feat(deploy): add Hugging Face Spaces support via Gradio SDK

- Add app.py entrypoint using gradio.Server wrapper
- Update Dockerfile for HF Spaces (port 7860, /tmp caches, auto-build index)
- Update config.py to read QDRANT_PATH/SQLITE_FTS_PATH from env vars
- Add gradio to requirements.txt
- Add HF Spaces YAML frontmatter to README.md
- Update .env.example with QDRANT_PATH variable

.env.example

@@ -3,6 +3,7 @@ SARVAM_STT_URL=https://api.sarvam.ai/speech-to-text
 SARVAM_STT_MODEL=saarika:v2.5
 
 QDRANT_URL=http://localhost:6333
+QDRANT_PATH=storage/qdrant_db
 QDRANT_API_KEY=
 QDRANT_COLLECTION=msmarco_xi_chunks
 

Dockerfile

@@ -1,5 +1,6 @@
 FROM python:3.10-slim
 
+RUN useradd -m -u 1000 user
 WORKDIR /app
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
@@ -8,11 +9,22 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     sqlite3 \
     && rm -rf /var/lib/apt/lists/*
 
+ENV HF_HOME=/tmp/hf_cache \
+    TRANSFORMERS_CACHE=/tmp/hf_cache/transformers \
+    TORCH_HOME=/tmp/hf_cache/torch \
+    HF_HUB_CACHE=/tmp/hf_cache/hub \
+    QDRANT_PATH=/tmp/storage/qdrant_db \
+    SQLITE_FTS_PATH=/tmp/storage/chunks.sqlite
+
+RUN mkdir -p /tmp/hf_cache /tmp/storage && chown -R user:user /tmp
+
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-COPY . .
+COPY --chown=user . /app
 
-EXPOSE 8000
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
 
-CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["sh", "-c", "python scripts/build_index.py --languages hin --max-rows 500 && python app.py"]

README.md

@@ -1,3 +1,13 @@
+---
+title: Voice RAG
+emoji: 🎙️
+colorFrom: green
+colorTo: yellow
+sdk: gradio
+app_port: 7860
+pinned: false
+---
+
 # Voice-Enabled RAG System (HH Goa 2026 Task 2)
 
 An end-to-end, ultra-low-latency voice-enabled Retrieval-Augmented Generation (RAG) system built for the `ai4bharat/MSMARCO-XI` dataset.

app.py

@@ -0,0 +1,10 @@
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent))
+
+from gradio import Server
+from app.main import app
+
+server = Server(app)
+server.launch()

app/config.py

@@ -8,12 +8,12 @@ class Settings(BaseSettings):
     sarvam_stt_model: str = "saarika:v2.5"
 
     qdrant_url: str = "http://localhost:6333"
-    qdrant_path: str = "storage/qdrant_db"
+    qdrant_path: str = os.environ.get("QDRANT_PATH", "storage/qdrant_db")
     qdrant_api_key: str | None = None
     qdrant_collection: str = "msmarco_xi_chunks"
 
     embed_model: str = "intfloat/multilingual-e5-small"
-    sqlite_fts_path: str = "storage/chunks.sqlite"
+    sqlite_fts_path: str = os.environ.get("SQLITE_FTS_PATH", "storage/chunks.sqlite")
 
     generation_mode: str = "extractive"
 

requirements.txt

@@ -1,4 +1,5 @@
 fastapi
+gradio
 uvicorn[standard]
 python-multipart
 requests