稀疏向量字段类型
编辑稀疏向量字段类型
编辑sparse_vector 字段可以索引特征和权重，以便后续在带有 sparse_vector 的查询中用于查询文档。此字段还可以与传统的 text_expansion 查询一起使用。
sparse_vector 是应与 ELSER 映射一起使用的字段类型。
resp = client.indices.create(
index="my-index",
mappings={
"properties": {
"text.tokens": {
"type": "sparse_vector"
}
}
},
)
print(resp)
response = client.indices.create(
index: 'my-index',
body: {
mappings: {
properties: {
'text.tokens' => {
type: 'sparse_vector'
}
}
}
}
)
puts response
const response = await client.indices.create({
index: "my-index",
mappings: {
properties: {
"text.tokens": {
type: "sparse_vector",
},
},
},
});
console.log(response);
PUT my-index
{
"mappings": {
"properties": {
"text.tokens": {
"type": "sparse_vector"
}
}
}
}
有关使用 ELSER 将文档添加到 sparse_vector 映射字段的完整示例，请参阅 使用 ELSER 进行语义搜索。
多值稀疏向量
编辑当传递稀疏向量的值数组时，将选择具有相似名称的特征的最大值。
论文《Adapting Learned Sparse Retrieval for Long Documents》（https://arxiv.org/pdf/2305.18494.pdf）对此进行了更详细的讨论。总而言之，研究结果支持表示聚合通常优于分数聚合。
对于需要重叠特征名称的情况，应将它们单独存储或使用嵌套字段。
以下是一个传递具有重叠特征名称的文档的示例。请考虑在此示例中，存在两个表示正面情绪和负面情绪的类别。但是，出于检索的目的，我们还希望获得整体影响，而不是特定的情绪。在示例中，impact 存储为多值稀疏向量，并且仅存储重叠名称的最大值。更具体地说，此处的最终 GET 查询返回的 _score 约为 1.2（这是 max(impact.delicious[0], impact.delicious[1])，并且由于我们具有如下所述的 0.4% 的相对误差，因此是近似值）
resp = client.indices.create(
index="my-index-000001",
mappings={
"properties": {
"text": {
"type": "text",
"analyzer": "standard"
},
"impact": {
"type": "sparse_vector"
},
"positive": {
"type": "sparse_vector"
},
"negative": {
"type": "sparse_vector"
}
}
},
)
print(resp)
resp1 = client.index(
index="my-index-000001",
document={
"text": "I had some terribly delicious carrots.",
"impact": [
{
"I": 0.55,
"had": 0.4,
"some": 0.28,
"terribly": 0.01,
"delicious": 1.2,
"carrots": 0.8
},
{
"I": 0.54,
"had": 0.4,
"some": 0.28,
"terribly": 2.01,
"delicious": 0.02,
"carrots": 0.4
}
],
"positive": {
"I": 0.55,
"had": 0.4,
"some": 0.28,
"terribly": 0.01,
"delicious": 1.2,
"carrots": 0.8
},
"negative": {
"I": 0.54,
"had": 0.4,
"some": 0.28,
"terribly": 2.01,
"delicious": 0.02,
"carrots": 0.4
}
},
)
print(resp1)
resp2 = client.search(
index="my-index-000001",
query={
"term": {
"impact": {
"value": "delicious"
}
}
},
)
print(resp2)
const response = await client.indices.create({
index: "my-index-000001",
mappings: {
properties: {
text: {
type: "text",
analyzer: "standard",
},
impact: {
type: "sparse_vector",
},
positive: {
type: "sparse_vector",
},
negative: {
type: "sparse_vector",
},
},
},
});
console.log(response);
const response1 = await client.index({
index: "my-index-000001",
document: {
text: "I had some terribly delicious carrots.",
impact: [
{
I: 0.55,
had: 0.4,
some: 0.28,
terribly: 0.01,
delicious: 1.2,
carrots: 0.8,
},
{
I: 0.54,
had: 0.4,
some: 0.28,
terribly: 2.01,
delicious: 0.02,
carrots: 0.4,
},
],
positive: {
I: 0.55,
had: 0.4,
some: 0.28,
terribly: 0.01,
delicious: 1.2,
carrots: 0.8,
},
negative: {
I: 0.54,
had: 0.4,
some: 0.28,
terribly: 2.01,
delicious: 0.02,
carrots: 0.4,
},
},
});
console.log(response1);
const response2 = await client.search({
index: "my-index-000001",
query: {
term: {
impact: {
value: "delicious",
},
},
},
});
console.log(response2);
PUT my-index-000001
{
"mappings": {
"properties": {
"text": {
"type": "text",
"analyzer": "standard"
},
"impact": {
"type": "sparse_vector"
},
"positive": {
"type": "sparse_vector"
},
"negative": {
"type": "sparse_vector"
}
}
}
}
POST my-index-000001/_doc
{
"text": "I had some terribly delicious carrots.",
"impact": [{"I": 0.55, "had": 0.4, "some": 0.28, "terribly": 0.01, "delicious": 1.2, "carrots": 0.8},
{"I": 0.54, "had": 0.4, "some": 0.28, "terribly": 2.01, "delicious": 0.02, "carrots": 0.4}],
"positive": {"I": 0.55, "had": 0.4, "some": 0.28, "terribly": 0.01, "delicious": 1.2, "carrots": 0.8},
"negative": {"I": 0.54, "had": 0.4, "some": 0.28, "terribly": 2.01, "delicious": 0.02, "carrots": 0.4}
}
GET my-index-000001/_search
{
"query": {
"term": {
"impact": {
"value": "delicious"
}
}
}
}
sparse_vector 字段不能包含在 8.0 到 8.10 之间的 Elasticsearch 版本上 创建 的索引中
sparse_vector 字段仅支持严格的正值。负值将被拒绝。
sparse_vector 字段不支持 分析器、查询、排序或聚合。它们只能在专门的查询中使用。建议在此类字段上使用的查询是 sparse_vector 查询。它们也可以在传统的 text_expansion 查询中使用。
sparse_vector 字段仅保留 9 个有效位的精度，这转化为大约 0.4% 的相对误差。