From a88e7ec21f8f139bb30642e304ec50ca28d4e34b Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Tue, 4 Nov 2025 02:24:08 +0000
Subject: [PATCH] fix: Correct Docker build for rustbpe tokenizer

This commit fixes a build failure in the Docker image by implementing a more robust build process for the `rustbpe` tokenizer.

The `Dockerfile` now explicitly creates a `uv` virtual environment, adds its `bin` directory to the `PATH`, installs `maturin` into the environment, and then runs the `maturin develop` command. This ensures that the build command executes within a fully configured environment with all necessary tools available on the `PATH`, resolving the "No such file or directory" error.
---
 vertex_pipelines/Dockerfile | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/vertex_pipelines/Dockerfile b/vertex_pipelines/Dockerfile
index c82061a..98e6bc4 100644
--- a/vertex_pipelines/Dockerfile
+++ b/vertex_pipelines/Dockerfile
@@ -8,16 +8,24 @@ WORKDIR /app
 RUN apt-get update && apt-get install -y curl build-essential
 RUN curl -LsSf https://astral.sh/uv/install.sh | sh
 RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
-ENV PATH="/root/.cargo/bin:${PATH}"
+# Add uv, cargo, and the future venv bin to the PATH
+ENV PATH="/root/.local/bin:/root/.cargo/bin:/app/.venv/bin:${PATH}"
 
 # Copy the entire project into the Docker image.
 COPY . .
 
+# Create a virtual environment.
+RUN uv venv
+
 # Install Python dependencies using uv.
-RUN /root/.local/bin/uv sync --extra gpu
+RUN uv sync --extra gpu
+
+# Install maturin, which is a build dependency.
+RUN uv pip install maturin
 
 # Build the rustbpe tokenizer.
-RUN /root/.local/bin/uv run maturin develop --release --manifest-path rustbpe/Cargo.toml --uv
+# The maturin executable from the venv should be on the PATH now.
+RUN maturin develop --release --manifest-path rustbpe/Cargo.toml
 
 # Set the entrypoint.
 ENTRYPOINT ["python"]