upgrade aws-sdk version

.dockerignore

@@ -0,0 +1,6 @@
+.idea/
+static/
+target/
+docker-compose.yaml
+Dockerfile
+README.MD

Cargo.lock

@@ -1100,6 +1100,15 @@ version = "0.4.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b5e6163cb8c49088c2c36f57875e58ccd8c87c7427f7fbd50ea6710b2f3f2e8f"
 
+[[package]]
+name = "matchers"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8263075bb86c5a1b1427b5ae862e8889656f126e9f77c484496e8b47cf5c5558"
+dependencies = [
+ "regex-automata 0.1.10",
+]
+
 [[package]]
 name = "memchr"
 version = "2.6.4"
@@ -1495,8 +1504,17 @@ checksum = "380b951a9c5e80ddfd6136919eef32310721aa4aacd4889a8d39124b026ab343"
 dependencies = [
  "aho-corasick",
  "memchr",
- "regex-automata",
- "regex-syntax",
+ "regex-automata 0.4.3",
+ "regex-syntax 0.8.2",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c230d73fb8d8c1b9c0b3135c5142a8acee3a0558fb8db5cf1cb65f8d7862132"
+dependencies = [
+ "regex-syntax 0.6.29",
 ]
 
 [[package]]
@@ -1507,9 +1525,15 @@ checksum = "5f804c7828047e88b2d32e2d7fe5a105da8ee3264f01902f796c8e067dc2483f"
 dependencies = [
  "aho-corasick",
  "memchr",
- "regex-syntax",
+ "regex-syntax 0.8.2",
 ]
 
+[[package]]
+name = "regex-syntax"
+version = "0.6.29"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f162c6dd7b008981e4d40210aca20b4bd0f9b60ca9271061b07f78537722f2e1"
+
 [[package]]
 name = "regex-syntax"
 version = "0.8.2"
@@ -2098,10 +2122,14 @@ version = "0.3.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "30a651bc37f915e81f087d86e62a18eec5f79550c7faff886f7090b4ea757c77"
 dependencies = [
+ "matchers",
  "nu-ansi-term",
+ "once_cell",
+ "regex",
  "sharded-slab",
  "smallvec",
  "thread_local",
+ "tracing",
  "tracing-core",
  "tracing-log",
 ]

Cargo.toml

@@ -19,7 +19,7 @@ serde_yaml = "0.9"
 tokio = { version = "1.33", features = ["macros", "rt-multi-thread", "sync"] }
 tokio-stream = "0.1"
 tracing = "0.1"
-tracing-subscriber = "0.3"
+tracing-subscriber = { version = "0.3", features = ["env-filter"] }
 whisper-rs = "0.8"
 whisper-rs-sys = "0.6"
 
@@ -34,9 +34,10 @@ features = ["coreml"]
 [target.aarch64-apple-darwin.dependencies.whisper-rs-sys]
 version = "0.6"
 
-
 [target.x86_64-unknown-linux-gnu.dependencies.whisper-rs]
+version = "0.8"
 features = ["cuda"]
 
 [target.aarch64-unknown-linux-gnu.dependencies.whisper-rs]
+version = "0.8"
 features = ["cuda"]

Dockerfile

@@ -1,46 +1,24 @@
-# Build stage
-FROM nvidia/cuda:12.2.2-devel-ubuntu22.04 as builder
-
-# Install python3.11 and build dependencies
-RUN apt-get update
-RUN apt-get install -y software-properties-common
-#RUN add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt-get update
-RUN apt-get install -y libssl-dev cmake python3-dev curl pkg-config clang
-
-# install rust toolchain
-RUN curl https://sh.rustup.rs -sSf | sh -s  -- --default-toolchain stable -y
+FROM nvidia/cuda:12.2.2-devel-ubuntu22.04 as chef
+RUN apt-get update && apt-get install -y curl
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- --default-toolchain stable -y
 ENV PATH=/root/.cargo/bin:$PATH
+RUN cargo install cargo-chef
+WORKDIR /app
 
-# Just copy the manifest files to cache dependencies
-COPY Cargo.toml Cargo.lock ./
-
-# Download dependencies
-RUN mkdir -p src/bin && echo "fn main() {println!(\"if you see this, the build broke\")}" > src/bin/bigbot.rs
-RUN --mount=type=cache,target=/usr/local/cargo/registry \
-    --mount=type=cache,target=/usr/local/cargo/git \
-    cargo build --release
+FROM chef as planner
+COPY . .
+RUN cargo chef prepare  --recipe-path recipe.json
 
-COPY ./src ./src
+FROM chef as builder
+RUN apt-get update && apt-get install -y cmake g++ libclang-dev libssl-dev pkg-config python3-dev
+COPY --from=planner /app/recipe.json recipe.json
+RUN cargo chef cook --release --recipe-path recipe.json
+COPY . .
+RUN cargo build --release
 
-# Build the project with release profile
-RUN --mount=type=cache,target=/usr/local/cargo/registry \
-    --mount=type=cache,target=/usr/local/cargo/git \
-    cargo build --release
-
-# Runtime stage
 FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04 as runtime
 
-# Install runtime dependencies
-RUN apt-get update && apt-get install -y ca-certificates python3-dev && rm -rf /var/lib/apt/lists/*
-
-# Just copy the binary from the build stage
-COPY --from=builder /target/release/polyhedron /usr/local/bin/polyhedron
-COPY ./models/ggml-large-encoder.mlmodelc ./models/ggml-large-encoder.mlmodelc
-COPY ./models/ggml-large.bin ./models/ggml-large.bin
-COPY ./config/dev.yaml ./config/dev.yaml
-COPY ./static ./static
-
-# Run the binary
-CMD ["polyhedron"]
+RUN apt-get update && apt-get install -y ca-certificates && rm -rf /var/lib/apt/lists/*
+WORKDIR /app
+COPY --from=builder /app/target/release/polyhedron .
+ENTRYPOINT ["./polyhedron"]

README.MD

@@ -22,7 +22,7 @@ Configuration like AWS credentials and models are specified in config.yaml.
 To run Polyhedron locally:
 
 1. Config AWS account via https://docs.aws.amazon.com/cli/latest/userguide/cli-configure-files.html
-2. Clone the repository, Run `cargo run --release`
+2. Clone the repository, Run `docker compose up`
 3. Open http://localhost:8080 in the browser
 ## Architecture
 

docker-compose.yaml

@@ -0,0 +1,16 @@
+version: "3"
+services:
+  polyhedron:
+    container_name: polyhedron
+    build: ./
+#    image: vitongue/polyhedron:latest
+    environment:
+      - AWS_DEFAULT_REGION=${AWS_DEFAULT_REGION}
+      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
+      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
+      - RUST_LOG=polyhedron=debug
+    volumes:
+      - ./config:/app/config
+      - ./static:/app/static
+    ports:
+      - "8080:8080"

src/config.rs

@@ -4,6 +4,7 @@ use config::{Config, Environment, File};
 use once_cell::sync::Lazy;
 use serde::Deserialize;
 use whisper_rs::FullParams;
+use tracing::debug;
 
 pub(crate) static SETTINGS: Lazy<Settings> =
     Lazy::new(|| Settings::new().expect("Failed to initialize settings"));
@@ -85,6 +86,10 @@ impl Settings {
             .map_err(anyhow::Error::from)?;
 
         config.try_deserialize::<Self>().map_err(Into::into)
+            .map(|settings| {
+                debug!("Settings: {settings:?}");
+                settings
+            })
     }
 }
 

src/main.rs

@@ -19,6 +19,8 @@ use poem::{
 };
 use serde::{Deserialize, Serialize};
 use tokio::select;
+use tracing::debug;
+use tracing_subscriber::{fmt, prelude::*, EnvFilter};
 
 use crate::{config::*, lesson::*, whisper::*};
 
@@ -34,11 +36,12 @@ struct Context {
 
 #[tokio::main]
 async fn main() -> Result<(), std::io::Error> {
-    tracing_subscriber::fmt::init();
+    tracing_subscriber::registry()
+        .with(fmt::layer())
+        .with(EnvFilter::from_default_env())
+        .init();
 
-    if tracing::enabled!(tracing::Level::DEBUG) {
-        tracing::debug!("Transcribe client version: {}", PKG_VERSION);
-    }
+    debug!("Transcribe client version: {}", PKG_VERSION);
 
     let shared_config = aws_config::load_from_env().await;
     let ctx = Context {
@@ -95,8 +98,8 @@ async fn stream_speaker(
     ws.on_upgrade(|mut socket| async move {
         let _origin_tx = lesson.voice_channel();
         let mut transcribe_rx = lesson.transcript_channel();
-        let whisper =
-            WhisperHandler::new(SETTINGS.whisper.clone(), prompt).expect("failed to create whisper");
+        let whisper = WhisperHandler::new(SETTINGS.whisper.clone(), prompt)
+            .expect("failed to create whisper");
         let mut whisper_transcribe_rx = whisper.subscribe();
         loop {
             select! {

src/whisper.rs

@@ -8,6 +8,7 @@ use std::{
 
 use once_cell::sync::Lazy;
 use tokio::sync::{broadcast, mpsc, oneshot};
+use tracing::trace;
 use whisper_rs::{convert_integer_to_float_audio, WhisperContext, WhisperState, WhisperToken};
 use whisper_rs_sys::WHISPER_SAMPLE_RATE;
 
@@ -124,15 +125,13 @@ impl WhisperHandler {
                     }
                 };
 
-                if tracing::enabled!(tracing::Level::TRACE) {
-                    for segment in segments.iter() {
-                        tracing::trace!(
-                            "[{}-{}]s SEGMENT: {}",
-                            segment.start_timestamp as f32 / 1000.0,
-                            segment.end_timestamp as f32 / 1000.0,
-                            segment.text
-                        );
-                    }
+                for segment in segments.iter() {
+                    trace!(
+                        "[{}-{}]s SEGMENT: {}",
+                        segment.start_timestamp as f32 / 1000.0,
+                        segment.end_timestamp as f32 / 1000.0,
+                        segment.text
+                    );
                 }
 
                 if let Err(e) = shared_transcription_tx.send(segments) {