Hologres¶

Hologres 是一款一站式实时数据仓库，支持高性能 OLAP 分析和高 QPS 在线服务。

要运行此 Notebook，您需要在云端运行一个 Hologres 实例。您可以通过此链接获取一个。

创建实例后，您可以使用Hologres 控制台找到以下配置：

In [ ]

test_hologres_config = {
    "host": "<host>",
    "port": 80,
    "user": "<user>",
    "password": "<password>",
    "database": "<database>",
    "table_name": "<table_name>",
}

test_hologres_config = { "host": "", "port": 80, "user": "", "password": "", "database": "", "table_name": "", }

顺便说一下，您需要确保已安装 llama-index

In [ ]

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

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

In [ ]

!pip install llama-index

!pip install llama-index

导入所需的包依赖：¶

In [ ]

from llama_index.core import (
    VectorStoreIndex,
    SimpleDirectoryReader,
    StorageContext,
)
from llama_index.vector_stores.hologres import HologresVectorStore

from llama_index.core import ( VectorStoreIndex, SimpleDirectoryReader, StorageContext, ) from llama_index.vector_stores.hologres import HologresVectorStore

加载一些示例数据：¶

In [ ]

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

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

  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
100 75042  100 75042    0     0  31985      0  0:00:02  0:00:02 --:--:-- 31987

读取数据：¶

In [ ]

# load documents
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()
print(f"Total documents: {len(documents)}")
print(f"First document, id: {documents[0].doc_id}")
print(f"First document, hash: {documents[0].hash}")
print(
    "First document, text"
    f" ({len(documents[0].text)} characters):\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"第一个文档，ID: {documents[0].doc_id}") print(f"第一个文档，哈希: {documents[0].hash}") print( "第一个文档，文本" f" ({len(documents[0].text)} 字符):\n{'='*20}\n{documents[0].text[:360]} ..." )

Total documents: 1
First document, id: 824dafc0-0aa1-4c80-b99c-33895cfc606a
First document, hash: 8430b3bdb65ee0a7853463b71e7e1e20beee3a3ce15ef3ec714919f8653b2eb9
First document, text (75014 characters):
====================


What I Worked On

February 2021

Before college the two main things I worked on, outside of school, were writing and programming. I didn't write essays. I wrote what beginning writers were supposed to write then, and probably still are: short stories. My stories were awful. They had hardly any plot, just characters with strong feelings, which I imagined ma ...

创建 AnalyticDB 向量存储对象：¶

In [ ]

hologres_store = HologresVectorStore.from_param(
    host=test_hologres_config["host"],
    port=test_hologres_config["port"],
    user=test_hologres_config["user"],
    password=test_hologres_config["password"],
    database=test_hologres_config["database"],
    table_name=test_hologres_config["table_name"],
    embedding_dimension=1536,
    pre_delete_table=True,
)

hologres_store = HologresVectorStore.from_param( host=test_hologres_config["host"], port=test_hologres_config["port"], user=test_hologres_config["user"], password=test_hologres_config["password"], database=test_hologres_config["database"], table_name=test_hologres_config["table_name"], embedding_dimension=1536, pre_delete_table=True, )

从文档构建索引：¶

In [ ]

storage_context = StorageContext.from_defaults(vector_store=hologres_store)

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

storage_context = StorageContext.from_defaults(vector_store=hologres_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)

The author was inspired to work on AI due to the influence of a science fiction novel, "The Moon is a Harsh Mistress," which featured an intelligent computer named Mike, and a PBS documentary showcasing Terry Winograd's use of the SHRDLU program. These experiences led the author to believe that creating intelligent machines was an imminent reality and sparked their interest in the field of AI.