AnalyticDB¶

AnalyticDB for PostgreSQL是一个大规模并行处理（MPP）数据仓库服务，旨在在线分析大量数据。

要运行此笔记本，您需要在云中运行一个AnalyticDB for PostgreSQL实例（您可以在common-buy.aliyun.com获取一个实例)。

创建实例后，您应该通过API或在实例详细信息网页的“帐号管理”中创建一个管理账户。

您应该确保已安装llama-index：

In [ ]:

%pip install llama-index-vector-stores-analyticdb

%pip install llama-index-vector-stores-analyticdb

In [ ]:

!pip install llama-index

!pip install llama-index

请提供参数：¶

In [ ]:

import os
import getpass

# 阿里云RAM的AK和SK：
alibaba_cloud_ak = ""
alibaba_cloud_sk = ""

# 实例信息：
region_id = "cn-hangzhou"  # 特定实例的区域ID
instance_id = "gp-xxxx"  # ADB实例ID
account = "test_account"  # 由API创建或在实例详细页面的“帐号管理”中创建的实例帐号名称
account_password = ""  # 实例帐号密码

import os import getpass # 阿里云RAM的AK和SK： alibaba_cloud_ak = "" alibaba_cloud_sk = "" # 实例信息： region_id = "cn-hangzhou" # 特定实例的区域ID instance_id = "gp-xxxx" # ADB实例ID account = "test_account" # 由API创建或在实例详细页面的“帐号管理”中创建的实例帐号名称 account_password = "" # 实例帐号密码

导入所需的包依赖项：¶

In [ ]:

from llama_index.core import (
    VectorStoreIndex,
    SimpleDirectoryReader,
    StorageContext,
)
from llama_index.vector_stores.analyticdb import AnalyticDBVectorStore

from llama_index.core import ( VectorStoreIndex, SimpleDirectoryReader, StorageContext, ) from llama_index.vector_stores.analyticdb import AnalyticDBVectorStore

AnalyticDB¶

AnalyticDB for PostgreSQL是一个大规模并行处理（MPP）数据仓库服务，旨在在线分析大量数据。

要运行此笔记本，您需要在云中运行一个AnalyticDB for PostgreSQL实例（您可以在common-buy.aliyun.com获取一个实例)。

创建实例后，您应该通过API或在实例详细信息网页的“帐号管理”中创建一个管理账户。

您应该确保已安装llama-index：

In [ ]:

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

!mkdir -p 'data/paul_graham/' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

读取数据：¶

In [ ]:

# 加载文档
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()
print(f"总文档数：{len(documents)}")
print(f"第一篇文档，id：{documents[0].doc_id}")
print(f"第一篇文档，哈希值：{documents[0].hash}")
print(
    "第一篇文档，文本"
    f"（{len(documents[0].text)} 个字符）：\n{'='*20}\n{documents[0].text[:360]} ..."
)

# 加载文档 documents = SimpleDirectoryReader("./data/paul_graham/").load_data() print(f"总文档数：{len(documents)}") print(f"第一篇文档，id：{documents[0].doc_id}") print(f"第一篇文档，哈希值：{documents[0].hash}") print( "第一篇文档，文本" f"（{len(documents[0].text)} 个字符）：\n{'='*20}\n{documents[0].text[:360]} ..." )

创建 AnalyticDB Vector 存储对象：¶

In [ ]:

analytic_db_store = AnalyticDBVectorStore.from_params(
    access_key_id=alibaba_cloud_ak,
    access_key_secret=alibaba_cloud_sk,
    region_id=region_id,
    instance_id=instance_id,
    account=account,
    account_password=account_password,
    namespace="llama",
    collection="llama",
    metrics="cosine",
    embedding_dimension=1536,
)

analytic_db_store = AnalyticDBVectorStore.from_params( access_key_id=alibaba_cloud_ak, access_key_secret=alibaba_cloud_sk, region_id=region_id, instance_id=instance_id, account=account, account_password=account_password, namespace="llama", collection="llama", metrics="cosine", embedding_dimension=1536, )

从文档中构建索引：¶

In [ ]:

storage_context = StorageContext.from_defaults(vector_store=analytic_db_store)

index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

storage_context = StorageContext.from_defaults(vector_store=analytic_db_store) index = VectorStoreIndex.from_documents( documents, storage_context=storage_context )

使用索引进行查询：¶

In [ ]:

query_engine = index.as_query_engine()
response = query_engine.query("Why did the author choose to work on AI?")

print(response.response)

query_engine = index.as_query_engine() response = query_engine.query("Why did the author choose to work on AI?") print(response.response)

删除集合：¶

In [ ]:

analytic_db_store.delete_collection()

analytic_db_store.delete_collection()