本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

# 使用 ElastiCache for Valkey 實作語意快取
<a name="semantic-caching-implementation"></a>

下列逐步解說說明如何使用 ElastiCache for Valkey 搭配 Amazon Bedrock 實作讀取語意快取。

## 步驟 1：建立 ElastiCache for Valkey 叢集
<a name="semantic-caching-step1"></a>

使用 建立版本為 8.2 或更新版本的 ElastiCache for Valkey 叢集 AWS CLI：

```
aws elasticache create-replication-group \
  --replication-group-id "valkey-semantic-cache" \
  --cache-node-type cache.r7g.large \
  --engine valkey \
  --engine-version 8.2 \
  --num-node-groups 1 \
  --replicas-per-node-group 1
```

## 步驟 2：連線至叢集並設定內嵌
<a name="semantic-caching-step2"></a>

從在 Amazon EC2 執行個體上執行的應用程式程式碼，連線至 ElastiCache 叢集並設定內嵌模型：

```
from valkey.cluster import ValkeyCluster
from langchain_aws import BedrockEmbeddings

# Connect to ElastiCache for Valkey
valkey_client = ValkeyCluster(
    host="mycluster.xxxxxx.clustercfg.use1.cache.amazonaws.com",  # Your cluster endpoint
    port=6379,
    decode_responses=False
)

# Set up Amazon Bedrock Titan embeddings
embeddings = BedrockEmbeddings(
    model_id="amazon.titan-embed-text-v2:0",
    region_name="us-east-1"
)
```

將主機值取代為 ElastiCache 叢集的組態端點。如需尋找叢集端點的指示，請參閱[存取 ElastiCache 叢集](accessing-elasticache.md)。

## 步驟 3：建立語意快取的向量索引
<a name="semantic-caching-step3"></a>

設定 ValkeyStore，使用具有 COSINE 距離的 HNSW 索引自動內嵌查詢，以進行向量搜尋：

```
from langgraph_checkpoint_aws import ValkeyStore
from hashlib import md5

store = ValkeyStore(
    client=valkey_client,
    index={
        "collection_name": "semantic_cache",
        "embed": embeddings,
        "fields": ["query"],           # Fields to vectorize
        "index_type": "HNSW",          # Vector search algorithm
        "distance_metric": "COSINE",   # Similarity metric
        "dims": 1024                   # Titan V2 produces 1024-d vectors
    }
)
store.setup()

def cache_key_for_query(query: str):
    """Generate a deterministic cache key for a query."""
    return md5(query.encode("utf-8")).hexdigest()
```

**注意**  
ElastiCache for Valkey 使用索引來提供快速且準確的向量搜尋。`FT.CREATE` 命令會建立基礎索引。如需詳細資訊，請參閱 [ ElastiCache 的向量搜尋](search.md)。

## 步驟 4：實作快取搜尋和更新函數
<a name="semantic-caching-step4"></a>

建立函數以搜尋快取是否有語意相似的查詢，以及存放新的查詢回應對：

```
def search_cache(user_message: str, k: int = 3, min_similarity: float = 0.8):
    """Look up a semantically similar cached response from ElastiCache."""
    hits = store.search(
        namespace="semantic-cache",
        query=user_message,
        limit=k
    )
    if not hits:
        return None

    # Sort by similarity score (highest first)
    hits = sorted(hits, key=lambda h: h["score"], reverse=True)
    top_hit = hits[0]
    score = top_hit["score"]

    if score < min_similarity:
        return None  # Below similarity threshold

    return top_hit["value"]["answer"]  # Return cached answer


def store_cache(user_message: str, result_message: str):
    """Store a new query-response pair in the semantic cache."""
    key = cache_key_for_query(user_message)
    store.put(
        namespace="semantic-cache",
        key=key,
        value={
            "query": user_message,
            "answer": result_message
        }
    )
```

## 步驟 5：實作讀取快取模式
<a name="semantic-caching-step5"></a>

將快取整合到應用程式的請求處理：

```
import time

def handle_query(user_message: str) -> dict:
    """Handle a user query with read-through semantic cache."""
    start = time.time()

    # Step 1: Search the semantic cache
    cached_response = search_cache(user_message, min_similarity=0.8)

    if cached_response:
        # Cache hit - return cached response
        elapsed = (time.time() - start) * 1000
        return {
            "response": cached_response,
            "source": "cache",
            "latency_ms": round(elapsed, 1),
        }

    # Step 2: Cache miss - invoke LLM
    llm_response = invoke_llm(user_message)  # Your LLM invocation function

    # Step 3: Store the response in cache for future reuse
    store_cache(user_message, llm_response)

    elapsed = (time.time() - start) * 1000
    return {
        "response": llm_response,
        "source": "llm",
        "latency_ms": round(elapsed, 1),
    }
```

## 基礎的 Valkey 命令
<a name="semantic-caching-valkey-commands"></a>

下表顯示用於實作語意快取的 Valkey 命令：


| 作業 | Valkey 命令 | 典型延遲 | 
| --- | --- | --- | 
| 建立索引 | FT.CREATE semantic\_cache SCHEMA query TEXT answer TEXT embedding VECTOR HNSW 6 TYPE FLOAT32 DIM 1024 DISTANCE\_METRIC COSINE | 一次性設定 | 
| 快取查詢 | FT.SEARCH semantic\_cache "\*=>[KNN 3 @embedding $query\_vec]" PARAMS 2 query\_vec [bytes] DIALECT 2 | 微秒 | 
| 儲存回應 | HSET cache:{hash} query "..." answer "..." embedding [bytes] | 微秒 | 
| 設定 TTL | EXPIRE cache:{hash} 82800 | 微秒 | 
| LLM 推論 （遺漏） | 對 Amazon Bedrock 的外部 API 呼叫 | 500–6000 毫秒 |