refactor: environment variable configuration for all pipeline settings

- Add config.py with dataclass-based configuration from env vars
- Remove hardcoded RunPod endpoint and credentials
- Consolidate duplicate training components into single reusable function
- Add .env.example with all configurable options
- Update README with environment variable documentation
- Add Kubernetes secrets example for production deployments
- Add timeout and error handling improvements

BREAKING: Pipeline parameters now use env vars by default.
Set RUNPOD_API_KEY, RUNPOD_ENDPOINT, S3_BUCKET, and AWS creds.

.env.example

@@ -0,0 +1,37 @@
+# =============================================================================
+# Healthcare ML Pipeline Configuration
+# =============================================================================
+# Copy this file to .env and fill in your values.
+# DO NOT commit .env to version control!
+
+# -----------------------------------------------------------------------------
+# RunPod Configuration (Required)
+# -----------------------------------------------------------------------------
+RUNPOD_API_KEY=your_runpod_api_key_here
+RUNPOD_ENDPOINT=your_endpoint_id_here
+RUNPOD_API_BASE=https://api.runpod.ai/v2
+
+# -----------------------------------------------------------------------------
+# AWS Configuration (Required for model storage)
+# -----------------------------------------------------------------------------
+AWS_ACCESS_KEY_ID=
+AWS_SECRET_ACCESS_KEY=
+AWS_SESSION_TOKEN=           # Optional - for assumed role sessions
+AWS_REGION=us-east-1
+S3_BUCKET=your-model-bucket
+
+# -----------------------------------------------------------------------------
+# Model Training Defaults (Optional - sensible defaults provided)
+# -----------------------------------------------------------------------------
+BASE_MODEL=emilyalsentzer/Bio_ClinicalBERT
+MAX_SAMPLES=10000
+EPOCHS=3
+BATCH_SIZE=16
+EVAL_SPLIT=0.1
+LEARNING_RATE=2e-5
+
+# -----------------------------------------------------------------------------
+# Pipeline Runtime Settings (Optional)
+# -----------------------------------------------------------------------------
+POLL_INTERVAL_SECONDS=10     # How often to check training status
+TRAINING_TIMEOUT_SECONDS=3600  # Max training time (1 hour default)