有关如何使用 Elasticsearch 中的托管嵌入模型生成嵌入的分步指南

实例化该类的最简单方法是 ElasticsearchEmbeddings either

• - 使用 from_credentials 如果您使用 Elastic Cloud，则使用构造函数
• - 或使用 from_es_connection 带有任何 Elasticsearch 集群的构造函数

!pip -q install langchain-elasticsearch

from langchain_elasticsearch import ElasticsearchEmbeddings

# Define the model ID
model_id = "your_model_id"

测试 from_credentials

这需要 Elastic Cloud cloud_id

# Instantiate ElasticsearchEmbeddings using credentials
embeddings = ElasticsearchEmbeddings.from_credentials(
    model_id,
    es_cloud_id="your_cloud_id",
    es_user="your_user",
    es_password="your_password",
)

# Create embeddings for multiple documents
documents = [
    "This is an example document.",
    "Another example document to generate embeddings for.",
]
document_embeddings = embeddings.embed_documents(documents)

# Print document embeddings
for i, embedding in enumerate(document_embeddings):
    print(f"Embedding for document {i + 1}: {embedding}")

# Create an embedding for a single query
query = "This is a single query."
query_embedding = embeddings.embed_query(query)

# Print query embedding
print(f"Embedding for query: {query_embedding}")

使用现有 Elasticsearch 客户端连接进行测试

这可用于任何 Elasticsearch 部署

# Create Elasticsearch connection
from elasticsearch import Elasticsearch

es_connection = Elasticsearch(
    hosts=["https://es_cluster_url:port"], basic_auth=("user", "password")
)

# Instantiate ElasticsearchEmbeddings using es_connection
embeddings = ElasticsearchEmbeddings.from_es_connection(
    model_id,
    es_connection,
)

# Create embeddings for multiple documents
documents = [
    "This is an example document.",
    "Another example document to generate embeddings for.",
]
document_embeddings = embeddings.embed_documents(documents)

# Print document embeddings
for i, embedding in enumerate(document_embeddings):
    print(f"Embedding for document {i + 1}: {embedding}")

# Create an embedding for a single query
query = "This is a single query."
query_embedding = embeddings.embed_query(query)

# Print query embedding
print(f"Embedding for query: {query_embedding}")