# Faiss Index Manager Helper

## Interface Definition

**Interface Name**: `IFaissIndexManager`

### Interface Methods

```python
class IFaissIndexManager(ABC):
    @abstractmethod
    def build_index(self, descriptors: np.ndarray, index_type: str) -> FaissIndex:
        pass
    
    @abstractmethod
    def add_descriptors(self, index: FaissIndex, descriptors: np.ndarray) -> bool:
        pass
    
    @abstractmethod
    def search(self, index: FaissIndex, query: np.ndarray, k: int) -> Tuple[np.ndarray, np.ndarray]:
        pass
    
    @abstractmethod
    def save_index(self, index: FaissIndex, path: str) -> bool:
        pass
    
    @abstractmethod
    def load_index(self, path: str) -> FaissIndex:
        pass
    
    @abstractmethod
    def is_gpu_available(self) -> bool:
        pass
    
    @abstractmethod
    def set_device(self, device: str) -> bool:
        """Set device: 'gpu' or 'cpu'."""
        pass
```

## Component Description

Manages Faiss indices for DINOv2 descriptor similarity search. H04 builds indexes from UAV image descriptors for:
1. **Loop closure detection**: Find when UAV revisits previously seen areas within the same flight
2. **Chunk-to-chunk matching**: Match disconnected chunks to each other
3. **Flight-to-flight matching**: Match current flight to previous flights in same area

**Index Source**: Descriptors are computed from UAV images using F08's DINOv2 encoder, NOT from satellite images. The index enables finding similar UAV viewpoints.

## API Methods

### `build_index(descriptors: np.ndarray, index_type: str) -> FaissIndex`

**Description**: Builds Faiss index from descriptors.

**Index Types**:
- **"IVF"**: Inverted File (fast for large databases)
- **"HNSW"**: Hierarchical Navigable Small World (best accuracy/speed trade-off)
- **"Flat"**: Brute force (exact, slow for large datasets)

**Input**: (N, D) descriptors array

---

### `add_descriptors(index: FaissIndex, descriptors: np.ndarray) -> bool`

**Description**: Adds more descriptors to existing index.

---

### `search(index: FaissIndex, query: np.ndarray, k: int) -> Tuple[np.ndarray, np.ndarray]`

**Description**: Searches for k nearest neighbors.

**Output**: (distances, indices) - shape (k,)

---

### `save_index(index: FaissIndex, path: str) -> bool`

**Description**: Saves index to disk for fast startup.

---

### `load_index(path: str) -> FaissIndex`

**Description**: Loads pre-built index from disk.

## Dependencies

**External**: faiss-gpu or faiss-cpu

## GPU/CPU Fallback

H04 supports automatic fallback from GPU to CPU:
- `is_gpu_available()`: Returns True if faiss-gpu is available and CUDA works
- `set_device("gpu")`: Use GPU acceleration (faster for large indexes)
- `set_device("cpu")`: Use CPU (fallback when GPU unavailable)

## Test Cases

1. Build index with 10,000 UAV image descriptors → succeeds
2. Search query UAV descriptor → returns top-k similar UAV frames
3. Save/load index → index restored correctly
4. GPU unavailable → automatically falls back to CPU
5. Add descriptors incrementally → index grows correctly