Milvus 实操

from pymilvus import MilvusClient, DataType
from sentence_transformers import SentenceTransformer

COLLECTION = "support_kb"
client = MilvusClient(uri="http://localhost:19530")
print(client.list_collections())  # 先确认服务可达；健康检查常见于 9091/healthz
RESET_LAB = False  # 只有确认可丢弃旧练习数据时才改为 True
if client.has_collection(collection_name=COLLECTION):
    if not RESET_LAB:
        raise RuntimeError("support_kb 已存在；请换名称，或确认后启用 RESET_LAB")
    client.drop_collection(collection_name=COLLECTION)  # 删除整个集合
encoder = SentenceTransformer("BAAI/bge-m3")
docs = [
  {"id": 1, "text": "退款通常在三个工作日内到账", "category": "refund"},
  {"id": 2, "text": "修改密码后需要重新登录", "category": "account"},
]
vectors = encoder.encode([d["text"] for d in docs], normalize_embeddings=True).tolist()
dim = len(vectors[0])

schema = MilvusClient.create_schema(auto_id=False, enable_dynamic_field=False)
schema.add_field(field_name="id", datatype=DataType.INT64, is_primary=True)
schema.add_field(field_name="vector", datatype=DataType.FLOAT_VECTOR, dim=dim)
schema.add_field(field_name="text", datatype=DataType.VARCHAR, max_length=1000)
schema.add_field(field_name="category", datatype=DataType.VARCHAR, max_length=64)
client.create_collection(collection_name=COLLECTION, schema=schema)

rows = [{**d, "vector": v} for d, v in zip(docs, vectors)]
client.insert(collection_name=COLLECTION, data=rows) # 数据较多时分批写，并记录失败批次

index = client.prepare_index_params()
index.add_index(field_name="vector", index_type="HNSW", metric_type="COSINE",
                params={"M": 16, "efConstruction": 200})
client.create_index(collection_name=COLLECTION, index_params=index)
client.load_collection(collection_name=COLLECTION)

query_vector = encoder.encode(["退的钱多久能回来？"], normalize_embeddings=True).tolist()
hits = client.search(
  collection_name=COLLECTION, data=query_vector, anns_field="vector", limit=3,
  filter='category == "refund"', output_fields=["text", "category"],
  search_params={"metric_type": "COSINE", "params": {"ef": 64}},
)
for hit in hits[0]:
    print(hit["id"], hit["distance"], hit["entity"]["text"])

# Query 不做向量相似度计算
rows = client.query(collection_name=COLLECTION, filter='category == "account"',
                    output_fields=["id", "text"])
client.delete(collection_name=COLLECTION, filter="id == 2")

# ⚠️ 仅用于可丢弃的练习环境；drop 会删除整个集合
# client.drop_collection(collection_name=COLLECTION)