WatsonxEmbeddings 集成

import os
from getpass import getpass

watsonx_api_key = getpass()
os.environ["WATSONX_APIKEY"] = watsonx_api_key

import os

os.environ["WATSONX_URL"] = "your service instance url"
os.environ["WATSONX_TOKEN"] = "your token for accessing the CLOUD or CPD cluster"
os.environ["WATSONX_PASSWORD"] = "your password for accessing the CPD cluster"
os.environ["WATSONX_USERNAME"] = "your username for accessing the CPD cluster"
os.environ["WATSONX_INSTANCE_ID"] = "your instance_id for accessing the CPD cluster"

!pip install -qU langchain-ibm

from ibm_watsonx_ai.metanames import EmbedTextParamsMetaNames

embed_params = {
    EmbedTextParamsMetaNames.TRUNCATE_INPUT_TOKENS: 3,
    EmbedTextParamsMetaNames.RETURN_OPTIONS: {"input_text": True},
}

from langchain_ibm import WatsonxEmbeddings

watsonx_embedding = WatsonxEmbeddings(
    model_id="ibm/granite-embedding-107m-multilingual",
    url="https://us-south.ml.cloud.ibm.com",
    project_id="PASTE YOUR PROJECT_ID HERE",
    params=embed_params,
)

watsonx_embedding = WatsonxEmbeddings(
    model_id="ibm/granite-embedding-107m-multilingual",
    url="PASTE YOUR URL HERE",
    username="PASTE YOUR USERNAME HERE",
    password="PASTE YOUR PASSWORD HERE",
    instance_id="openshift",
    version="4.8",
    project_id="PASTE YOUR PROJECT_ID HERE",
    params=embed_params,
)

from ibm_watsonx_ai import APIClient

api_client = APIClient(...)

watsonx_embedding = WatsonxEmbeddings(
    model_id="ibm/granite-embedding-107m-multilingual",
    watsonx_client=api_client,
)

# 使用示例文本创建向量存储
from langchain_core.vectorstores import InMemoryVectorStore

text = "LangChain is the framework for building context-aware reasoning applications"

vectorstore = InMemoryVectorStore.from_texts(
    [text],
    embedding=watsonx_embedding,
)

# 使用向量存储作为检索器
retriever = vectorstore.as_retriever()

# 检索最相似的文本
retrieved_documents = retriever.invoke("What is LangChain?")

# 显示检索到的文档内容
retrieved_documents[0].page_content

'LangChain is the framework for building context-aware reasoning applications'

text = "This is a test document."

query_result = watsonx_embedding.embed_query(text)
query_result[:5]

[0.009447193, -0.024981951, -0.026013248, -0.040483937, -0.05780445]

texts = ["This is a content of the document", "This is another document"]

doc_result = watsonx_embedding.embed_documents(texts)
doc_result[0][:5]

[0.009447167, -0.024981938, -0.02601326, -0.04048393, -0.05780444]