pip3 install dashvector dashscope

import os
import dashscopefrom dashscope import TextEmbedding
from dashvector import Client, Doc
# 文档批量处理，batch_size表示批量处理的文档数量def prepare_data(path, batch_size=25):    batch_docs = []    for file in os.listdir(path):        with open(path + '/' + file, 'r', encoding='utf-8') as f:            batch_docs.append(f.read())            if len(batch_docs) == batch_size:                yield batch_docs                batch_docs = []
    if batch_docs:        yield batch_docs
# 生成embeddingsdef generate_embeddings(news):    rsp = TextEmbedding.call(        model=TextEmbedding.Models.text_embedding_v1,        input=news    )    embeddings = [record['embedding'] for record in rsp.output['embeddings']]    return embeddings if isinstance(news, list) else embeddings[0]

if __name__ == '__main__':    dashscope.api_key = '{your-dashscope-api-key}'  #注意，这个不是DashVector的apikey，不要混了        # 初始化 dashvector client    client = Client(      api_key='{your-dashvector-api-key}',      endpoint='{your-dashvector-cluster-endpoint}'    )
    # 创建集合：指定集合名称和向量维度, text_embedding_v1 模型产生的向量统一为 1536 维    rsp = client.create('news_embedings', 1536)    assert rsp
    # 加载语料    id = 0    collection = client.get('news_embedings')    for news in list(prepare_data('CEC-Corpus/raw corpus/allSourceText')):        ids = [id + i for i, _ in enumerate(news)]        id += len(news)                vectors = generate_embeddings(news)        # 写入 dashvector 构建索引        rsp = collection.upsert(            [                Doc(id=str(id), vector=vector, fields={"raw": doc})                for id, vector, doc in zip(ids, vectors, news)            ]        )        assert rsp

from dashvector import Client
from embedding import generate_embeddings

def search_relevant_news(question):    # 初始化 dashvector client    client = Client(      api_key='{your-dashvector-api-key}',      endpoint='{your-dashvector-cluster-endpoint}'    )
    # 获取刚刚存入的集合    collection = client.get('news_embedings')    assert collection
    # 向量检索：指定 topk = 1     rsp = collection.query(generate_embeddings(question), output_fields=['raw'],                           topk=1)    assert rsp    return rsp.output[0].fields['raw']

from dashscope import Generation

def answer_question(question, context):    prompt = f'''请基于```内的内容回答问题。"	```	{context}	```	我的问题是：{question}。    '''        rsp = Generation.call(model='qwen-turbo', prompt=prompt)    return rsp.output.text

<!-- https://mvnrepository.com/artifact/com.alibaba/dashscope-sdk-java --><dependency>    <groupId>com.alibaba</groupId>    <artifactId>dashscope-sdk-java</artifactId>    <version>the-latest-version</version></dependency>

// 需要引入的依赖包import com.alibaba.dashscope.embeddings.TextEmbedding;import com.alibaba.dashscope.embeddings.TextEmbeddingParam;import com.alibaba.dashscope.embeddings.TextEmbeddingResult;import com.alibaba.dashscope.utils.JsonUtils;
/** * 生成文档的embedding */TextEmbeddingParam param = TextEmbeddingParam.builder()        .apiKey(llmAliConfig.getDashscopeApiKey())        .model(TextEmbedding.Models.TEXT_EMBEDDING_V1)        .text(query)        .build();TextEmbedding textEmbedding = new TextEmbedding();TextEmbeddingResult textEmbeddingResult = textEmbedding.call(param);log.info("query textEmbeddingResult:{}", textEmbeddingResult.getOutput());/** * 封装文档检索 request, 传入embedding */List<Double> embeddings = textEmbeddingResult.getOutput().getEmbeddings().get(0).getEmbedding();

public static HalfDuplexClient getHalfDuplexClient(ConnectionOptions options, String protocol) {        if (protocol == null) {            protocol = "https";        }
        if (options == null) {            return (HalfDuplexClient)(protocol.toLowerCase().startsWith("http") ? new OkHttpHttpClient(OkHttpClientFactory.getOkHttpClient()) : new OkHttpWebSocketClient(OkHttpClientFactory.getOkHttpClient()));        } else {            return (HalfDuplexClient)(protocol.toLowerCase().startsWith("http") ? new OkHttpHttpClient(OkHttpClientFactory.getNewOkHttpClient(options)) : new OkHttpWebSocketClient(OkHttpClientFactory.getNewOkHttpClient(options)));        }    }

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation' \--header 'Authorization: Bearer <your-dashscope-api-key>' \--header 'Content-Type: application/json' \--data '{    "model": "belle-llama-13b-2m-v1",    "input": {        "prompt": "Human:你好\n\nAssistant:"    },    "parameters":{    }}'

{	"output": {		"finish_reason": "stop",		"text": "你好！很高兴为你提供帮助。有什么我可以解答的问题或者需要协助的吗？"	},	"usage": {		"total_tokens": 42,		"output_tokens": 17,		"input_tokens": 25	},	"request_id": "44ec45fc-910f-91fb-971a-d3b6c29e969d"}

curl -XPOST \  -H 'dashvector-auth-token: YOUR_API_KEY' \  -H 'Content-Type: application/json' \  -d '{    "vector": [0.1, 0.2, 0.3, 0.4],    "sparse_vector":{"1":0.4, "10000":0.6, "222222":0.8},    "topk": 1,    "include_vector": true  }' https://YOUR_CLUSTER_ENDPOINT/v1/collections/quickstart/query

# {#   "code":0,#   "request_id":"ad84f7a0-b4b2-4023-ae80-b6f092609a53",#   "message":"Success",#   "output":[#     {#       "id":"2",#       "vector":[#         0.10000000149011612,#         0.20000000298023224,#         0.30000001192092896,#         0.4000000059604645#       ],#       "fields":{"name":null,"weight":null,"age":null},#       "score":1.46,#       "sparse_vector":{#         "10000":0.6,#         "1":0.4,#         "222222":0.8#       }#     }#   ]# }