Build tested and working

Author: Ariel Vernaza

Dockerfile

@@ -6,15 +6,19 @@ FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim AS builder
 
 WORKDIR /app
 
-# Optional: set to 1 to install Transformer + Image embedders in the image (larger image).
+# Set to 1 to install Sentence Transformers in the image (large: ~2GB+ for torch). Default 0 = small image, use cohere:// for ingest-pdf.
+ARG INSTALL_TRANSFORMER=0
+# Set to 1 to add Image embedder (CLIP/ViT). Requires INSTALL_TRANSFORMER or separate install.
 ARG INSTALL_EMBEDDING_EXTRAS=0
 
-# Install deps from lockfile (reproducible). Include pdf + embedding-transformer for POST /libraries/{id}/ingest-pdf (no Cohere key needed).
+# Install deps from lockfile (reproducible). PDF extra for POST /libraries/{id}/ingest-pdf.
 COPY pyproject.toml uv.lock ./
 COPY app ./app
-RUN uv sync --frozen --no-dev --extra pdf --extra embedding-transformer
+RUN uv sync --frozen --no-dev --extra pdf
 
-# Optional: add Image embedder (CLIP/ViT) when building with --build-arg INSTALL_EMBEDDING_EXTRAS=1
+# Optional: Sentence Transformers (torch) for embedding_transformer:// without Cohere. Build with: --build-arg INSTALL_TRANSFORMER=1
+RUN if [ "$INSTALL_TRANSFORMER" = "1" ]; then uv sync --no-dev --extra embedding-transformer; fi
+# Optional: Image embedder (CLIP/ViT)
 RUN if [ "$INSTALL_EMBEDDING_EXTRAS" = "1" ]; then uv sync --no-dev --extra embedding-image; fi
 
 # ---

README.md

@@ -454,7 +454,7 @@ podman build --target test -t vector-db-api-test .
 podman run --rm vector-db-api-test
 ```
 
-To include Transformer and Image in the **API image** (larger image): `podman build --build-arg INSTALL_EMBEDDING_EXTRAS=1 -t vector-db-api .`
+The **default API image** includes only the `pdf` extra (small image). Use `embedder=cohere://` for ingest-pdf (set `COHERE_API_KEY` in `.env`). To include **Sentence Transformers** in the API image (larger, ~2GB+ for torch): `podman build --build-arg INSTALL_TRANSFORMER=1 -t vector-db-api .`. To add the **Image embedder**: `--build-arg INSTALL_EMBEDDING_EXTRAS=1`.
 
 ### Local development (optional)
 

docker-compose.yml

@@ -1,6 +1,8 @@
 # Run the Vector DB API in an isolated container.
 # Use: docker compose up  OR  podman compose up
 
+# Default API image is small (pdf only). For ingest-pdf use embedder=cohere:// and COHERE_API_KEY.
+# To include Sentence Transformers (larger image): podman compose build --build-arg INSTALL_TRANSFORMER=1
 services:
   api:
     build: .