fix:datasets revamp

Dockerfile

@@ -40,9 +40,14 @@ RUN python -c 'from sentence_transformers import SentenceTransformer; SentenceTr
 # Copy source files
 COPY models.py environment.py inference.py app.py openenv.yaml ./
 
-COPY Datasets.zip ./
-
-RUN apt-get update && apt-get install -y unzip && unzip Datasets.zip -d ./ && rm Datasets.zip && rm -rf /var/lib/apt/lists/*
+# Download the zip file directly (requires a direct download URL, not a folder sharing link)
+# Download dataset using gdown (RELIABLE)
+RUN apt-get update && apt-get install -y unzip && \
+    pip install --no-cache-dir gdown && \
+    gdown https://drive.google.com/uc?id=1-L8LCTSjjQs9qFdnIzFdnf0J37Yf6cxm -O Datasets.zip && \
+    unzip Datasets.zip -d ./ && \
+    rm Datasets.zip && \
+    rm -rf /var/lib/apt/lists/*
 
 # Environment variable defaults (DATA_DIR removed so it falls back to the local folder)
 ENV TASK=all \
@@ -51,4 +56,4 @@ ENV TASK=all \
 EXPOSE 7860
 
 # Default: run the FastAPI server (used by inference.py and HF Space)
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

requirements.txt

@@ -36,4 +36,5 @@ datasets>=2.18.0
 # Serving / inference client
 httpx>=0.25.0
 fastapi>=0.110.0
-uvicorn>=0.29.0
+uvicorn>=0.29.0
+openenv-core

validate-submission.sh

@@ -109,7 +109,7 @@ CURL_OUTPUT=$(portable_mktemp "validate-curl")
 CLEANUP_FILES+=("$CURL_OUTPUT")
 HTTP_CODE=$(curl -s -o "$CURL_OUTPUT" -w "%{http_code}" -X POST \
   -H "Content-Type: application/json" -d '{}' \
-  "$PING_URL/reset" --max-time 30 2>"$CURL_OUTPUT" || printf "000")
+  "$PING_URL/reset" --max-time 300 2>"$CURL_OUTPUT" || printf "000")
 
 if [ "$HTTP_CODE" = "200" ]; then
   pass "HF Space is live and responds to /reset"