跳至主要内容

Yellowbrick

Yellowbrick 是一款弹性、大规模并行处理 (MPP) SQL 数据库,它可以在云和本地运行,使用 Kubernetes 来实现扩展、弹性和云可移植性。Yellowbrick 旨在解决最大、最复杂的关键业务数据仓库用例。Yellowbrick 提供的规模效率也使其能够用作高性能且可扩展的向量数据库,用于使用 SQL 存储和搜索向量。

使用 Yellowbrick 作为 ChatGpt 的向量存储

本教程演示了如何使用 Yellowbrick 作为向量存储来创建由 ChatGpt 支持的简单聊天机器人,以支持检索增强生成 (RAG)。您需要什么

  1. Yellowbrick 沙盒 上的一个帐户
  2. 来自OpenAI 的 api 密钥

本教程分为五个部分。首先,我们将使用 langchain 创建一个基线聊天机器人,与没有向量存储的 ChatGpt 进行交互。其次,我们将创建一个 Yellowbrick 中的嵌入表,该表将表示向量存储。第三,我们将加载一系列文档(Yellowbrick 手册的管理章节)。第四,我们将创建这些文档的向量表示并将它们存储在 Yellowbrick 表中。最后,我们将向改进的聊天机器人发送相同的查询,以查看结果。

# Install all needed libraries
%pip install --upgrade --quiet langchain
%pip install --upgrade --quiet langchain-openai langchain-community
%pip install --upgrade --quiet psycopg2-binary
%pip install --upgrade --quiet tiktoken

设置:输入用于连接到 Yellowbrick 和 OpenAI API 的信息

我们的聊天机器人通过 langchain 库与 ChatGpt 集成,因此您首先需要来自 OpenAI 的 API 密钥

要获取 OpenAI 的 api 密钥

  1. https://platform.openai.com/ 注册
  2. 添加付款方式 - 您不太可能超过免费配额
  3. 创建 API 密钥

您还需要注册 Yellowbrick 沙盒帐户时,欢迎电子邮件中提供的用户名、密码和数据库名称。

以下内容应修改为包含您的 Yellowbrick 数据库和 OpenAPI 密钥的信息

# Modify these values to match your Yellowbrick Sandbox and OpenAI API Key
YBUSER = "[SANDBOX USER]"
YBPASSWORD = "[SANDBOX PASSWORD]"
YBDATABASE = "[SANDBOX_DATABASE]"
YBHOST = "trialsandbox.sandbox.aws.yellowbrickcloud.com"

OPENAI_API_KEY = "[OPENAI API KEY]"
# Import libraries and setup keys / login info
import os
import pathlib
import re
import sys
import urllib.parse as urlparse
from getpass import getpass

import psycopg2
from IPython.display import Markdown, display
from langchain.chains import LLMChain, RetrievalQAWithSourcesChain
from langchain_community.vectorstores import Yellowbrick
from langchain_core.documents import Document
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter

# Establish connection parameters to Yellowbrick. If you've signed up for Sandbox, fill in the information from your welcome mail here:
yellowbrick_connection_string = (
f"postgres://{urlparse.quote(YBUSER)}:{YBPASSWORD}@{YBHOST}:5432/{YBDATABASE}"
)

YB_DOC_DATABASE = "sample_data"
YB_DOC_TABLE = "yellowbrick_documentation"
embedding_table = "my_embeddings"

# API Key for OpenAI. Signup at https://platform.openai.com
os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY

from langchain_core.prompts.chat import (
ChatPromptTemplate,
HumanMessagePromptTemplate,
SystemMessagePromptTemplate,
)

第 1 部分:创建一个由 ChatGpt 支持的基线聊天机器人,但没有向量存储

我们将使用 langchain 查询 ChatGPT。由于没有向量存储,ChatGPT 将没有上下文来回答问题。

# Set up the chat model and specific prompt
system_template = """If you don't know the answer, Make up your best guess."""
messages = [
SystemMessagePromptTemplate.from_template(system_template),
HumanMessagePromptTemplate.from_template("{question}"),
]
prompt = ChatPromptTemplate.from_messages(messages)

chain_type_kwargs = {"prompt": prompt}
llm = ChatOpenAI(
model_name="gpt-3.5-turbo", # Modify model_name if you have access to GPT-4
temperature=0,
max_tokens=256,
)

chain = LLMChain(
llm=llm,
prompt=prompt,
verbose=False,
)


def print_result_simple(query):
result = chain(query)
output_text = f"""### Question:
{query}
### Answer:
{result['text']}
"""
display(Markdown(output_text))


# Use the chain to query
print_result_simple("How many databases can be in a Yellowbrick Instance?")

print_result_simple("What's an easy way to add users in bulk to Yellowbrick?")

第 2 部分:连接到 Yellowbrick 并创建嵌入表

要将您的文档嵌入加载到 Yellowbrick 中,您应该创建自己的表来存储它们。请注意,表所在的 Yellowbrick 数据库必须是 UTF-8 编码的。

在 UTF-8 数据库中创建一个表,使用以下模式,并提供您选择的表名

# Establish a connection to the Yellowbrick database
try:
conn = psycopg2.connect(yellowbrick_connection_string)
except psycopg2.Error as e:
print(f"Error connecting to the database: {e}")
exit(1)

# Create a cursor object using the connection
cursor = conn.cursor()

# Define the SQL statement to create a table
create_table_query = f"""
CREATE TABLE IF NOT EXISTS {embedding_table} (
doc_id uuid NOT NULL,
embedding_id smallint NOT NULL,
embedding double precision NOT NULL
)
DISTRIBUTE ON (doc_id);
truncate table {embedding_table};
"""

# Execute the SQL query to create a table
try:
cursor.execute(create_table_query)
print(f"Table '{embedding_table}' created successfully!")
except psycopg2.Error as e:
print(f"Error creating table: {e}")
conn.rollback()

# Commit changes and close the cursor and connection
conn.commit()
cursor.close()
conn.close()

第 3 部分:从 Yellowbrick 中的现有表中提取要索引的文档

从现有的 Yellowbrick 表中提取文档路径和内容。我们将使用这些文档在下一步中创建嵌入。

yellowbrick_doc_connection_string = (
f"postgres://{urlparse.quote(YBUSER)}:{YBPASSWORD}@{YBHOST}:5432/{YB_DOC_DATABASE}"
)

print(yellowbrick_doc_connection_string)

# Establish a connection to the Yellowbrick database
conn = psycopg2.connect(yellowbrick_doc_connection_string)

# Create a cursor object
cursor = conn.cursor()

# Query to select all documents from the table
query = f"SELECT path, document FROM {YB_DOC_TABLE}"

# Execute the query
cursor.execute(query)

# Fetch all documents
yellowbrick_documents = cursor.fetchall()

print(f"Extracted {len(yellowbrick_documents)} documents successfully!")

# Close the cursor and connection
cursor.close()
conn.close()

第 4 部分:使用文档加载 Yellowbrick 向量存储

遍历文档,将它们拆分成可消化的块,创建嵌入并将它们插入到 Yellowbrick 表中。这大约需要 5 分钟。

# Split documents into chunks for conversion to embeddings
DOCUMENT_BASE_URL = "https://docs.yellowbrick.com/6.7.1/" # Actual URL


separator = "\n## " # This separator assumes Markdown docs from the repo uses ### as logical main header most of the time
chunk_size_limit = 2000
max_chunk_overlap = 200

documents = [
Document(
page_content=document[1],
metadata={"source": DOCUMENT_BASE_URL + document[0].replace(".md", ".html")},
)
for document in yellowbrick_documents
]

text_splitter = RecursiveCharacterTextSplitter(
chunk_size=chunk_size_limit,
chunk_overlap=max_chunk_overlap,
separators=[separator, "\nn", "\n", ",", " ", ""],
)
split_docs = text_splitter.split_documents(documents)

docs_text = [doc.page_content for doc in split_docs]

embeddings = OpenAIEmbeddings()
vector_store = Yellowbrick.from_documents(
documents=split_docs,
embedding=embeddings,
connection_string=yellowbrick_connection_string,
table=embedding_table,
)

print(f"Created vector store with {len(documents)} documents")

第 5 部分:创建一个使用 Yellowbrick 作为向量存储的聊天机器人

接下来,我们添加 Yellowbrick 作为向量存储。向量存储已填充了表示 Yellowbrick 产品文档的管理章节的嵌入。

我们将发送与上面相同的查询,以查看改进的响应。

system_template = """Use the following pieces of context to answer the users question.
Take note of the sources and include them in the answer in the format: "SOURCES: source1 source2", use "SOURCES" in capital letters regardless of the number of sources.
If you don't know the answer, just say that "I don't know", don't try to make up an answer.
----------------
{summaries}"""
messages = [
SystemMessagePromptTemplate.from_template(system_template),
HumanMessagePromptTemplate.from_template("{question}"),
]
prompt = ChatPromptTemplate.from_messages(messages)

vector_store = Yellowbrick(
OpenAIEmbeddings(),
yellowbrick_connection_string,
embedding_table, # Change the table name to reflect your embeddings
)

chain_type_kwargs = {"prompt": prompt}
llm = ChatOpenAI(
model_name="gpt-3.5-turbo", # Modify model_name if you have access to GPT-4
temperature=0,
max_tokens=256,
)
chain = RetrievalQAWithSourcesChain.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=vector_store.as_retriever(search_kwargs={"k": 5}),
return_source_documents=True,
chain_type_kwargs=chain_type_kwargs,
)


def print_result_sources(query):
result = chain(query)
output_text = f"""### Question:
{query}
### Answer:
{result['answer']}
### Sources:
{result['sources']}
### All relevant sources:
{', '.join(list(set([doc.metadata['source'] for doc in result['source_documents']])))}
"""
display(Markdown(output_text))


# Use the chain to query

print_result_sources("How many databases can be in a Yellowbrick Instance?")

print_result_sources("Whats an easy way to add users in bulk to Yellowbrick?")

第 6 部分:引入索引以提高性能

Yellowbrick 还支持使用局部敏感哈希 (LSH) 方法进行索引。这是一种近似最近邻搜索技术,它允许人们以准确性为代价来权衡相似性搜索时间。索引引入了两个新的可调参数

  • 超平面数,它作为参数提供给 create_lsh_index(num_hyperplanes)。文档越多,需要的超平面就越多。LSH 是一种降维形式。原始嵌入被转换为低维向量,其中组件数量与超平面数量相同。
  • 汉明距离,一个整数,表示搜索范围。较小的汉明距离会导致更快的检索,但准确性较低。

以下是如何在加载到 Yellowbrick 中的嵌入上创建索引。我们还将重新运行之前的聊天会话,但这次检索将使用索引。请注意,对于如此少量的文档,您不会在性能方面看到索引的好处。

system_template = """Use the following pieces of context to answer the users question.
Take note of the sources and include them in the answer in the format: "SOURCES: source1 source2", use "SOURCES" in capital letters regardless of the number of sources.
If you don't know the answer, just say that "I don't know", don't try to make up an answer.
----------------
{summaries}"""
messages = [
SystemMessagePromptTemplate.from_template(system_template),
HumanMessagePromptTemplate.from_template("{question}"),
]
prompt = ChatPromptTemplate.from_messages(messages)

vector_store = Yellowbrick(
OpenAIEmbeddings(),
yellowbrick_connection_string,
embedding_table, # Change the table name to reflect your embeddings
)

lsh_params = Yellowbrick.IndexParams(
Yellowbrick.IndexType.LSH, {"num_hyperplanes": 8, "hamming_distance": 2}
)
vector_store.create_index(lsh_params)

chain_type_kwargs = {"prompt": prompt}
llm = ChatOpenAI(
model_name="gpt-3.5-turbo", # Modify model_name if you have access to GPT-4
temperature=0,
max_tokens=256,
)
chain = RetrievalQAWithSourcesChain.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=vector_store.as_retriever(
k=5, search_kwargs={"index_params": lsh_params}
),
return_source_documents=True,
chain_type_kwargs=chain_type_kwargs,
)


def print_result_sources(query):
result = chain(query)
output_text = f"""### Question:
{query}
### Answer:
{result['answer']}
### Sources:
{result['sources']}
### All relevant sources:
{', '.join(list(set([doc.metadata['source'] for doc in result['source_documents']])))}
"""
display(Markdown(output_text))


# Use the chain to query

print_result_sources("How many databases can be in a Yellowbrick Instance?")

print_result_sources("Whats an easy way to add users in bulk to Yellowbrick?")

下一步:

此代码可以修改为提出不同的问题。您也可以将自己的文档加载到向量存储中。langchain 模块非常灵活,可以解析各种各样的文件(包括 HTML、PDF 等)。

您还可以修改它以使用 Huggingface 嵌入模型和 Meta 的 Llama 2 LLM 来获得完全私密的聊天机器人体验。


此页面是否有帮助?


您也可以留下详细的反馈 在 GitHub 上.