token: null # Uses sources.gitlab.token if null
+    depth: 1
+    sites:
+      - agent-files
+      - ai-assisted-coding
+      - ansible
+      - brq-map
+      - consoledot
+      - core-platform-apps
+      - data-hub
+      - dataverse
+      - devhub
+      - fuse
+      - fuse-prod
+      - infrastories
+      - insights-experiences
+      - it-akamai
+      - it-platform
+      - ocponrhv
+      - osbuild
+      - osci
+      - ospodata
+      - poseidon
+      - releng-league
+      - rhel-lightspeed
+      - shiftstack
+      - spmm
+      - sysdeseng
+      - vault
+
+  # Maximum concurrent git clone/pull operations
+  max_concurrent_clones: 5
+
+vectordb:
+  embeddings:
+    provider: sentence-transformers # sentence-transformers | ollama | openai
+    model: all-MiniLM-L6-v2 # 384-dim, ~80MB
+    batch_size: 64
+
+  chunking:
+    method: ast # ast (Python) / fixed (everything else)
+    chunk_size: 500 # Words per chunk (fixed mode)
+    chunk_overlap: 50 # Overlap words between chunks
+    max_file_size: 524288 # Skip files larger than 512KB
+
+llm:
+  default_provider: ollama # ollama | openvino | openai | anthropic
+  ollama_base_url: http://localhost:11436
+  ollama_model: llama3:8b
+  openai_api_key: null # Use OPENAI_API_KEY env var
+  anthropic_api_key: null # Use ANTHROPIC_API_KEY env var
+
+rag:
+  top_k: 10 # Number of chunks to retrieve
+  min_score: 0.3 # Minimum similarity score threshold
+  system_prompt: >
+    You are the Red Hat Oracle, an AI assistant with deep knowledge of
+    Red Hat engineering codebases and internal communications. Answer questions
+    using the provided context. Always cite your sources.