Skip to main content
Open In ColabOpen on GitHub

ThirdAI NeuralDB

NeuralDB 是由 ThirdAI 开发的一种对 CPU 友好且可微调的向量存储。

初始化

有以下两种初始化方法:

  • 从头开始:基础模型
  • 从检查点加载:加载之前保存的模型

以下所有初始化方法中,如果设置了THIRDAI_KEY环境变量,则可以省略thirdai_key参数。

ThirdAI API密钥可以在https://www.thirdai.com/try-bolt/获取

您需要使用 langchain-community 安装 pip install -qU langchain-community 才能使用此集成

from langchain_community.vectorstores import NeuralDBVectorStore

# From scratch
vectorstore = NeuralDBVectorStore.from_scratch(thirdai_key="your-thirdai-key")

# From checkpoint
vectorstore = NeuralDBVectorStore.from_checkpoint(
# Path to a NeuralDB checkpoint. For example, if you call
# vectorstore.save("/path/to/checkpoint.ndb") in one script, then you can
# call NeuralDBVectorStore.from_checkpoint("/path/to/checkpoint.ndb") in
# another script to load the saved model.
checkpoint="/path/to/checkpoint.ndb",
thirdai_key="your-thirdai-key",
)

插入文档来源

vectorstore.insert(
# If you have PDF, DOCX, or CSV files, you can directly pass the paths to the documents
sources=["/path/to/doc.pdf", "/path/to/doc.docx", "/path/to/doc.csv"],
# When True this means that the underlying model in the NeuralDB will
# undergo unsupervised pretraining on the inserted files. Defaults to True.
train=True,
# Much faster insertion with a slight drop in performance. Defaults to True.
fast_mode=True,
)

from thirdai import neural_db as ndb

vectorstore.insert(
# If you have files in other formats, or prefer to configure how
# your files are parsed, then you can pass in NeuralDB document objects
# like this.
sources=[
ndb.PDF(
"/path/to/doc.pdf",
version="v2",
chunk_size=100,
metadata={"published": 2022},
),
ndb.Unstructured("/path/to/deck.pptx"),
]
)

要查询向量存储,您可以使用标准的 LangChain 向量存储方法 similarity_search,该方法返回一个 LangChain Document 对象列表。每个文档对象代表来自索引文件的一段文本。例如,它可能包含来自某个已索引 PDF 文件的一个段落。除了文本内容外,文档的元数据字段还包含诸如文档 ID、文档来源(即该文档来自哪个文件)以及文档的匹配得分等信息。

# This returns a list of LangChain Document objects
documents = vectorstore.similarity_search("query", k=10)

微调

NeuralDBVectorStore 可以根据用户行为和特定领域的知识进行微调。它可以通过两种方式进行微调:

  1. 关联:向量数据库将源短语与目标短语相关联。当向量数据库看到源短语时,它也会考虑与目标短语相关的结果。
  2. 点赞:向量数据库会为特定查询提升某个文档的评分。这在您希望根据用户行为微调向量数据库时非常有用。例如,如果用户搜索“汽车是如何制造的”并喜欢返回的 ID 为 52 的文档,那么我们可以针对查询“汽车是如何制造的”为 ID 为 52 的文档进行点赞。
vectorstore.associate(source="source phrase", target="target phrase")
vectorstore.associate_batch(
[
("source phrase 1", "target phrase 1"),
("source phrase 2", "target phrase 2"),
]
)

vectorstore.upvote(query="how is a car manufactured", document_id=52)
vectorstore.upvote_batch(
[
("query 1", 52),
("query 2", 20),
]
)