Update Dockerfile for caching and modify req.txt for platform-specific dependencies; add smoke test for Google Custom Search API

Dockerfile

@@ -1,20 +1,22 @@
+# syntax=docker/dockerfile:1.6
 FROM python:3.13-slim
 
 ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1 \
-    PIP_NO_CACHE_DIR=1 \
     PYTHONPATH=/app
 
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y --no-install-recommends \
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt,sharing=locked \
+    apt-get update && apt-get install -y --no-install-recommends \
         build-essential \
         curl \
-        git \
-    && rm -rf /var/lib/apt/lists/*
+        git
 
 COPY req.txt ./
-RUN pip install --upgrade pip && pip install -r req.txt
+RUN --mount=type=cache,target=/root/.cache/pip \
+    pip install --upgrade pip && pip install -r req.txt
 
 COPY dev_backend ./dev_backend
 COPY custom_search_api ./custom_search_api

req.txt

@@ -5,9 +5,9 @@ asyncmy==0.2.11
 certifi==2026.4.22
 click==8.3.3
 contourpy==1.3.3
-cuda-bindings==13.2.0
-cuda-pathfinder==1.5.4
-cuda-toolkit==13.0.2
+cuda-bindings==13.2.0 ; sys_platform == "linux"
+cuda-pathfinder==1.5.4 ; sys_platform == "linux"
+cuda-toolkit==13.0.2 ; sys_platform == "linux"
 cycler==0.12.1
 et_xmlfile==2.0.0
 fastapi==0.136.1
@@ -23,6 +23,7 @@ httpcore==1.0.9
 httpx==0.28.1
 hyperframe==6.1.0
 idna==3.13
+imagehash==4.3.2
 Jinja2==3.1.6
 joblib==1.5.3
 kiwisolver==1.5.0
@@ -31,21 +32,21 @@ matplotlib==3.10.9
 mpmath==1.3.0
 networkx==3.6.1
 numpy==2.4.4
-nvidia-cublas==13.1.0.3
-nvidia-cuda-cupti==13.0.85
-nvidia-cuda-nvrtc==13.0.88
-nvidia-cuda-runtime==13.0.96
-nvidia-cudnn-cu13==9.19.0.56
-nvidia-cufft==12.0.0.61
-nvidia-cufile==1.15.1.6
-nvidia-curand==10.4.0.35
-nvidia-cusolver==12.0.4.66
-nvidia-cusparse==12.6.3.3
-nvidia-cusparselt-cu13==0.8.0
-nvidia-nccl-cu13==2.28.9
-nvidia-nvjitlink==13.0.88
-nvidia-nvshmem-cu13==3.4.5
-nvidia-nvtx==13.0.85
+nvidia-cublas==13.1.0.3 ; sys_platform == "linux"
+nvidia-cuda-cupti==13.0.85 ; sys_platform == "linux"
+nvidia-cuda-nvrtc==13.0.88 ; sys_platform == "linux"
+nvidia-cuda-runtime==13.0.96 ; sys_platform == "linux"
+nvidia-cudnn-cu13==9.19.0.56 ; sys_platform == "linux"
+nvidia-cufft==12.0.0.61 ; sys_platform == "linux"
+nvidia-cufile==1.15.1.6 ; sys_platform == "linux"
+nvidia-curand==10.4.0.35 ; sys_platform == "linux"
+nvidia-cusolver==12.0.4.66 ; sys_platform == "linux"
+nvidia-cusparse==12.6.3.3 ; sys_platform == "linux"
+nvidia-cusparselt-cu13==0.8.0 ; sys_platform == "linux"
+nvidia-nccl-cu13==2.28.9 ; sys_platform == "linux"
+nvidia-nvjitlink==13.0.88 ; sys_platform == "linux"
+nvidia-nvshmem-cu13==3.4.5 ; sys_platform == "linux"
+nvidia-nvtx==13.0.85 ; sys_platform == "linux"
 openpyxl==3.1.5
 packaging==26.2
 pandas==3.0.2
@@ -58,10 +59,12 @@ pyparsing==3.3.2
 python-dateutil==2.9.0.post0
 python-dotenv==1.2.2
 qdrant-client==1.17.1
+requests==2.34.1
 scikit-learn==1.8.0
 scipy==1.17.1
 setuptools==81.0.0
 six==1.17.0
+sqlmodel==0.0.22
 SQLAlchemy==2.0.49
 starlette==1.0.0
 sympy==1.14.0
@@ -69,7 +72,7 @@ threadpoolctl==3.6.0
 torch==2.11.0
 torchvision==0.26.0
 tqdm==4.67.3
-triton==3.6.0
+triton==3.6.0 ; sys_platform == "linux"
 typing-inspection==0.4.2
 typing_extensions==4.15.0
 urllib3==2.6.3

test_search_api.py

@@ -0,0 +1,60 @@
+"""Quick smoke test that hits Google Custom Search API directly.
+
+Reads GEMINI_API_KEY and SEARCH_ENGINE_ID from .env and confirms credentials
+work without going through the FastAPI service.
+"""
+import os
+import sys
+import requests
+from dotenv import load_dotenv
+
+load_dotenv()
+
+GOOGLE_CSE_ENDPOINT = "https://www.googleapis.com/customsearch/v1"
+API_KEY = os.getenv("GEMINI_API_KEY")
+CX = os.getenv("SEARCH_ENGINE_ID")
+
+QUERY = sys.argv[1] if len(sys.argv) > 1 else "lectures"
+NUM = int(sys.argv[2]) if len(sys.argv) > 2 else 5
+
+
+def main():
+    if not API_KEY:
+        print("[FAIL] GEMINI_API_KEY not set in .env")
+        sys.exit(1)
+    if not CX:
+        print("[FAIL] SEARCH_ENGINE_ID not set in .env")
+        sys.exit(1)
+
+    params = {"key": API_KEY, "cx": CX, "q": QUERY, "num": NUM}
+    print(f"GET {GOOGLE_CSE_ENDPOINT}?q={QUERY}&num={NUM} (key/cx hidden)\n")
+
+    try:
+        r = requests.get(GOOGLE_CSE_ENDPOINT, params=params, timeout=30)
+    except requests.RequestException as e:
+        print(f"[FAIL] Could not reach Google CSE: {e}")
+        sys.exit(1)
+
+    print(f"Status: {r.status_code}")
+    if r.status_code != 200:
+        print(f"Body: {r.text}")
+        sys.exit(1)
+
+    data = r.json()
+    info = data.get("searchInformation", {}) or {}
+    items = data.get("items", []) or []
+
+    print(f"Query: {QUERY}")
+    print(f"Total results: {info.get('totalResults')}")
+    print(f"Search time: {info.get('searchTime')}s")
+    print(f"Items returned: {len(items)}\n")
+
+    for i, item in enumerate(items, 1):
+        print(f"{i}. {item.get('title')}")
+        print(f"   {item.get('link')}")
+        snippet = (item.get("snippet") or "").replace("\n", " ")
+        print(f"   {snippet[:120]}{'...' if len(snippet) > 120 else ''}\n")
+
+
+if __name__ == "__main__":
+    main()