DatabricksEmbeddings 集成

import getpass
import os

os.environ["DATABRICKS_HOST"] = "https://your-workspace.cloud.databricks.com"
if "DATABRICKS_TOKEN" not in os.environ:
    os.environ["DATABRICKS_TOKEN"] = getpass.getpass(
        "Enter your Databricks access token: "
    )

pip install -qU databricks-langchain

from databricks_langchain import DatabricksEmbeddings

embeddings = DatabricksEmbeddings(
    endpoint="databricks-bge-large-en",
    # 如果需要，指定嵌入查询和文档的参数
    # query_params={...},
    # document_params={...},
)

# 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=embeddings,
)

# 将向量存储用作检索器
retriever = vectorstore.as_retriever()

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

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

single_vector = embeddings.embed_query(text)
print(str(single_vector)[:100])  # 显示向量的前 100 个字符

text2 = (
    "LangGraph is a library for building stateful, multi-actor applications with LLMs"
)
two_vectors = embeddings.embed_documents([text, text2])
for vector in two_vectors:
    print(str(vector)[:100])  # 显示向量的前 100 个字符

import asyncio


async def async_example():
    single_vector = await embeddings.aembed_query(text)
    print(str(single_vector)[:100])  # 显示向量的前 100 个字符


asyncio.run(async_example())