### Download GoodQ4All Setup
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/install/INSTALL.md
Direct download link for the GoodQ4All standalone Windows installer. This is the recommended installation method for most users.
```html
🚀 Download GoodQ4All Setup v1.0.0.exe
```
--------------------------------
### Setup and Start vLLM Service
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/llm/VLLM_SYSTEMD_SETUP.md
Commands to set up the necessary directory for logs, reload the systemd daemon to recognize the new service, enable the service to start on boot, and then start the service immediately.
```bash
mkdir -p "${VLLM_HOME}/logs"
sudo systemctl daemon-reload
sudo systemctl enable vllm-llama1b.service
sudo systemctl start vllm-llama1b.service
```
--------------------------------
### Run Silent Installer
Source: https://github.com/goodq02/goodq4all/blob/main/docs/agent/workflows/LAPTOP_TEST_AND_REPORT_PROTOCOL.md
Execute the GoodQ4All setup executable silently to perform a clean installation. The '/S' argument ensures a non-interactive setup, and '-Wait' ensures the script pauses until the installation is complete.
```powershell
Start-Process -FilePath "$env:USERPROFILE\OneDrive\One_Domingo\test_v1.0.0_package\GoodQ4All_Setup_1.0.0.exe" -ArgumentList "/S" -Wait
```
--------------------------------
### CI/CD Environment Setup and Installation
Source: https://github.com/goodq02/goodq4all/blob/main/envs/locks/README.md
Example GitHub Actions workflow for creating a Conda environment, installing dependencies from a lock file, and verifying an installation.
```yaml
# Example GitHub Actions
- name: Create Environment
run: conda create -n test_env python=3.10 -y
- name: Install from Lock
run: |
conda run -n test_env pip install -r envs/locks/.lock.txt \
--no-cache-dir \
--no-user \
--isolated
- name: Verify Installation
run: conda run -n test_env python -c "import torch; print(torch.__version__)"
```
--------------------------------
### Non-Interactive Installation
Source: https://github.com/goodq02/goodq4all/blob/main/docs/bootstrap/INSTALL_BOOTSTRAP.md
Run the installer with `--yes` to accept defaults and `--no-launch` to create/update the environment and local config without starting the GoodQ runtime.
```powershell
python scripts/bootstrap_install.py --yes --no-launch
```
--------------------------------
### Install GPU Support with Batch Launcher
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/gpu/GPU_SETUP.md
Alternatively, use the provided Windows batch launcher script to initiate the GPU setup process.
```batch
.\scripts\setup_gpu_environments.bat
```
--------------------------------
### Install Dependencies and Setup Virtual Environment in WSL2
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/llm/WSL2_AUDIO_SETUP.md
Installs necessary audio processing dependencies and creates a Python virtual environment. Ensure you are in the WSL2 environment before running.
```bash
# 1. Install dependencies
sudo apt update
sudo apt install python3.12-venv python3-pip ffmpeg libsndfile1 portaudio19-dev -y
# 2. Create and activate venv
cd ~
mkdir goodq_audio
cd goodq_audio
python3 -m venv venv
source venv/bin/activate
# 3. Install runtime packages through the repo constraints
# Use the active repo setup script or constraints file. Do not install
# unpinned torch/pyannote packages here.
# 4. Test
python -c "import torch; print('CUDA:', torch.cuda.is_available())"
```
--------------------------------
### MCP Server Configuration Example
Source: https://github.com/goodq02/goodq4all/blob/main/gemini.md
Example configuration for MCP servers, including sequential thinking and a mock reference server. Ensure these runners are installed and accessible.
```json
{
"servers": {
"sequential-thinking": {
"runner": "npx -y @modelcontextprotocol/server-sequential-thinking"
},
"everything": {
"runner": "npx -y @modelcontextprotocol/server-everything"
}
}
}
```
--------------------------------
### Bootstrap Installation and Validation
Source: https://github.com/goodq02/goodq4all/blob/main/docs/CHEAT_SHEET.md
Use these commands to install and validate the GoodQ4All system. The PowerShell script is for installation, and the batch script is for validation.
```powershell
python scripts/bootstrap_install.py
```
```powershell
.\scripts\bootstrap_validate.bat
```
--------------------------------
### WSL2 Installation Script
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/wsl2/WSL2_BENCHMARKS.md
Commands for installing WSL2 audio components, either via an automated script or a manual setup script.
```bash
# Run automated installer
cd
.\INSTALL_WSL2_AUDIO.bat
```
```bash
# Or manual setup
wsl -d -- bash /mnt///scripts/wsl2_quick_install.sh
```
--------------------------------
### Qdrant Service Not Responding Example
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/FIRST_RUN.md
This text output indicates that the Qdrant service is not responding and failed to start automatically. Manual intervention is required.
```text
[!] Qdrant: Not responding
Attempting to start Qdrant service...
[!!] Qdrant: Failed to start - manual intervention required
```
--------------------------------
### Install WSL2 Audio
Source: https://github.com/goodq02/goodq4all/blob/main/wsl2_audio/QUICK_START.md
Run the installation script to set up WSL2 Audio. This process takes approximately 30 minutes.
```cmd
cd
INSTALL_WSL2_AUDIO.bat
```
--------------------------------
### Install Qdrant as a Windows Service
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/QDRANT_SETUP.md
Installs Qdrant as a Windows service named 'GoodQ_Qdrant' with auto-start enabled. This is the recommended installation method for seamless integration.
```batch
# Right-click and "Run as Administrator"
scripts\qdrant\INSTALL_QDRANT_SERVICE.bat
```
--------------------------------
### Launch Application Supervisor
Source: https://github.com/goodq02/goodq4all/blob/main/docs/agent/workflows/LAPTOP_TEST_AND_REPORT_PROTOCOL.md
Start the GoodQ4All application supervisor. This command assumes the application is installed in the default Program Files directory.
```powershell
Start-Process -FilePath "$env:ProgramFiles\GoodQ4All\LAUNCH_GOODQ.exe"
```
--------------------------------
### Install System Dependencies with Homebrew
Source: https://github.com/goodq02/goodq4all/blob/main/docs/setup-macos.md
Installs core system packages required by GoodQ4All using Homebrew. Ensure Homebrew is installed before running this command.
```bash
# Install core system packages
brew install ffmpeg poppler tesseract tesseract-lang qdrant
```
--------------------------------
### Install Development Dependencies (Windows)
Source: https://github.com/goodq02/goodq4all/blob/main/CONTRIBUTING.md
Run the bootstrap installation script to set up the development environment on Windows.
```powershell
python scripts/bootstrap_install.py
```
--------------------------------
### Initialize Qdrant and Verify Health
Source: https://github.com/goodq02/goodq4all/blob/main/docs/QDRANT_QUICKREF.md
A sequence of batch scripts to perform the initial setup for Qdrant. This includes starting the service, initializing collections, and verifying the health status.
```batch
# 1. Start Qdrant (pick one method above)
scripts\qdrant\START_QDRANT.bat
# 2. Initialize collections
scripts\qdrant\INIT_QDRANT.bat
# 3. Verify health
scripts\qdrant\CHECK_QDRANT.bat
```
--------------------------------
### Start API Server
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/general/LAUNCH_INSTRUCTIONS.md
Starts the API server process. Access API documentation at http://127.0.0.1:30000/docs after it's running.
```python
python -m api.server
```
```powershell
pwsh .\scripts\start_api.ps1
```
--------------------------------
### Start Audio Service Manually with Logging
Source: https://github.com/goodq02/goodq4all/blob/main/wsl2_audio/WSL2_AUDIO_FIX_COMPLETE.md
Manually start the audio service after setting up the CUDA environment, ensuring that all output is logged for debugging.
```bash
cd ~/goodq_audio
source setup_cuda_env.sh
python3 ~/goodq_audio/audio_service.py
```
--------------------------------
### API Server Startup Output Example
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/llm/LLM_INTEGRATION_COMPLETE.md
Example output observed in the console during the API server startup after successful LLM integration. It confirms LM Studio connection and Uvicorn server status.
```text
✓ LM Studio connected! Using model: qwen/qwen3-vl-4b
LLM Status: CONNECTED
INFO: Started server process [XXXX]
INFO: Uvicorn running on http://0.0.0.0:30000
```
--------------------------------
### Initialize LLM Client with Configuration
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/llm/LLM_CLIENT_GUIDE.md
Demonstrates the recommended pattern for initializing the LLM client using configuration files and a model factory. Ensure `models` are built and then passed to `get_client` with runtime parameters.
```python
from steps.common.config_loader import load_configs
from steps.common.llm_model_factory import build_llm_models
from lib.llm_client import get_client
cfg = load_configs({})
models = build_llm_models(cfg)
client = get_client(
models=models,
health_check_interval=60,
max_retries=3,
timeout=30,
cache_ttl=300,
enable_health_checks=False,
)
```
--------------------------------
### Configuration Paths Example
Source: https://github.com/goodq02/goodq4all/blob/main/docs/CLI-REFERENCE.md
Illustrates the structure of path configurations resolved from `configs/config.yaml` and environment overlays.
```yaml
paths:
import_inbox: ${GOODQ_DATA_ROOT}/GoodQ_Data/import_inbox
processing: ${GOODQ_DATA_ROOT}/GoodQ_Data/epochs//processing
db_path: ${GOODQ_DATA_ROOT}/GoodQ_Data/epochs//memory.db
knowledge_graph_db: ${GOODQ_DATA_ROOT}/GoodQ_Data/epochs//knowledge_graph.db
log_dir: ${GOODQ_DATA_ROOT}/GoodQ_Data/epochs//logs
```
--------------------------------
### Run the Bootstrap Installer
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/DEMO.md
Execute the primary installation script to set up the project environment. For systems with limited resources or specific configurations, use the CPU-safe variant.
```bash
python scripts/bootstrap_install.py
```
```bash
python scripts/bootstrap_install.py --disable-gpu --disable-wsl-audio --skip-model-prefetch
```
--------------------------------
### Start WSL2 Audio Service (WSL2)
Source: https://github.com/goodq02/goodq4all/blob/main/wsl2_audio/QUICK_REFERENCE.md
Navigate to the audio directory, set up the CUDA environment, and run the audio service script in the background.
```bash
# From WSL2
cd ~/goodq_audio
source setup_cuda_env.sh
python3 ~/goodq_audio/audio_service.py &
```
--------------------------------
### Automated CUDA Environment Setup (Shell Script)
Source: https://github.com/goodq02/goodq4all/blob/main/docs/WSL2_SCRIPTS_ADDED.md
Shell script for automated CUDA environment setup on WSL2. Useful for ensuring the correct CUDA drivers and libraries are installed.
```shell
setup_cuda_env.sh
```
--------------------------------
### Get All Scenes SQL Query
Source: https://github.com/goodq02/goodq4all/blob/main/docs/technical/PIPELINE_DEEP_DIVE_REPORT.md
Retrieves all scene data, ordered by start time. Used for populating the scene list.
```sql
-- Get all scenes
SELECT id, video_hash, start, end, meta, created_at
FROM scenes
ORDER BY start;
```
--------------------------------
### Run Qdrant Manually (Foreground)
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/QDRANT_SETUP.md
Starts Qdrant in the foreground for testing purposes. This is a fallback option if service installation is not desired or fails.
```batch
# Start Qdrant in foreground
scripts\qdrant\START_QDRANT.bat
```
--------------------------------
### Start vLLM Server with Qwen 2.5 7B Model
Source: https://github.com/goodq02/goodq4all/blob/main/vllm_wsl/MODEL_SCAN_UPDATED.md
This command starts the vLLM server, loading the Qwen 2.5 7B model from the specified directory and configuring it to use 90% of GPU memory on port 8000.
```bash
vllm serve ~/vllm_server/models/llm/chat/Qwen2.5-7B-Instruct \
--port 8000 --gpu-memory-utilization 0.90
```
--------------------------------
### Example Pytest Validation Command
Source: https://github.com/goodq02/goodq4all/blob/main/docs/architecture/GOODQ_EXECPLAN_PROTOCOL.md
Use this command to run pytest for the bootstrap install WSL unit tests. Ensure the path is correct.
```bash
python -m pytest tests/unit/test_bootstrap_install_wsl.py
```
--------------------------------
### Run Bootstrap Installer (CPU-Safe Variant)
Source: https://github.com/goodq02/goodq4all/blob/main/README.md
Use this command to run the installer while disabling GPU and WSL audio acceleration, and skipping model prefetching. This is useful for CPU-only environments.
```python
python scripts/bootstrap_install.py --disable-gpu --disable-wsl-audio --skip-model-prefetch
```
--------------------------------
### Configure GPU for a Specific Device ID
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/gpu/GPU_MANAGEMENT_GUIDE.md
Example for configuring GPU for a specific step on a particular GPU device ID, useful for multi-GPU setups.
```python
# Configure for specific GPU
config = GPUManager.configure_gpu("my_step", gpu_id=1)
```
--------------------------------
### Verify CUDA and Hugging Face Token Setup
Source: https://github.com/goodq02/goodq4all/blob/main/wsl2_audio/TEST_RESULTS.md
Source the CUDA environment setup script and then run Python scripts to verify that CUDA is accessible and the Hugging Face token is correctly configured.
```bash
source ~/goodq_audio/setup_cuda_env.sh
python3 ~/goodq_audio/check_cuda.py
python3 ~/goodq_audio/check_hf_token.py
```
--------------------------------
### Navigate to Project Directory
Source: https://github.com/goodq02/goodq4all/blob/main/README.md
Change your current directory to the root of the cloned GoodQ4All project.
```bash
cd goodq4all
```
--------------------------------
### Manual Error Diagnosis with Control Agent
Source: https://github.com/goodq02/goodq4all/blob/main/docs/CONTROL_AGENT.md
Example of using the Control Agent's diagnose_error method to analyze an error and get recommended actions.
```python
from agents.control_agent import ControlAgent
agent = ControlAgent(llm_client=llm_client)
# Analyze an error
diagnosis = agent.diagnose_error(
error_message="CUDA out of memory",
context={
"step_name": "face_embed",
"gpu_usage_mb": 15800,
"batch_size": 32
}
)
print(diagnosis)
# {
# "error_pattern": "cuda_oom",
# "recommended_actions": ["reduce_batch_size", "switch_to_cpu"],
# "auto_apply": True,
# "confidence": 0.95
# }
```
--------------------------------
### AI Agent Quick Start Section
Source: https://github.com/goodq02/goodq4all/blob/main/docs/architecture/DOCUMENTATION_REORGANIZATION_PLAN.md
Markdown section within an index file to guide AI agents on the recommended reading order for AI-relevant indexes.
```markdown
## 🤖 AI Agent Quick Start
1. Read this index overview
2. Check [Current System Status](../archive/status-reports/CURRENT_SYSTEM_STATUS_2025-12-02.md)
3. Review relevant section below
```
--------------------------------
### Clone Repository and Navigate
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/DEMO.md
Clone the GoodQ4All repository from GitHub and navigate into the project directory. This is the initial step for running the project from source.
```powershell
git clone https://github.com/GoodQ02/goodq4all.git
cd goodq4all
```
--------------------------------
### WSL2 Environment Setup Script (Shell)
Source: https://github.com/goodq02/goodq4all/blob/main/docs/WSL2_SCRIPTS_ADDED.md
Shell script for setting up the WSL2 environment for audio processing. Ensures all necessary components are installed and configured within WSL2.
```shell
setup_wsl2_audio.sh
```
--------------------------------
### Qdrant Configuration Example
Source: https://github.com/goodq02/goodq4all/blob/main/docs/CLI-REFERENCE.md
Shows the configuration for enabling Qdrant as the canonical vector endpoint, including its host.
```yaml
qdrant:
enabled: true
host: http://localhost:6333
```
--------------------------------
### Start Qwen 2.5 7B Server
Source: https://github.com/goodq02/goodq4all/blob/main/vllm_wsl/MODEL_DOWNLOAD_REPORT.md
Launches the vLLM server for the Qwen 2.5 7B model on port 8000.
```bash
~/vllm_server/scripts/start_qwen.sh
```
--------------------------------
### Start vLLM Server with Startup Script
Source: https://github.com/goodq02/goodq4all/blob/main/vllm_wsl/INSTALLATION_REPORT.md
Launches the vLLM server using a custom startup script, which handles environment activation and logging. It accepts a model path as an argument.
```bash
~/vllm_server/scripts/start_server.sh facebook/opt-125m
```
--------------------------------
### Setup WSL2 Environment
Source: https://github.com/goodq02/goodq4all/blob/main/wsl2_audio/README.md
Execute this bash script within your WSL2 Ubuntu terminal to install system dependencies, Python virtual environment, and core audio packages including PyTorch with CUDA support.
```bash
cd ~/goodq_audio
./setup_wsl2_audio.sh
```
--------------------------------
### Install CUDA-enabled PyTorch
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/wsl2/WSL2_AUDIO_FEASIBILITY_ANALYSIS.md
Installs PyTorch with CUDA 12.1 support for GPU acceleration. Verifies CUDA availability after installation.
```bash
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
python3 -c "import torch; print('CUDA:', torch.cuda.is_available())"
```
--------------------------------
### Example Progress Tracking
Source: https://github.com/goodq02/goodq4all/blob/main/PLAN.md
Illustrates how to track progress using a checklist with timestamps. Each step, whether completed or incomplete, should be documented.
```markdown
- [x] (2025-10-01 13:00Z) Example completed step.
- [ ] Example incomplete step.
- [ ] Example partially completed step (completed: X; remaining: Y).
```
--------------------------------
### Reinstall with System Site Packages
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/llm/WSL2_AUDIO_SETUP.md
Creates a virtual environment that includes system site packages, which can resolve import errors for audio libraries. Use this if standard venv creation fails.
```bash
# Reinstall with system site packages
python3 -m venv --system-site-packages venv
source venv/bin/activate
pip install
```
--------------------------------
### Login from WSL Audio Environment
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/wsl2/HF_CLI_LOGIN_GUIDE.md
Source the CUDA environment setup script and then log in using the HuggingFace CLI. This is for users working within the WSL audio environment.
```bash
source ~/goodq_audio/setup_cuda_env.sh
hf auth login
```
--------------------------------
### Install vLLM Service via WSL
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/llm/LLM_INFRASTRUCTURE.md
Installs the vLLM service using the WSL systemd installer. Replace placeholders with your specific distribution and repository root.
```bash
wsl -d -- bash /mnt///scripts/wsl/install_vllm_service.sh
```
--------------------------------
### Download Qwen/Qwen2.5-7B-Instruct Model
Source: https://github.com/goodq02/goodq4all/blob/main/vllm_wsl/MODEL_SCAN_REPORT.md
Use this command to download the Qwen2.5-7B-Instruct model for vLLM. Ensure your virtual environment is activated.
```bash
source ~/vllm_server/activate.sh
huggingface-cli download Qwen/Qwen2.5-7B-Instruct \
--local-dir ~/vllm_server/models/Qwen2.5-7B-Instruct \
--local-dir-use-symlinks False
```
--------------------------------
### Install GPU Support with PowerShell
Source: https://github.com/goodq02/goodq4all/blob/main/docs/guides/gpu/GPU_SETUP.md
Use the canonical PowerShell installer script to set up CUDA-enabled PyTorch in the maintained GPU-capable environments. The -Force flag ensures a complete installation.
```powershell
pwsh scripts\install_gpu_support.ps1 -Force
```
--------------------------------
### Install Flash Attention
Source: https://github.com/goodq02/goodq4all/blob/main/docs/technical/AUDIO_GPU_OPTIMIZATION.md
Install the flash-attn library to enable Flash Attention, which can significantly speed up attention mechanisms. This command activates the conda environment and installs the library with no build isolation.
```batch
conda activate audio_transcribe
pip install flash-attn --no-build-isolation
```
--------------------------------
### Install PyTorch with MPS Support
Source: https://github.com/goodq02/goodq4all/blob/main/docs/setup-macos.md
Installs PyTorch, torchvision, and torchaudio with Metal Performance Shaders (MPS) support for Apple Silicon. Note that standard pip installs on macOS include MPS support by default.
```bash
# Install PyTorch with Metal Performance Shaders (MPS) support
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
# Note: On macOS, standard pip install of torch includes MPS support out-of-the-box.
pip install torch torchvision torchaudio
```
--------------------------------
### Start API Server
Source: https://github.com/goodq02/goodq4all/blob/main/README.md
Launch the GoodQ4All API server using Conda. This allows interaction with the system and inspection of ingestion proofs.
```bash
conda run --no-capture-output -n goodq_core python -m api.server
```
--------------------------------
### Download microsoft/Phi-3.5-mini-instruct Model
Source: https://github.com/goodq02/goodq4all/blob/main/vllm_wsl/MODEL_SCAN_REPORT.md
Download the Phi-3.5-mini-instruct model using this command. Activate your vLLM server environment first.
```bash
source ~/vllm_server/activate.sh
huggingface-cli download microsoft/Phi-3.5-mini-instruct \
--local-dir ~/vllm_server/models/Phi-3.5-mini-instruct \
--local-dir-use-symlinks False
```
--------------------------------
### Align Quick Install
Source: https://github.com/goodq02/goodq4all/blob/main/docs/superpowers/plans/2026-05-08-wsl-wav2vec-transformers-lane.md
Update the constrained install command in `wsl2_quick_install.sh` to request transformers, tokenizers, and safetensors.
```bash
transformers tokenizers safetensors
```
--------------------------------
### Commit Message Example
Source: https://github.com/goodq02/goodq4all/blob/main/CONTRIBUTING.md
Example of a conventional commit message for a feature, including a detailed description of changes.
```bash
git commit -m "feat: Add emotion detection to audio pipeline
- Integrate Wav2Vec2 emotion classifier
- Add 8-class emotion output to result.json
- Update audio processing documentation"
```
--------------------------------
### Run Quick Test Suite
Source: https://github.com/goodq02/goodq4all/blob/main/docs/technical/AUDIO_GPU_QUICK_START.md
Execute the batch file for a quick test of the audio GPU optimization pipeline. Option 1 runs the full pipeline with integrated monitoring.
```batch
TEST_AUDIO_GPU.bat
```
--------------------------------
### Install Dependencies from Lock File
Source: https://github.com/goodq02/goodq4all/blob/main/envs/locks/README.md
Command to install all dependencies listed in a lock file into a specified Conda environment.
```text
conda run -n pip install -r envs/locks/.lock.txt
```
--------------------------------
### CLI Runtime Entry Points
Source: https://github.com/goodq02/goodq4all/blob/main/docs/architecture/ARCHITECTURE_REFERENCE.md
Lists the available command-line interface entry points for GoodQ4All, including ingestion, watchdog, monitoring, status checks, configuration printing, inbox listing, retrieval, and natural language querying.
```python
python -m cli.run_ingestion
```
```python
python -m cli.watchdog
```
```python
python -m cli.monitor_ingestion
```
```python
python -m cli.system_status
```
```python
python -m cli.print_config
```
```python
python -m cli.list_inbox
```
```python
python -m cli.retrieve
```
```python
python -m cli.nl_query
```