llm doc

docs/docs/installation/docker-setup.md

@@ -100,7 +100,11 @@ docker compose -f docker-compose.prod.yml logs server --tail 50
 
 ### Restart a service
 ```bash
+# Quick restart (doesn't reload .env changes)
 docker compose -f docker-compose.prod.yml restart server
+
+# Reload .env and restart
+docker compose -f docker-compose.prod.yml up -d server
 ```
 
 ### Run database migrations

docs/docs/installation/overview.md

@@ -24,6 +24,7 @@ Before starting, you need:
 - [ ] **Two domain names** - e.g., `app.example.com` (frontend) and `api.example.com` (backend)
 - [ ] **Modal.com account** - Free tier at https://modal.com
 - [ ] **HuggingFace account** - Free at https://huggingface.co
+- [ ] **OpenAI API key** - For summaries and topic detection at https://platform.openai.com/account/api-keys
 
 ### Optional (for live meeting rooms)
 
@@ -159,7 +160,14 @@ DIARIZATION_BACKEND=modal
 DIARIZATION_URL=https://yourname--reflector-diarizer-web.modal.run
 DIARIZATION_MODAL_API_KEY=<from-deploy-all.sh-output>
 
-# Auth - disable for initial setup (see Step 9 for authentication)
+# Storage - where to store audio files and transcripts
+TRANSCRIPT_STORAGE_BACKEND=local
+
+# LLM - for generating titles, summaries, and topics
+LLM_API_KEY=sk-your-openai-api-key
+LLM_MODEL=gpt-4o-mini
+
+# Auth - disable for initial setup (see Step 8 for authentication)
 AUTH_BACKEND=none
 ```
 
@@ -286,9 +294,9 @@ DAILYCO_STORAGE_AWS_REGION=us-east-1
 DAILYCO_STORAGE_AWS_ROLE_ARN=<arn:aws:iam::ACCOUNT:role/DailyCo>
 ```
 
-Restart server:
+Reload env and restart:
 ```bash
-docker compose -f docker-compose.prod.yml restart server worker
+docker compose -f docker-compose.prod.yml up -d server worker
 ```
 
 ---
@@ -302,7 +310,7 @@ docker compose -f docker-compose.prod.yml logs
 
 ### CORS errors in browser
 - Verify `CORS_ORIGIN` in `server/.env` matches your frontend domain exactly (including `https://`)
-- Restart: `docker compose -f docker-compose.prod.yml restart server`
+- Reload env: `docker compose -f docker-compose.prod.yml up -d server`
 
 ### SSL certificate errors
 - Caddy auto-provisions Let's Encrypt certificates

docs/docs/installation/requirements.md

@@ -36,6 +36,7 @@ This page lists hardware and software requirements. For the complete deployment
 - **Two domain names** - One for frontend (e.g., `app.example.com`), one for API (e.g., `api.example.com`)
 - **Modal.com account** - For GPU-accelerated transcription and diarization (free tier available)
 - **HuggingFace account** - For Pyannote diarization model access
+- **OpenAI API key** - For generating summaries and topic detection (https://platform.openai.com/account/api-keys)
 
 ### Required for Live Meeting Rooms
 

gpu/modal_deployments/reflector_transcriber.py

@@ -89,6 +89,7 @@ image = (
         "torch==2.5.1",
         "faster-whisper==1.1.1",
         "fastapi==0.115.12",
+        "python-multipart",
         "requests",
         "librosa==0.10.1",
         "numpy<2",

server/env.example

@@ -63,18 +63,21 @@ TRANSLATE_URL=https://monadical-sas--reflector-translator-web.modal.run
 #TRANSLATION_MODAL_API_KEY=xxxxx
 
 ## =======================================================
-## LLM backend
+## LLM backend (Required)
 ##
-## Responsible for titles and short summary
+## Responsible for generating titles, summaries, and topic detection
-## Check reflector/llm/* for the full list of available
+## Requires OpenAI API key
-## llm backend implementation
 ## =======================================================
 
+## OpenAI API key - get from https://platform.openai.com/account/api-keys
+LLM_API_KEY=sk-your-openai-api-key
+LLM_MODEL=gpt-4o-mini
+
+## Optional: Custom endpoint (defaults to OpenAI)
+# LLM_URL=https://api.openai.com/v1
+
 ## Context size for summary generation (tokens)
-# LLM_MODEL=microsoft/phi-4
 LLM_CONTEXT_WINDOW=16000
-LLM_URL=
-LLM_API_KEY=sk-
 
 ## =======================================================
 ## Diarization
@@ -88,6 +91,22 @@ DIARIZATION_URL=https://monadical-sas--reflector-diarizer-web.modal.run
 #DIARIZATION_MODAL_API_KEY=xxxxx
 
 
+## =======================================================
+## Transcript Storage
+##
+## Where to store audio files and transcripts
+## Options: local, aws
+## =======================================================
+TRANSCRIPT_STORAGE_BACKEND=local
+
+## For AWS S3 storage (optional):
+#TRANSCRIPT_STORAGE_BACKEND=aws
+#TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID=your-aws-access-key
+#TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY=your-aws-secret-key
+#TRANSCRIPT_STORAGE_AWS_BUCKET_NAME=reflector-media
+#TRANSCRIPT_STORAGE_AWS_REGION=us-east-1
+
+
 ## =======================================================
 ## Sentry
 ## =======================================================