106e4baf17
- New: Vector search with pgvector extension (cosine similarity) - Embeddings: Vertex AI text-embedding-005 (768 dims, HIPAA-eligible) - 3 search modes: keyword, semantic, hybrid (best of both) - Auto-generate embeddings on content create/update - Admin endpoints: /api/admin/learning/embeddings/generate (backfill), /status - User endpoints: /api/learning/search/semantic, /search/hybrid - Falls back to OpenAI embeddings if Vertex not configured - Supports LiteLLM proxy routing Models tested: - vertex_ai/text-embedding-005 (768 dims, English+code) ✅ - vertex_ai/gemini-embedding-001 (3072 dims, multilingual) ✅ - vertex_ai/text-multilingual-embedding-002 (768 dims) ✅
153 lines
5.9 KiB
Text
153 lines
5.9 KiB
Text
# ============================================================
|
|
# AI PROVIDER (choose one)
|
|
# ============================================================
|
|
|
|
# Option 1: OpenRouter (default, cheapest, NOT HIPAA)
|
|
AI_PROVIDER=openrouter
|
|
OPENROUTER_API_KEY=sk-or-v1-your-key
|
|
|
|
# Option 2: AWS Bedrock (HIPAA compliant with BAA)
|
|
# AI_PROVIDER=bedrock
|
|
# AWS_BEDROCK_REGION=us-east-1
|
|
# AWS_ACCESS_KEY_ID=AKIA...
|
|
# AWS_SECRET_ACCESS_KEY=...
|
|
# (Or use IAM role — no keys needed if running on EC2/ECS)
|
|
|
|
# Option 3: Azure OpenAI (HIPAA compliant with BAA)
|
|
# AI_PROVIDER=azure
|
|
# AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
|
|
# AZURE_OPENAI_API_KEY=your-key
|
|
# AZURE_DEPLOYMENT_NAME=gpt-4o-mini
|
|
# AZURE_OPENAI_API_VERSION=2024-02-01
|
|
|
|
# Option 4: Google Vertex AI (HIPAA compliant with BAA)
|
|
# AI_PROVIDER=vertex
|
|
# GOOGLE_VERTEX_PROJECT=your-gcp-project-id
|
|
# GOOGLE_VERTEX_LOCATION=us-central1
|
|
# GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json
|
|
# (Or use default credentials if running on GCE/GKE/Cloud Run)
|
|
#
|
|
# Google STT — Gemini inline audio (auto-detected when GOOGLE_VERTEX_PROJECT set)
|
|
# TRANSCRIBE_PROVIDER=google
|
|
# GOOGLE_STT_MODEL=gemini-2.0-flash # or gemini-2.5-flash for better accuracy
|
|
#
|
|
# Google TTS — Google Cloud Text-to-Speech (auto-detected when GOOGLE_VERTEX_PROJECT set)
|
|
# TTS_PROVIDER=google
|
|
# GOOGLE_TTS_VOICE=en-US-Journey-F # female | en-US-Journey-D = male
|
|
# Other options: en-US-Studio-O, en-US-Neural2-C, en-US-Neural2-J
|
|
|
|
# Option 5: LiteLLM Proxy (self-hosted, routes to any provider)
|
|
# AI_PROVIDER=litellm
|
|
# LITELLM_API_BASE=http://localhost:4000
|
|
# LITELLM_API_KEY=sk-litellm-your-key
|
|
# Admin can discover available models via the admin panel
|
|
#
|
|
# LiteLLM Speech-to-Text
|
|
# TRANSCRIBE_PROVIDER=litellm
|
|
# LITELLM_STT_MODEL=whisper-1 # Use the model name from your LiteLLM model_list
|
|
# If your LiteLLM config uses full paths as model names, use the full path:
|
|
# LITELLM_STT_MODEL=openai/whisper-1
|
|
# NOTE: vertex_ai/chirp does NOT work via LiteLLM audio proxy.
|
|
# For Vertex AI speech, use TRANSCRIBE_PROVIDER=google (Gemini inline audio).
|
|
#
|
|
# LiteLLM TTS
|
|
# TTS_PROVIDER=litellm (auto-detected when LITELLM_API_BASE set)
|
|
# LITELLM_TTS_MODEL=tts-1 # Use model name from your LiteLLM model_list
|
|
# If your config uses full paths: LITELLM_TTS_MODEL=vertex_ai/google-tts
|
|
# LITELLM_TTS_VOICE=en-US-Journey-F # Google Cloud voice name (or alloy/nova for OpenAI)
|
|
|
|
# ============================================================
|
|
# TRANSCRIPTION (speech-to-text)
|
|
# ============================================================
|
|
|
|
# Option A: OpenAI Whisper (default if no AWS configured)
|
|
OPENAI_API_KEY=sk-your-openai-key
|
|
|
|
# Option B: Amazon Transcribe (HIPAA eligible, no S3 needed)
|
|
# Uses same AWS credentials as Bedrock above.
|
|
# Set TRANSCRIBE_PROVIDER=aws to force AWS even if OPENAI_API_KEY is set.
|
|
# Leave unset to auto-detect (uses AWS when AWS_BEDROCK_REGION is configured).
|
|
# TRANSCRIBE_PROVIDER=aws
|
|
|
|
# Option C: Local Whisper (privacy-first, no cloud API needed)
|
|
# Requires whisper.cpp or faster-whisper installed on the server.
|
|
# TRANSCRIBE_PROVIDER=local
|
|
# WHISPER_MODEL_SIZE=small # tiny, base, small, medium, large
|
|
# WHISPER_BINARY=whisper-cpp # or: whisper, faster-whisper
|
|
# WHISPER_MODEL_PATH= # custom path to .bin model file
|
|
# WHISPER_LANGUAGE=en
|
|
# WHISPER_THREADS=4 # defaults to CPU count - 1
|
|
|
|
# Amazon Transcribe Medical — better accuracy for clinical dictation
|
|
# Knows drug names, diagnoses, procedures, SOAP terminology
|
|
# HIPAA eligible (ensure your AWS account has a BAA)
|
|
# AWS_TRANSCRIBE_MEDICAL=true
|
|
# AWS_TRANSCRIBE_SPECIALTY=PRIMARYCARE
|
|
# Other options: CARDIOLOGY, NEUROLOGY, ONCOLOGY, RADIOLOGY, UROLOGY
|
|
|
|
# Optional
|
|
ELEVENLABS_API_KEY=
|
|
|
|
# App
|
|
PORT=3000
|
|
APP_URL=https://your-domain.com
|
|
JWT_SECRET=generate-a-random-64-char-string-here
|
|
|
|
# Email (for verification & password reset)
|
|
SMTP_HOST=smtp.gmail.com
|
|
SMTP_PORT=587
|
|
SMTP_USER=your-email@gmail.com
|
|
SMTP_PASS=your-app-password
|
|
SMTP_FROM=noreply@yourdomain.com
|
|
|
|
# Nextcloud (optional)
|
|
NEXTCLOUD_URL=https://cloud.yourdomain.com
|
|
|
|
# S3 Document Storage (optional — works with AWS S3, Backblaze B2, MinIO)
|
|
# S3_BUCKET=your-bucket-name
|
|
# S3_REGION=us-east-1
|
|
# S3_PREFIX=documents/
|
|
#
|
|
# For AWS S3: uses same AWS credentials as Bedrock above, or set S3-specific keys:
|
|
# S3_ACCESS_KEY_ID=...
|
|
# S3_SECRET_ACCESS_KEY=...
|
|
#
|
|
# For Backblaze B2:
|
|
# S3_ENDPOINT=https://s3.us-west-004.backblazeb2.com
|
|
# S3_REGION=us-west-004
|
|
# S3_ACCESS_KEY_ID=your-b2-application-key-id
|
|
# S3_SECRET_ACCESS_KEY=your-b2-application-key
|
|
#
|
|
# For MinIO (self-hosted):
|
|
# S3_ENDPOINT=http://minio:9000
|
|
# S3_REGION=us-east-1
|
|
# S3_ACCESS_KEY_ID=minio-access-key
|
|
# S3_SECRET_ACCESS_KEY=minio-secret-key
|
|
# S3_FORCE_PATH_STYLE=true
|
|
|
|
# ============================================================
|
|
# EMBEDDINGS (for Learning Hub semantic search)
|
|
# ============================================================
|
|
# Enables vector-based semantic search in Learning Hub
|
|
# Requires pgvector extension: apt-get install postgresql-16-pgvector
|
|
|
|
# Default model (Vertex AI text-embedding-005, 768 dims, English + code optimized)
|
|
EMBEDDING_MODEL=vertex_ai/text-embedding-005
|
|
EMBEDDING_DIMENSIONS=768
|
|
|
|
# Other Vertex AI embedding models:
|
|
# - vertex_ai/text-embedding-005 → 768 dims, English + code (recommended)
|
|
# - vertex_ai/gemini-embedding-001 → up to 3072 dims, multilingual + code
|
|
# - vertex_ai/text-multilingual-embedding-002 → 768 dims, multilingual focus
|
|
#
|
|
# LiteLLM usage (if using LiteLLM proxy):
|
|
# EMBEDDING_MODEL=text-embedding-005 # LiteLLM will route to configured provider
|
|
#
|
|
# OpenAI fallback (NOT HIPAA-eligible):
|
|
# Uses text-embedding-3-small if OPENAI_API_KEY is set and no Vertex/LiteLLM configured
|
|
|
|
# ============================================================
|
|
# DATABASE
|
|
# ============================================================
|
|
DATABASE_URL=postgresql://pedscribe:<password>@postgres:5432/pedscribe
|
|
DB_PASSWORD=pedscribe_secret_change_me
|