# Knowledge Base RAG System (md-kb-rag)

## Overview
Semantic search over the entire `claude-home` documentation repo using vector embeddings. Runs on `ubuntu-manticore` (10.10.0.226) as a Docker stack, exposed as an MCP server to Claude Code for the `claude-home` project.

- **App**: [st0nefish/md-kb-rag](https://github.com/st0nefish/md-kb-rag) (Rust)
- **Host**: `manticore` (10.10.0.226)
- **Stack location**: `~/docker/md-kb-rag/` on manticore
- **MCP endpoint**: `http://10.10.0.226:8001/mcp`
- **Current state**: 132 files indexed, ~1186 vector points

## Architecture

Three containers in a single Docker Compose stack:

| Container | Image | Role | Port |
|-----------|-------|------|------|
| `md-kb-rag-kb-rag-1` | `ghcr.io/st0nefish/md-kb-rag:latest` | MCP server + indexer | 8001 |
| `md-kb-rag-qdrant-1` | `qdrant/qdrant:v1.17.0` | Vector database | 6333/6334 (localhost) |
| `md-kb-rag-embeddings-1` | `ghcr.io/ggml-org/llama.cpp:server-cuda` | GPU embedding server | 8080 (internal) |

### Embedding Model
- **Model**: `nomic-embed-text-v2-moe` (Q8_0 quantization)
- **Vector size**: 768 dimensions
- **Context size**: 8192 tokens
- **GPU accelerated**: NVIDIA CUDA with flash attention

### Data Flow
```
claude-home repo files → rsync to manticore → md-kb-rag index
  → chunks markdown → nomic-embed generates vectors → stored in Qdrant
  → MCP search tool queries Qdrant → returns ranked chunks to Claude
```

## MCP Integration

### Claude Code Config
Registered as a project-scoped MCP server in `~/.claude.json` under the `/mnt/NV2/Development/claude-home` project:

```json
{
  "kb-search": {
    "type": "http",
    "url": "http://10.10.0.226:8001/mcp",
    "headers": {
      "Authorization": "Bearer <MCP_BEARER_TOKEN from .env>"
    }
  }
}
```

### Available MCP Tools

#### `search`
Semantic search across all indexed documents. Returns ranked chunks with scores.
```
query: "natural language search query"
limit: 10          # max results (default 10, max 50)
domain: null       # optional filter
type: null         # optional filter
tags: []           # optional tag filter
```

#### `get_document`
Retrieve full raw content of a document by file path (as returned by search results).
```
path: "/data/productivity/google-workspace-cli.md"
```

## Data Sync

The KB data lives at `~/docker/md-kb-rag/data/repo/` on manticore. This is **not** a functional git clone — it's a directory with a broken `.git` that contains the repo files directly. Files must be synced manually.

### Syncing New/Updated Files
```bash
# Sync a single file
rsync -av /mnt/NV2/Development/claude-home/path/to/file.md \
  manticore:~/docker/md-kb-rag/data/repo/path/to/

# Sync an entire directory
rsync -av /mnt/NV2/Development/claude-home/dirname/ \
  manticore:~/docker/md-kb-rag/data/repo/dirname/

# Sync everything (careful — includes tmp/, .claude/, etc.)
rsync -av --exclude='.git' --exclude='.claude' --exclude='tmp' \
  /mnt/NV2/Development/claude-home/ \
  manticore:~/docker/md-kb-rag/data/repo/
```

### Re-indexing After Sync
```bash
# Incremental (only changed/new files — fast, use this normally)
ssh manticore "docker exec md-kb-rag-kb-rag-1 md-kb-rag index"

# Full re-index (clears state DB, re-embeds everything — slow)
ssh manticore "docker exec md-kb-rag-kb-rag-1 md-kb-rag index --full"
```

The incremental indexer compares content hashes in a SQLite state DB (`data/state/state.db`) and only re-embeds files whose content has changed.

## Operations

### Health Check
```bash
ssh manticore "docker exec md-kb-rag-kb-rag-1 md-kb-rag health"
```

### Status (file list + Qdrant point count)
```bash
ssh manticore "docker exec md-kb-rag-kb-rag-1 md-kb-rag status"
```

### Validate Markdown (without indexing)
```bash
ssh manticore "docker exec md-kb-rag-kb-rag-1 md-kb-rag validate"
```

### View Logs
```bash
ssh manticore "docker logs md-kb-rag-kb-rag-1 --tail 50"
```

### Restart Stack
```bash
ssh manticore "cd ~/docker/md-kb-rag && docker compose restart"
```

## Adding New Documentation

The standard workflow for adding docs to the KB:

1. **Create/edit the markdown file** in `/mnt/NV2/Development/claude-home/`
2. **Update the relevant CONTEXT.md** with a summary and link
3. **Rsync to manticore**:
   ```bash
   rsync -av /mnt/NV2/Development/claude-home/path/to/newfile.md \
     manticore:~/docker/md-kb-rag/data/repo/path/to/
   rsync -av /mnt/NV2/Development/claude-home/path/to/CONTEXT.md \
     manticore:~/docker/md-kb-rag/data/repo/path/to/
   ```
4. **Re-index**:
   ```bash
   ssh manticore "docker exec md-kb-rag-kb-rag-1 md-kb-rag index"
   ```
5. **Verify** with a search query to confirm the new content is findable

## Environment Variables (on manticore)

File: `~/docker/md-kb-rag/.env`

| Variable | Purpose |
|----------|---------|
| `MODEL_PATH` | Path to embedding model directory |
| `MODEL_FILE` | Embedding model filename (nomic-embed-text-v2-moe.Q8_0.gguf) |
| `KB_PATH` | Path to knowledge base repo (./data/repo) |
| `MCP_PORT` | MCP server port (8001) |
| `MCP_BEARER_TOKEN` | Auth token for MCP endpoint |
| `RUST_LOG` | Log level (info) |

## Troubleshooting

### Search returns no results
- Check health: `ssh manticore "docker exec md-kb-rag-kb-rag-1 md-kb-rag health"`
- Verify files are synced: `ssh manticore "ls ~/docker/md-kb-rag/data/repo/path/to/file.md"`
- Re-index: may need `--full` if state DB is out of sync

### MCP connection refused
- Check container is running: `ssh manticore "docker ps | grep kb-rag"`
- Check port is listening: `ssh manticore "curl -s http://localhost:8001/health"`
- Restart: `ssh manticore "cd ~/docker/md-kb-rag && docker compose restart kb-rag"`

### Embedding server OOM / crash
- The llama.cpp embedding server uses GPU memory. Check with `ssh manticore "nvidia-smi"`
- Restart embeddings container: `ssh manticore "cd ~/docker/md-kb-rag && docker compose restart embeddings"`

### Stale index after deleting files
- Incremental indexing doesn't remove orphaned vectors for deleted files
- Run `--full` re-index to clean up: `ssh manticore "docker exec md-kb-rag-kb-rag-1 md-kb-rag index --full"`