chore: add flag to not include ml libs in docker image

docker/standalone/Dockerfile

@@ -2,19 +2,24 @@
 # Supports building API-only, Control Plane-only, or both
 #
 # Build args:
-#   INCLUDE_API=true/false       - Include API (default: true)
-#   INCLUDE_CP=true/false        - Include Control Plane (default: true)
-#   PRELOAD_ML_MODELS=true/false - Pre-download ML models during build (default: true)
+#   INCLUDE_API=true/false         - Include API (default: true)
+#   INCLUDE_CP=true/false          - Include Control Plane (default: true)
+#   INCLUDE_LOCAL_MODELS=true/false - Include local ML models for embeddings/reranking (default: true)
+#                                     Set to false when using external providers (TEI, OpenAI, Cohere)
+#   PRELOAD_ML_MODELS=true/false   - Pre-download ML models during build (default: true)
+#                                     Only effective when INCLUDE_LOCAL_MODELS=true
 #
 # Examples:
 #   docker build -t hindsight .                                          # Both (standalone)
 #   docker build -t hindsight-api --build-arg INCLUDE_CP=false .         # API only
 #   docker build -t hindsight-cp --build-arg INCLUDE_API=false .         # Control Plane only
 #   docker build -t hindsight --build-arg PRELOAD_ML_MODELS=false .      # Skip ML model preload
+#   docker build -t hindsight --build-arg INCLUDE_LOCAL_MODELS=false .   # Skip local ML deps (for external providers)
 
 ARG INCLUDE_API=true
 ARG INCLUDE_CP=true
 ARG PRELOAD_ML_MODELS=true
+ARG INCLUDE_LOCAL_MODELS=true
 
 # =============================================================================
 # Stage: API Builder
@@ -22,6 +27,7 @@ ARG PRELOAD_ML_MODELS=true
 FROM python:3.11-slim AS api-builder
 
 ARG INCLUDE_API
+ARG INCLUDE_LOCAL_MODELS
 RUN if [ "$INCLUDE_API" != "true" ]; then echo "Skipping API build" && exit 0; fi
 
 WORKDIR /app
@@ -40,6 +46,15 @@ COPY hindsight-api/README.md ./api/
 
 WORKDIR /app/api
 
+# Remove local ML model dependencies if INCLUDE_LOCAL_MODELS=false
+# This creates a smaller image when using external providers (TEI, OpenAI, Cohere)
+RUN if [ "$INCLUDE_LOCAL_MODELS" != "true" ]; then \
+        echo "Removing local-models dependencies (sentence-transformers, torch, transformers)..." && \
+        sed -i '/"sentence-transformers/d' pyproject.toml && \
+        sed -i '/"transformers/d' pyproject.toml && \
+        sed -i '/"torch/d' pyproject.toml; \
+    fi
+
 # Sync dependencies (will create lock file if needed)
 RUN uv sync
 
@@ -153,8 +168,10 @@ USER hindsight
 ENV PATH="/app/api/.venv/bin:${PATH}"
 
 # Pre-download ML models to avoid runtime download (conditional)
+# Only runs if both PRELOAD_ML_MODELS=true AND INCLUDE_LOCAL_MODELS=true
 ARG PRELOAD_ML_MODELS
-RUN if [ "$PRELOAD_ML_MODELS" = "true" ]; then \
+ARG INCLUDE_LOCAL_MODELS
+RUN if [ "$PRELOAD_ML_MODELS" = "true" ] && [ "$INCLUDE_LOCAL_MODELS" = "true" ]; then \
     /app/api/.venv/bin/python -c "\
 from sentence_transformers import SentenceTransformer, CrossEncoder; \
 print('Downloading embedding model...'); \
@@ -162,6 +179,7 @@ SentenceTransformer('BAAI/bge-small-en-v1.5'); \
 print('Downloading cross-encoder model...'); \
 CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2'); \
 print('Models cached successfully')"; \
+    elif [ "$INCLUDE_LOCAL_MODELS" != "true" ]; then echo "Skipping ML model preload (local-models not included)"; \
     else echo "Skipping ML model preload"; fi
 
 EXPOSE 8888
@@ -258,8 +276,10 @@ USER hindsight
 ENV PATH="/app/api/.venv/bin:${PATH}"
 
 # Pre-download ML models to avoid runtime download (conditional)
+# Only runs if both PRELOAD_ML_MODELS=true AND INCLUDE_LOCAL_MODELS=true
 ARG PRELOAD_ML_MODELS
-RUN if [ "$PRELOAD_ML_MODELS" = "true" ]; then \
+ARG INCLUDE_LOCAL_MODELS
+RUN if [ "$PRELOAD_ML_MODELS" = "true" ] && [ "$INCLUDE_LOCAL_MODELS" = "true" ]; then \
     /app/api/.venv/bin/python -c "\
 from sentence_transformers import SentenceTransformer, CrossEncoder; \
 print('Downloading embedding model...'); \
@@ -267,6 +287,7 @@ SentenceTransformer('BAAI/bge-small-en-v1.5'); \
 print('Downloading cross-encoder model...'); \
 CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2'); \
 print('Models cached successfully')"; \
+    elif [ "$INCLUDE_LOCAL_MODELS" != "true" ]; then echo "Skipping ML model preload (local-models not included)"; \
     else echo "Skipping ML model preload"; fi
 
 EXPOSE 8888 9999

hindsight-api/pyproject.toml

@@ -14,7 +14,6 @@ dependencies = [
     "openai>=1.0.0",
     "pydantic>=2.0.0",
     "rich>=13.0.0",
-    "sentence-transformers>=3.0.0,<3.3.0",
     "langchain-text-splitters>=0.3.0",
     "fastapi[standard]>=0.120.3",
     "uvicorn>=0.38.0",
@@ -24,8 +23,6 @@ dependencies = [
     "pgvector>=0.4.1",
     "greenlet>=3.2.4",
     "psycopg2-binary>=2.9.11",
-    "transformers>=4.30.0,<4.46.0",
-    "torch>=2.0.0",
     "tiktoken>=0.12.0",
     "httpx>=0.27.0",
     "fastmcp>=2.3.0",
@@ -40,6 +37,10 @@ dependencies = [
     "anthropic>=0.40.0",
     "typer>=0.9.0",
     "cohere>=5.0.0",
+    # Local ML models for embeddings/reranking - can be excluded in Docker with INCLUDE_LOCAL_MODELS=false
+    "sentence-transformers>=3.0.0,<3.3.0",
+    "transformers>=4.30.0,<4.46.0",
+    "torch>=2.0.0",
 ]
 
 [project.optional-dependencies]