文本向量化检索最佳实践

{
  "file_compress": [
    {
      "name": "file_compressor",
      "type": "zstd"
    },
    {
      "name": "no_compressor",
      "type": ""
    }
  ],
  "table_name": "xiaoming001",
  "summarys": {
    "summary_fields": [
      "id",
      "vector_source_text",
      "cate_id",
      "vector"
    ],
    "parameter": {
      "file_compressor": "zstd"
    }
  },
  "indexs": [
    {
      "index_name": "id",
      "index_type": "PRIMARYKEY64",
      "index_fields": "id",
      "has_primary_key_attribute": true,
      "is_primary_key_sorted": false
    },
    {
      "index_name": "vector",
      "index_type": "CUSTOMIZED",
      "index_fields": [
        {
          "boost": 1,
          "field_name": "id"
        },
        {
          "boost": 1,
          "field_name": "vector"
        }
      ],
      "indexer": "aitheta2_indexer",
      "parameters": {
        "enable_rt_build": "true",
        "min_scan_doc_cnt": "20000",
        "vector_index_type": "Qc",
        "major_order": "col",
        "builder_name": "QcBuilder",
        "distance_type": "SquaredEuclidean",
        "embedding_delimiter": ",",
        "enable_recall_report": "true",
        "ignore_invalid_doc": "true",
        "is_embedding_saved": "false",
        "linear_build_threshold": "5000",
        "dimension": "768",
        "rt_index_params": "{\"proxima.oswg.streamer.segment_size\":2048}",
        "search_index_params": "{\"proxima.qc.searcher.scan_ratio\":0.01}",
        "searcher_name": "QcSearcher",
        "build_index_params": "{\"proxima.qc.builder.quantizer_class\":\"Int8QuantizerConverter\",\"proxima.qc.builder.quantize_by_centroid\":true,\"proxima.qc.builder.optimizer_class\":\"BruteForceBuilder\",\"proxima.qc.builder.thread_count\":10,\"proxima.qc.builder.optimizer_params\":{\"proxima.linear.builder.column_major_order\":true},\"proxima.qc.builder.store_original_features\":false,\"proxima.qc.builder.train_sample_count\":3000000,\"proxima.qc.builder.train_sample_ratio\":0.5}"
      }
    }
  ],
  "attributes": [
    {
      "field_name": "id",
      "file_compress": "no_compressor"
    },
    {
      "field_name": "vector_source_text",
      "file_compress": "no_compressor"
    },
    {
      "field_name": "cate_id",
      "file_compress": "no_compressor"
    },
    {
      "field_name": "vector",
      "file_compress": "no_compressor"
    }
  ],
  "fields": [
    {
      "user_defined_param": {},
      "field_name": "id",
      "field_type": "INT64",
      "compress_type": "equal"
    },
    {
      "field_name": "vector_source_text",
      "field_type": "STRING",
      "compress_type": "uniq"
    },
    {
      "field_name": "cate_id",
      "field_type": "STRING",
      "compress_type": "uniq"
    },
    {
      "user_defined_param": {
        "vector_model": "ops-text-embedding-000",
        "vector_modal": "text",
        "vector_source_field": "vector_source_text"
      },
      "field_name": "vector",
      "field_type": "FLOAT",
      "compress_type": "uniq",
      "multi_value": true
    }
  ]
}

vector:'水壶&modal=text&n=10&search_params={}'&&config=start:0,hit:10,format:json&&kvpairs=formula:proxima_score(vector)&&sort=+RANK

pip install alibabacloud-ha3engine

# -*- coding: utf-8 -*-


from alibabacloud_ha3engine import models, client
from alibabacloud_tea_util import models as util_models
from Tea.exceptions import TeaException, RetryError
def search():
    Config = models.Config(
        endpoint="参考实例详情页>API入口下的API域名",
        instance_id="",
        protocol="http",
        access_user_name="购买实例时设置的用户名",
        access_pass_word="购买实例时设置的密码"

    )

    # 如用户请求时间较长. 可通过此配置增加请求等待时间. 单位 ms
    # 此参数可在 search_with_options 方法中使用
    runtime = util_models.RuntimeOptions(
        connect_timeout=5000,
        read_timeout=10000,
        autoretry=False,
        ignore_ssl=False,
        max_idle_conns=50
    )

    # 初始化 Ha3Engine Client
    ha3EngineClient = client.Client(Config)

    optionsHeaders = {}

    try:
        # 示例1: 直接使用 ha 查询串进行搜索.
        # =====================================================
        query_str = "config=hit:4,format:json,fetch_summary_type:pk,qrs_chain:search&&query=text_index:'文本内容&modal=text&n=10&search_params={}'&&cluster=general"
        haSearchQuery = models.SearchQuery(query=query_str)
        haSearchRequestModel = models.SearchRequestModel(optionsHeaders, haSearchQuery)
        hastrSearchResponseModel = ha3EngineClient.search(haSearchRequestModel)
        print(hastrSearchResponseModel)
    except TeaException as e:
        print(f"send request with TeaException : {e}")
    except RetryError as e:
        print(f"send request with Connection Exception  : {e}")