AwaDB

AwaDB 是一种用于搜索和存储由 LLM 应用程序使用的嵌入向量的 AI 本地数据库。

本笔记本展示了如何使用与 AwaDB 相关的功能。

%pip install --upgrade --quiet  awadb

from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import AwaDB
from langchain_text_splitters import CharacterTextSplitter

loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=100, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

db = AwaDB.from_documents(docs)
query = "What did the president say about Ketanji Brown Jackson"
docs = db.similarity_search(query)

print(docs[0].page_content)

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.

使用分数进行相似性搜索

返回的距离分数在 0-1 之间。0 表示不相似，1 表示最相似。

docs = db.similarity_search_with_score(query)

print(docs[0])

(Document(page_content='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.', metadata={'source': '../../how_to/state_of_the_union.txt'}), 0.561813814013747)

恢复之前创建并添加数据的表

AwaDB 会自动保留已添加的文档数据。

如果您想要恢复之前创建并添加的表，只需按照以下步骤操作：

import awadb
awadb_client = awadb.Client()
ret = awadb_client.Load("langchain_awadb")
if ret:
    print("awadb load table success")
else:
    print("awadb load table failed")

awadb load table success