Merge pull request #6 from dhruvpathak1/cursor/live-10s-parallel-transcribe-pipeline

Live pipeline, Pages deploy, Docker compose image

Author: dhruvpathak1

.dockerignore

@@ -0,0 +1,19 @@
+.git
+.github
+node_modules
+venv
+.venv
+dist
+**/__pycache__
+**/*.pyc
+.env
+.env.*
+!.env.example
+server/transcripts
+server/entity_exports
+server/whisper_models
+server/torch_home
+adhoc
+*.md
+!DOCKER.md
+.DS_Store

DOCKER.md

@@ -0,0 +1,43 @@
+# Run PodLens with Docker
+
+One container serves the **built React UI** and the **FastAPI** backend (Whisper, NER, enrichment).
+
+## Quick start
+
+```bash
+docker compose up --build
+```
+
+Open **http://localhost:8080**. The first transcription downloads the Whisper model — expect a long delay and **several GB** of disk/RAM (CPU image).
+
+## Optional configuration
+
+- Copy `.env.example` to `.env` next to `docker-compose.yml` and fill in keys. Docker Compose reads that file for `${VAR}` substitution and forwards common variables into the container.
+- Override CORS for another browser origin:  
+  `CORS_EXTRA_ORIGINS=https://example.com docker compose up`
+
+## Share with others
+
+1. **Same LAN**: expose port `8080` (or change the mapping in `docker-compose.yml`) and share your machine IP.
+2. **Internet**: run the same compose stack on a small VPS, open firewall port **8080** (or put **nginx + HTTPS** in front).
+3. **Publish an image** (GitHub Container Registry example):
+
+   ```bash
+   docker build -t ghcr.io/YOUR_USER/podlens:latest .
+   docker push ghcr.io/YOUR_USER/podlens:latest
+   ```
+
+   Others run:
+
+   ```bash
+   docker run --rm -p 8080:8000 -v podlens-data:/data ghcr.io/YOUR_USER/podlens:latest
+   ```
+
+## GPU (optional)
+
+The default image uses **CPU** Whisper. For NVIDIA GPUs you’d extend the Dockerfile with CUDA base images and compatible PyTorch wheels; not included here to keep the shareable image simple.
+
+## Troubleshooting
+
+- **`docker compose` fails during `pip install`**: ensure the build has network access; `server/requirements.txt` installs spaCy and downloads models.
+- **Container exits / OOM**: Whisper + PyTorch need RAM; try `WHISPER_MODEL=tiny` in `.env` for a smaller model.

Dockerfile

@@ -0,0 +1,44 @@
+# syntax=docker/dockerfile:1
+# PodLens: React SPA (built) + FastAPI (Whisper, entities, enrichment).
+
+FROM node:22-bookworm-slim AS frontend
+WORKDIR /build
+COPY package.json package-lock.json ./
+RUN npm ci
+COPY tsconfig.json tsconfig.app.json tsconfig.node.json vite.config.ts index.html ./
+COPY public ./public
+COPY src ./src
+# Same-origin /api/* in the browser — no VITE_TRANSCRIBE_URL needed.
+RUN npm run build
+
+FROM python:3.11-slim-bookworm
+
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY server/requirements.txt ./server/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade pip \
+    && pip install --no-cache-dir openai-whisper \
+    && pip install --no-cache-dir -r server/requirements.txt
+
+COPY server ./server
+COPY --from=frontend /build/dist ./server/static
+
+ENV PYTHONUNBUFFERED=1 \
+    STATIC_DIST_DIR=/app/server/static \
+    WHISPER_DOWNLOAD_ROOT=/data/whisper_models \
+    TORCH_HOME=/data/torch_home \
+    TRANSCRIPTS_DIR=/data/transcripts \
+    ENTITY_JSON_DIR=/data/entity_exports
+
+RUN mkdir -p /data/whisper_models /data/torch_home /data/transcripts /data/entity_exports
+
+WORKDIR /app/server
+
+EXPOSE 8000
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

docker-compose.yml

@@ -0,0 +1,29 @@
+# PodLens — run UI + API together (single container).
+#
+#   docker compose up --build
+#   Open http://localhost:8080
+#
+# Optional: copy `.env.example` → `.env` in this folder. Compose reads `.env` for
+# variable substitution and passes the values below into the container.
+
+services:
+  podlens:
+    build: .
+    ports:
+      - "8080:8000"
+    environment:
+      ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY:-}
+      UNSPLASH_ACCESS_KEY: ${UNSPLASH_ACCESS_KEY:-}
+      UNSPLASH_SECRET_KEY: ${UNSPLASH_SECRET_KEY:-}
+      ENTITY_BACKEND: ${ENTITY_BACKEND:-}
+      SPACY_MODEL: ${SPACY_MODEL:-}
+      WHISPER_MODEL: ${WHISPER_MODEL:-base}
+      CLAUDE_MODEL: ${CLAUDE_MODEL:-}
+      CLAUDE_ENTITY_BATCH: ${CLAUDE_ENTITY_BATCH:-}
+      NOMINATIM_USER_AGENT: ${NOMINATIM_USER_AGENT:-}
+      CORS_EXTRA_ORIGINS: ${CORS_EXTRA_ORIGINS:-http://localhost:8080,http://127.0.0.1:8080}
+    volumes:
+      - podlens-data:/data
+
+volumes:
+  podlens-data:

server/main.py

@@ -483,3 +483,12 @@ def health():
         "entity_backend": resolve_entity_backend(None),
         "unsplash_configured": uk,
     }
+
+
+_static_dir_raw = os.environ.get("STATIC_DIST_DIR", "").strip()
+if _static_dir_raw:
+    _static_dir = Path(_static_dir_raw)
+    if _static_dir.is_dir():
+        from fastapi.staticfiles import StaticFiles
+
+        app.mount("/", StaticFiles(directory=str(_static_dir), html=True), name="spa")