Amazon DocumentDB 集成

!pip install pymongo

import getpass

# DocumentDB 连接字符串
# 例如："mongodb://{username}:{pass}@{cluster_endpoint}:{port}/?{params}"
CONNECTION_STRING = getpass.getpass("DocumentDB 集群 URI:")

INDEX_NAME = "izzy-test-index"
NAMESPACE = "izzy_test_db.izzy_test_collection"
DB_NAME, COLLECTION_NAME = NAMESPACE.split(".")

import getpass
import os

# 设置 OpenAI 环境变量
if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
os.environ["OPENAI_EMBEDDINGS_DEPLOYMENT"] = (
    "smart-agent-embedding-ada"  # 嵌入模型的部署名称
)
os.environ["OPENAI_EMBEDDINGS_MODEL_NAME"] = "text-embedding-ada-002"  # 模型名称

from langchain.vectorstores.documentdb import (
    DocumentDBSimilarityType,
    DocumentDBVectorSearch,
)
from langchain_community.document_loaders import TextLoader
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter

SOURCE_FILE_NAME = "../../how_to/state_of_the_union.txt"

loader = TextLoader(SOURCE_FILE_NAME)
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

# OpenAI 设置
model_deployment = os.getenv(
    "OPENAI_EMBEDDINGS_DEPLOYMENT", "smart-agent-embedding-ada"
)
model_name = os.getenv("OPENAI_EMBEDDINGS_MODEL_NAME", "text-embedding-ada-002")


openai_embeddings: [`OpenAIEmbeddings`](https://reference.langchain.com/python/langchain-openai/embeddings/base/OpenAIEmbeddings) = OpenAIEmbeddings(
    deployment=model_deployment, model=model_name
)

from pymongo import MongoClient

INDEX_NAME = "izzy-test-index-2"
NAMESPACE = "izzy_test_db.izzy_test_collection"
DB_NAME, COLLECTION_NAME = NAMESPACE.split(".")

client: MongoClient = MongoClient(CONNECTION_STRING)
collection = client[DB_NAME][COLLECTION_NAME]

model_deployment = os.getenv(
    "OPENAI_EMBEDDINGS_DEPLOYMENT", "smart-agent-embedding-ada"
)
model_name = os.getenv("OPENAI_EMBEDDINGS_MODEL_NAME", "text-embedding-ada-002")

vectorstore = DocumentDBVectorSearch.from_documents(
    documents=docs,
    embedding=openai_embeddings,
    collection=collection,
    index_name=INDEX_NAME,
)

# 上述模型使用的维度数
dimensions = 1536

# 指定相似度算法，有效选项为：
#   cosine (COS)、euclidean (EUC)、dotProduct (DOT)
similarity_algorithm = DocumentDBSimilarityType.COS

vectorstore.create_index(dimensions, similarity_algorithm)

{ 'createdCollectionAutomatically' : false,
   'numIndexesBefore' : 1,
   'numIndexesAfter' : 2,
   'ok' : 1,
   'operationTime' : Timestamp(1703656982, 1)}

# 在查询的嵌入与文档的嵌入之间执行相似度搜索
query = "What did the President say about Ketanji Brown Jackson"
docs = vectorstore.similarity_search(query)

print(docs[0].page_content)

Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you're at it, pass the Disclose Act so Americans can know who is funding our elections.

Tonight, I'd like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.

One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.

And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation's top legal minds, who will continue Justice Breyer's legacy of excellence.

vectorstore = DocumentDBVectorSearch.from_connection_string(
    connection_string=CONNECTION_STRING,
    namespace=NAMESPACE,
    embedding=openai_embeddings,
    index_name=INDEX_NAME,
)

# 在查询与已导入文档之间执行相似度搜索
query = "What did the president say about Ketanji Brown Jackson"
docs = vectorstore.similarity_search(query)

print(docs[0].page_content)

Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you're at it, pass the Disclose Act so Americans can know who is funding our elections.

Tonight, I'd like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.

One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.

And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation's top legal minds, who will continue Justice Breyer's legacy of excellence.

# 在查询与已导入文档之间执行相似度搜索
query = "Which stats did the President share about the U.S. economy"
docs = vectorstore.similarity_search(query)

print(docs[0].page_content)

And unlike the $2 Trillion tax cut passed in the previous administration that benefitted the top 1% of Americans, the American Rescue Plan helped working people—and left no one behind.

And it worked. It created jobs. Lots of jobs.

In fact—our economy created over 6.5 Million new jobs just last year, more jobs created in one year
than ever before in the history of America.

Our economy grew at a rate of 5.7% last year, the strongest growth in nearly 40 years, the first step in bringing fundamental change to an economy that hasn't worked for the working people of this nation for too long.

For the past 40 years we were told that if we gave tax breaks to those at the very top, the benefits would trickle down to everyone else.

But that trickle-down theory led to weaker economic growth, lower wages, bigger deficits, and the widest gap between those at the top and everyone else in nearly a century.

qa_retriever = vectorstore.as_retriever(
    search_type="similarity",
    search_kwargs={"k": 25},
)

from langchain_core.prompts import PromptTemplate

prompt_template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.

{context}

Question: {question}
"""
PROMPT = PromptTemplate(
    template=prompt_template, input_variables=["context", "question"]
)

from langchain_classic.chains import RetrievalQA
from langchain_openai import OpenAI

qa = RetrievalQA.from_chain_type(
    llm=OpenAI(),
    chain_type="stuff",
    retriever=qa_retriever,
    return_source_documents=True,
    chain_type_kwargs={"prompt": PROMPT},
)

docs = qa({"query": "gpt-4 compute requirements"})

print(docs["result"])
print(docs["source_documents"])