legco_ai_assistant/README.md

# LegCo Reranker

RAG-powered document Q&A app with video ASR. Upload PDFs, upload videos with Cantonese ASR transcription, ask questions, get bullet-point answers with citations.

## Quick Start (Dev)

```bash
# Backend
cd backend
cp .env.example .env    # edit .env with your LLM API key AND DashScope API key (for video ASR)
pip install -r requirements.txt
uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload

# Frontend
cd frontend
npm install
npm run dev
```

Backend → `http://localhost:8000` | Frontend → `http://localhost:5173`

## Deploy with Docker

### Prerequisites

- Docker 24+ and Docker Compose v2
- OpenRouter API key (or compatible LLM provider)
- Alibaba Cloud DashScope API key (for video ASR transcription)

### Setup

```bash
# 1. Configure environment
cp backend/.env.example backend/.env
# Edit backend/.env with your API keys and model names

# 2. Build and start
docker compose up -d --build

# 3. Check health
curl http://localhost:8000/health
```

The app is served at `http://localhost:8000` — both the API and the frontend UI.

### Volumes

| Volume | Purpose |
|--------|---------|
| `chroma_data` | ChromaDB vector store (persistent) |
| `chunk_data` | Extracted PDF page files |
| `sqlite_data` | Prompt templates and query history |
| `uploads_data` | Uploaded video files (persistent) |

### Environment Variables

All configurable via `backend/.env`:

| Variable | Default | Description |
|----------|---------|-------------|
| `LLM_BASE_URL` | `https://openrouter.ai/api/v1` | LLM API endpoint |
| `LLM_API_KEY` | — | API key for LLM provider |
| `LLM_MODEL_NAME` | `qwen/qwen3.5-35b-a3b` | Chat model |
| `LLM_TIMEOUT` | `60.0` | LLM request timeout in seconds |
| `LLM_ENABLE_THINKING` | `false` | Enable LLM thinking/reasoning tokens |
| `VLLM_ENGINE` | `false` | Use vLLM-format `extra_body` instead of OpenRouter |
| `EMBEDDING_MODEL` | `qwen/qwen3-embedding-4b` | Embedding model |
| `EMBEDDING_BASE_URL` | `https://openrouter.ai/api/v1` | Embedding API endpoint |
| `EMBEDDING_API_KEY` | — | API key for embeddings (falls back to `LLM_API_KEY`) |
| `CHROMA_DB_PATH` | `./chroma_db` | ChromaDB persistent storage |
| `CHUNK_SIZE` | `1000` | Token chunk size |
| `CHUNK_OVERLAP` | `200` | Token chunk overlap |
| `RETRIEVAL_N_RESULTS` | `10` | Chunks per sub-question |
| `RELEVANCE_THRESHOLD` | `7.0` | Min relevance score (0-10) |
| `PROMPTS_DB_PATH` | `./data/prompts.db` | Prompt templates SQLite |
| `HISTORY_DB_PATH` | `./data/history.db` | Query history SQLite |
| `CORS_ORIGINS` | `["http://localhost:5173","http://localhost:3000"]` | Allowed CORS origins |
| `DASHSCOPE_API_KEY` | — | Alibaba Cloud DashScope API key (for video ASR) |
| `ASR_MODEL_NAME` | `qwen3-asr-flash` | ASR model for batch transcription |
| `ASR_REALTIME_MODEL_NAME` | `qwen3-asr-flash-realtime` | ASR model for real-time streaming |
| `VIDEO_UPLOAD_DIR` | `./uploads` | Video file storage directory |
| `MAX_VIDEO_SIZE_MB` | `300` | Maximum video upload size |
| `SUPPORTED_VIDEO_FORMATS` | `.mp4, .webm, .mov, .avi, .mkv` | Allowed video file extensions |

### Production: Nginx Reverse Proxy

```nginx
# Include nginx.conf in your site config
# Key settings:
# - client_max_body_size 350M   (allow large PDF uploads)
# - proxy_read_timeout 300s     (LLM calls can take minutes)
```

```bash
# Install nginx
sudo apt install nginx

# Copy config
sudo cp nginx.conf /etc/nginx/sites-available/legco
sudo ln -s /etc/nginx/sites-available/legco /etc/nginx/sites-enabled/
sudo nginx -t && sudo systemctl reload nginx
```

### Stopping

```bash
docker compose down
```

### Updating

```bash
git pull
docker compose up -d --build
```

### Cross-Platform Build (aarch64 → amd64)

When building on an aarch64/ARM64 machine (Apple Silicon, ARM Windows WSL2, Raspberry Pi) for deployment to an x86_64/amd64 server:

#### 1. Install buildx

```bash
# Download buildx for arm64
BUILDX_VERSION=$(wget -qO- https://api.github.com/repos/docker/buildx/releases/latest | grep tag_name | head -1 | cut -d'"' -f4)
wget "https://github.com/docker/buildx/releases/download/${BUILDX_VERSION}/buildx-${BUILDX_VERSION}.linux-arm64" -O ~/.docker/cli-plugins/docker-buildx
chmod +x ~/.docker/cli-plugins/docker-buildx
```

#### 2. Register QEMU for amd64 emulation

```bash
docker run --privileged --rm tonistiigi/binfmt --install all
```

#### 3. Build for amd64

```bash
DOCKER_BUILDKIT=1 docker build --platform linux/amd64 -t legco_reranker:amd64 .
```

#### 4. Export and transfer to server

```bash
# Save image to tar file
docker save legco_reranker:amd64 -o legco_reranker_amd64.tar

# Compress (~762MB → ~250MB)
gzip legco_reranker_amd64.tar

# Transfer to server
scp legco_reranker_amd64.tar.gz user@server:/path/

# On the x86_64 server:
gunzip legco_reranker_amd64.tar.gz
docker load -i legco_reranker_amd64.tar

# Run
docker run -d --name legco -p 80:8000 --env-file backend/.env \
  -v chroma_data:/app/chroma_db \
  -v chunk_data:/app/document_chunk \
  -v sqlite_data:/app/data \
  legco_reranker:amd64
```

#### 5. Test run (local, port 8888)

Before transferring to the server, test the amd64 image locally. Pass all config inline (no `--env-file`):

```bash
docker run -d --name legco_test -p 8888:8000 \
  -e LLM_BASE_URL=https://openrouter.ai/api/v1 \
  -e LLM_API_KEY=your_key_here \
  -e LLM_MODEL_NAME=qwen/qwen3.6-35b-a3b \
  -e LLM_TIMEOUT=60.0 \
  -e LLM_ENABLE_THINKING=false \
  -e VLLM_ENGINE=false \
  -e EMBEDDING_MODEL=qwen/qwen3-embedding-4b \
  -e EMBEDDING_BASE_URL=https://openrouter.ai/api/v1 \
  -e EMBEDDING_API_KEY=your_key_here \
  -e CHROMA_DB_PATH=./chroma_db \
  -e CHUNK_SIZE=1000 \
  -e CHUNK_OVERLAP=200 \
  -e RETRIEVAL_N_RESULTS=10 \
  -e RELEVANCE_THRESHOLD=7.0 \
  -e PROMPTS_DB_PATH=./data/prompts.db \
  -e HISTORY_DB_PATH=./data/history.db \
  -e CORS_ORIGINS='["http://localhost:5173","http://localhost:3000"]' \
  -e DASHSCOPE_API_KEY=your_dashscope_key \
  -e ASR_MODEL_NAME=qwen3-asr-flash-2026-02-10 \
  -e ASR_REALTIME_MODEL_NAME=qwen3-asr-flash-realtime-2026-02-10 \
  -e VIDEO_UPLOAD_DIR=./uploads \
  -e MAX_VIDEO_SIZE_MB=300 \
  -v ~/woody/legco/data/chroma_db:/app/chroma_db \
  -v ~/woody/legco/data/document_chunk:/app/document_chunk \
  -v ~/woody/legco/data/data:/app/data \
  legco_reranker:amd64.01.02

# Verify
curl http://localhost:8888/health

# Clean up
docker rm -f legco_test
```

## Architecture

```
User → Nginx (80) → Uvicorn (8000)
                         ├── FastAPI API (/api/v1/*)
                         └── Static Frontend (/*)
                              └── React 18 + Vite + Tailwind
```

### RAG Pipeline (Per-Sub-Question)

```
User Question
  → [LLM] Decompose into 2-5 sub-questions
  → [ChromaDB] Retrieve 10 chunks per sub-question
  → [LLM] Score all chunks against their own sub-question (single call)
  → [LLM] Generate markdown response per sub-question
  → SSE stream with per-sub-question sources
```

### Video Q&A (Phase 2)

```
Video → Audio → DashScope ASR → Transcript → QueryInput → RAG Pipeline
```

**Streaming Mode (real-time):**
- Upload video → press play → transcript flows into QueryInput in real time
- Audio captured from video element (no microphone needed)
- Auto-starts on play, stops on pause/end

**Full Transcript Mode (batch):**
- Click "Full Transcript" button under video player
- Server extracts audio via ffmpeg → Full DashScope transcription
- Complete transcript fills QueryInput

**Requirements:**
- `DASHSCOPE_API_KEY` in `.env`
- `ffmpeg` on server (for batch transcription)
- `dashscope` Python package (in `requirements.txt`)

### YouTube Live Stream Proxy (Phase 3)

Proxy YouTube live streams and VODs through the backend, with real-time ASR transcription piped into the RAG pipeline — no file upload needed.

```
YouTube URL → yt-dlp extract → HLS manifest URLs
                ↓
HLS Proxy (backend): rewrites segment URLs → client fetches via proxy
                ↓
Frontend: hls.js plays video/audio → AudioContext → WebSocket → ASR → transcript
```

**How to use:**
1. Toggle source from "Upload" to "YouTube" in the video panel
2. Paste a YouTube URL (live stream or VOD)
3. Click "Load Stream" — backend extracts streams via yt-dlp
4. Press play — video plays via hls.js, audio feeds real-time ASR
5. Transcript flows into QueryInput as you watch

**Configuration:**

| Variable | Default | Description |
|----------|---------|-------------|
| `YOUTUBE_PROXY_ENABLED` | `false` | Enable YouTube proxy feature |
| `YT_DLP_TIMEOUT` | `30` | yt-dlp extraction timeout (seconds) |
| `YT_DLP_CACHE_TTL` | `300` | Cache TTL for extracted stream info |

**Requirements:**
- `YOUTUBE_PROXY_ENABLED=true` in `.env`
- `yt-dlp` (auto-installed via `requirements.txt`)
- `DASHSCOPE_API_KEY` in `.env` (for ASR)

**Known limitations:**
- YouTube may require PO tokens for some videos (especially live streams) — stream may need re-extraction if tokens expire
- Video quality limited to 480p max (no quality selector in UI — low resolution sufficient for reference viewing)
- YouTube segment URLs expire after ~6 hours
- "Full Transcript" button hidden for YouTube source (streaming ASR only)

### Installing ffmpeg

```bash
# Ubuntu/Debian
sudo apt install ffmpeg

# macOS
brew install ffmpeg

# Static build (no root, any Linux)
mkdir -p ~/.local/bin
wget -qO- https://johnvansickle.com/ffmpeg/releases/ffmpeg-release-amd64-static.tar.xz | tar -xJ -C /tmp
cp /tmp/ffmpeg-*-static/ffmpeg ~/.local/bin/
```

## Notes

- PDF upload limit: 300MB
- Video upload limit: 300MB (same as PDF)
- ffmpeg required on server (for video transcription)
- DashScope ASR supports Cantonese (yue), Mandarin (zh), English (en), auto-detect
- Desktop only (not mobile-optimized)
- No authentication (public demo)
- All LLM calls routed through configurable base URL