在这篇文章里，我将使用 gpt-oss 大模型来展示如何在 AI agent builder 中进行使用。有关 gpt-oss 的安装请参考文章 "如何使用 Ollama 在本地设置和运行 GPT-OSS"。我们需要按照这篇文章来安装我们的 gpt-oss。
细心的开发者，可能在之前的版本中运行如下的查询：
我们研究了一下原因。这个其实就我们在写入文档时，我们的 mapping 是这样定义的：
PUT /people
{
"mappings": {
"properties": {
"id": {
"type": "integer"
},
"name": {
"type": "text"
},
"description": {
"type": "text",
"copy_to": "des_semantic"
},
"des_semantic": {
"type": "semantic_text"
},
"sex": {
"type": "keyword"
},
"age": {
"type": "integer"
},
"address": {
"type": "text"
},
"location": {
"type": "geo_point"
}
}
}
}很显然，des_semantic 在没有定义端点的情况下，默认的就是使用系数向量模型 ELSER。我们可以参考文章 "Elasticsearch：使用推理端点及语义搜索演示"。在目前的阶段，由于 ELSER 模型不支持中文，这也导致我们的查询得不到想要的结果。我们可以采用多语言模型。
我们使用如下的 API 来获得所有的 endpoints：
我们可以看到已经为我们定制好的 .multilingual-e5-small-elasticsearch id。我们可以重新定义我们的索引 mapping：
DELETE people
PUT /people
{
"mappings": {
"properties": {
"id": {
"type": "integer"
},
"name": {
"type": "text"
},
"description": {
"type": "text",
"copy_to": "des_semantic"
},
"des_semantic": {
"type": "semantic_text",
"inference_id": ".multilingual-e5-small-elasticsearch"
},
"sex": {
"type": "keyword"
},
"age": {
"type": "integer"
},
"address": {
"type": "text"
},
"location": {
"type": "geo_point"
}
}
}
}然后，我们再次写入文档：
POST /_bulk
{ "index" : { "_index" : "people", "_id" : "1" } }
{ "id": 1, "name" : "John Doe", "description" : "A software developer", "sex" : "Male", "age" : 30, "address" : "123 Elm Street, Springfield", "location": {"lat": 37.7749, "lon": -122.4194} }
{ "index" : { "_index" : "people", "_id" : "2" } }
{ "id": 2, "name" : "Jane Smith", "description" : "A project manager", "sex" : "Female", "age" : 28, "address" : "456 Maple Avenue, Anytown", "location": {"lat": 40.7128, "lon": -74.0060} }
{ "index" : { "_index" : "people", "_id" : "3" } }
{ "id": 3, "name" : "Alice Johnson", "description" : "A graphic designer", "sex" : "Female", "age" : 26, "address" : "789 Oak Lane, Metropolis", "location": {"lat": 34.0522, "lon": -118.2437} }
{ "index" : { "_index" : "people", "_id" : "4" } }
{ "id": 4, "name" : "Bob Brown", "description" : "A marketing specialist", "sex" : "Male", "age" : 32, "address" : "321 Pine Street, Gotham", "location": {"lat": 41.8781, "lon": -87.6298} }
{ "index" : { "_index" : "people", "_id" : "5" } }
{ "id": 5, "name" : "Charlie Davis", "description" : "An IT analyst", "sex" : "Male", "age" : 29, "address" : "654 Cedar Blvd, Star City", "location": {"lat": 29.7604, "lon": -95.3698} }
{ "index" : { "_index" : "people", "_id" : "6" } }
{ "id": 6, "name" : "Diana Prince", "description" : "A diplomat", "sex" : "Female", "age" : 35, "address" : "987 Birch Road, Themyscira", "location": {"lat": 39.9526, "lon": -75.1652} }
{ "index" : { "_index" : "people", "_id" : "7" } }
{ "id": 7, "name" : "Evan Wright", "description" : "A journalist", "sex" : "Male", "age" : 27, "address" : "213 Willow Lane, Central City", "location": {"lat": 33.4484, "lon": -112.0740} }
{ "index" : { "_index" : "people", "_id" : "8" } }
{ "id": 8, "name" : "Fiona Gallagher", "description" : "A nurse", "sex" : "Female", "age" : 31, "address" : "546 Spruce Street, South Side", "location": {"lat": 32.7157, "lon": -117.1611} }
{ "index" : { "_index" : "people", "_id" : "9" } }
{ "id": 9, "name" : "George King", "description" : "A teacher", "sex" : "Male", "age" : 34, "address" : "879 Elm St, Smallville", "location": {"lat": 39.7392, "lon": -104.9903} }
{ "index" : { "_index" : "people", "_id" : "10" } }
{ "id": 10, "name" : "Helen Parr", "description" : "A full-time superhero", "sex" : "Female", "age": 37, "address" : "123 Metro Avenue, Metroville", "location": {"lat": 47.6062, "lon": -122.3321} }我们再次重新查询：
很显然，这次我们得到我们想要的答案了。
最近我们 Elastic 公司收购了 JINA。JINA 支持多模态的嵌入模型，它同时也支持多语言模型。我们可以参考文章 "使用 Jina Embeddings v2 在 Elasticsearch 中进行后期分块" 来进行测试。