pgvecto.rs¶

首先，您可能需要安装依赖项

In [ ]

%pip install llama-index-vector-stores-pgvecto-rs

%pip install llama-index-vector-stores-pgvecto-rs

In [ ]

%pip install llama-index "pgvecto_rs[sdk]"

%pip install llama-index "pgvecto_rs[sdk]"

然后按照官方文档的建议启动 pgvecto.rs 服务器

In [ ]

!docker run --name pgvecto-rs-demo -e POSTGRES_PASSWORD=mysecretpassword -p 5432:5432 -d tensorchord/pgvecto-rs:latest

!docker run --name pgvecto-rs-demo -e POSTGRES_PASSWORD=mysecretpassword -p 5432:5432 -d tensorchord/pgvecto-rs:latest

设置日志记录器。

In [ ]

import logging
import os
import sys

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

import logging import os import sys logging.basicConfig(stream=sys.stdout, level=logging.INFO) logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

创建一个 pgvecto_rs 客户端¶

In [ ]

from pgvecto_rs.sdk import PGVectoRs

URL = "postgresql+psycopg://{username}:{password}@{host}:{port}/{db_name}".format(
    port=os.getenv("DB_PORT", "5432"),
    host=os.getenv("DB_HOST", "localhost"),
    username=os.getenv("DB_USER", "postgres"),
    password=os.getenv("DB_PASS", "mysecretpassword"),
    db_name=os.getenv("DB_NAME", "postgres"),
)

client = PGVectoRs(
    db_url=URL,
    collection_name="example",
    dimension=1536,  # Using OpenAI’s text-embedding-ada-002
)

from pgvecto_rs.sdk import PGVectoRs URL = "postgresql+psycopg://{username}:{password}@{host}:{port}/{db_name}".format( port=os.getenv("DB_PORT", "5432"), host=os.getenv("DB_HOST", "localhost"), username=os.getenv("DB_USER", "postgres"), password=os.getenv("DB_PASS", "mysecretpassword"), db_name=os.getenv("DB_NAME", "postgres"), ) client = PGVectoRs( db_url=URL, collection_name="example", dimension=1536, # 使用 OpenAI 的 text-embedding-ada-002 )

设置 OpenAI¶

In [ ]

import os

os.environ["OPENAI_API_KEY"] = "sk-..."

import os os.environ["OPENAI_API_KEY"] = "sk-..."

加载文档，构建 PGVectoRsStore 和 VectorStoreIndex¶

In [ ]

from IPython.display import Markdown, display

from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
from llama_index.vector_stores.pgvecto_rs import PGVectoRsStore

from IPython.display import Markdown, display from llama_index.core import SimpleDirectoryReader, VectorStoreIndex from llama_index.vector_stores.pgvecto_rs import PGVectoRsStore

下载数据

In [ ]

!mkdir -p 'data/paul_graham/'
!wget '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/' !wget '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'

In [ ]

# load documents
documents = SimpleDirectoryReader("./data/paul_graham").load_data()

# 加载文档 documents = SimpleDirectoryReader("./data/paul_graham").load_data()

In [ ]

# initialize without metadata filter
from llama_index.core import StorageContext

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

# 初始化时不带元数据过滤器 from llama_index.core import StorageContext vector_store = PGVectoRsStore(client=client) storage_context = StorageContext.from_defaults(vector_store=vector_store) index = VectorStoreIndex.from_documents( documents, storage_context=storage_context )

查询索引¶

In [ ]

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")

# 将日志级别设置为 DEBUG 以获取更详细的输出 query_engine = index.as_query_engine() response = query_engine.query("作者从小都做了些什么？")

INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"

In [ ]

display(Markdown(f"<b>{response}</b>"))

display(Markdown(f"{response}"))

作者从小就开始写作和编程。他们写短篇小说，也尝试在 IBM 1401 计算机上编写程序。后来他们得到了一台微型计算机，并开始更广泛地进行编程，编写简单的游戏和文字处理器。