Bedrock 嵌入模型¶

如果您在 Colab 上打开此 Notebook，可能需要先安装 LlamaIndex 🦙。

In [ ]:

%pip install llama-index-embeddings-bedrock

%pip install llama-index-embeddings-bedrock

In [ ]:

import os

from llama_index.embeddings.bedrock import BedrockEmbedding

import os from llama_index.embeddings.bedrock import BedrockEmbedding

In [ ]:

embed_model = BedrockEmbedding(
    aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
    aws_secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
    aws_session_token=os.getenv("AWS_SESSION_TOKEN"),
    region_name="<aws-region>",
    profile_name="<aws-profile>",
)

embed_model = BedrockEmbedding( aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID"), aws_secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY"), aws_session_token=os.getenv("AWS_SESSION_TOKEN"), region_name="", profile_name="", )

In [ ]:

embedding = embed_model.get_text_embedding("hello world")

embedding = embed_model.get_text_embedding("hello world")

查看支持的模型列表¶

要查询 LlamaIndex 上 Amazon Bedrock 支持的所有模型列表，可调用 BedrockEmbedding.list_supported_models() 方法，操作如下。

In [ ]:

from llama_index.embeddings.bedrock import BedrockEmbedding
import json

supported_models = BedrockEmbedding.list_supported_models()
print(json.dumps(supported_models, indent=2))

from llama_index.embeddings.bedrock import BedrockEmbedding import json supported_models = BedrockEmbedding.list_supported_models() print(json.dumps(supported_models, indent=2))

服务提供商：亚马逊¶

Amazon Bedrock Titan 嵌入模型。

In [ ]:

from llama_index.embeddings.bedrock import BedrockEmbedding

model = BedrockEmbedding(model_name="amazon.titan-embed-g1-text-02")
embeddings = model.get_text_embedding("hello world")
print(embeddings)

from llama_index.embeddings.bedrock import BedrockEmbedding model = BedrockEmbedding(model_name="amazon.titan-embed-g1-text-02") embeddings = model.get_text_embedding("hello world") print(embeddings)

服务提供商：Cohere¶

cohere.embed-english-v3¶

In [ ]:

model = BedrockEmbedding(model_name="cohere.embed-english-v3")
coherePayload = ["This is a test document", "This is another test document"]

embed1 = model.get_text_embedding("This is a test document")
print(embed1)

embeddings = model.get_text_embedding_batch(coherePayload)
print(embeddings)

model = BedrockEmbedding(model_name="cohere.embed-english-v3") coherePayload = ["This is a test document", "This is another test document"] embed1 = model.get_text_embedding("This is a test document") print(embed1) embeddings = model.get_text_embedding_batch(coherePayload) print(embeddings)

Cohere 的多语言嵌入技术¶

In [ ]:

model = BedrockEmbedding(model_name="cohere.embed-multilingual-v3")
coherePayload = [
    "This is a test document",
    "తెలుగు అనేది ద్రావిడ భాషల కుటుంబానికి చెందిన భాష.",
    "Esto es una prueba de documento multilingüe.",
    "攻殻機動隊",
    "Combien de temps ça va prendre ?",
    "Документ проверен",
]
embeddings = model.get_text_embedding_batch(coherePayload)
print(embeddings)

model = BedrockEmbedding(model_name="cohere.embed-multilingual-v3") coherePayload = [ "This is a test document", "తెలుగు అనేది ద్రావిడ భాషల కుటుంబానికి చెందిన భాష.", "Esto es una prueba de documento multilingüe.", "攻殻機動隊", "Combien de temps ça va prendre ?", "Документ проверен", ] embeddings = model.get_text_embedding_batch(coherePayload) print(embeddings)