Documentation Index
Fetch the complete documentation index at: https://docs.blindference.xyz/llms.txt
Use this file to discover all available pages before exploring further.
Installation
Option 1: PyPI (Recommended)
pip install blindference-node
For GPU-accelerated local inference:
pip install "blindference-node[gpu]"
For development (tests, linting):
pip install "blindference-node[dev]"
Option 2: From Source
git clone https://github.com/baync180705/Blindference-node.git
cd Blindference-node
pip install -e .
For GPU support from source:
Option 3: Docker
docker build -t blindference-node .
docker run -e BLF_KEY_PASSWORD=secure_password \
-e BLF_ICL_ENDPOINT=https://icl.blindference.xyz \
blindference-node run
Or use docker-compose:
System Requirements
Minimum (Mock Inference)
| Resource | Requirement |
|---|
| Python | 3.10+ |
| CPU | 1 core |
| RAM | 512MB |
| Network | Outbound HTTPS |
| GPU | None |
Recommended (Production)
| Resource | Requirement |
|---|
| Python | 3.11+ |
| CPU | 2+ cores |
| RAM | 2GB |
| Network | Stable internet |
| TPM | TPM 2.0 chip (for tier 1) |
Optional (Local Model Inference)
| Resource | Requirement |
|---|
| GPU | NVIDIA with CUDA |
| VRAM | 4GB+ |
| vLLM | Installed |
Verify Installation
blindference-node --version
# Expected: blindference-node, version 0.3.0
Troubleshooting Installation
Issue: pip install fails with compilation errors
Cause: Missing system dependencies for cryptography or web3.
Fix (Ubuntu/Debian):
sudo apt-get update
sudo apt-get install -y python3-dev libssl-dev libffi-dev build-essential
Fix (macOS):
brew install openssl libffi
Issue: blindference-node: command not found
Cause: pip installed to a location not in your PATH.
Fix:
# Find the binary
python -m site --user-base
# Add to PATH:
export PATH="$PATH:$(python -m site --user-base)/bin"
Or use:
python -m blindference_node.cli --help
Issue: GPU inference fails with CUDA not available
Cause: vLLM requires CUDA but GPU drivers are missing.
Fix:
# Check CUDA availability
python -c "import torch; print(torch.cuda.is_available())"
# If False, install NVIDIA drivers and CUDA toolkit
# Or run without GPU:
BLF_SUPPORTED_MODELS=qwen2.5-7b blindference-node init