inferno-ai 0.10.3

Enterprise AI/ML model runner with automatic updates, real-time monitoring, and multi-interface support
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87

# Multi-stage Dockerfile for Inferno AI/ML inference server
# This is an example Dockerfile - adjust paths and dependencies as needed

# Stage 1: Build stage
FROM rust:1.75-slim as builder

# Install build dependencies
RUN apt-get update && apt-get install -y \
    pkg-config \
    libssl-dev \
    libclang-dev \
    build-essential \
    cmake \
    && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

# Copy dependency files
COPY Cargo.toml Cargo.lock ./

# Create a dummy main.rs to cache dependencies
RUN mkdir src && echo "fn main() {}" > src/main.rs

# Build dependencies (this layer will be cached)
RUN cargo build --release && rm src/main.rs

# Copy source code
COPY src ./src

# Build the application
RUN cargo build --release

# Stage 2: Runtime stage
FROM debian:bookworm-slim

# Install runtime dependencies
RUN apt-get update && apt-get install -y \
    ca-certificates \
    curl \
    libssl3 \
    && rm -rf /var/lib/apt/lists/*

# Create non-root user
RUN useradd -m -u 1001 -s /bin/bash inferno

# Set working directory
WORKDIR /app

# Copy binary from builder stage
COPY --from=builder /app/target/release/inferno /usr/local/bin/inferno

# Copy configuration files
COPY --chown=inferno:inferno examples/config/ ./config/

# Create directories
RUN mkdir -p /app/models /app/cache /app/logs && \
    chown -R inferno:inferno /app

# Switch to non-root user
USER inferno

# Environment variables
ENV INFERNO_MODELS_DIR=/app/models
ENV INFERNO_CACHE_DIR=/app/cache
ENV INFERNO_LOG_LEVEL=info
ENV INFERNO_BIND_ADDRESS=0.0.0.0
ENV INFERNO_PORT=8080

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
    CMD curl -f http://localhost:8080/health || exit 1

# Expose ports
EXPOSE 8080 9090

# Default command
CMD ["inferno", "serve"]

# Labels for metadata
LABEL org.opencontainers.image.title="Inferno AI/ML Inference Server"
LABEL org.opencontainers.image.description="High-performance offline AI/ML model runner"
LABEL org.opencontainers.image.version="0.1.0"
LABEL org.opencontainers.image.authors="Inferno Developers"
LABEL org.opencontainers.image.url="https://github.com/inferno-ai/inferno"
LABEL org.opencontainers.image.source="https://github.com/inferno-ai/inferno"
LABEL org.opencontainers.image.licenses="MIT OR Apache-2.0"