Skip to main content
Open In Colab在 GitHub 上打开

ThirdAI 神经网络数据库

NeuralDB 是由 ThirdAI 开发的 CPU 友好且可调的向量存储。

初始化

有两种初始化方法：

  • 从零开始：基本模型
  • From Checkpoint：加载以前保存的模型

对于以下所有初始化方法，thirdai_key如果THIRDAI_KEY环境变量。

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

您需要安装langchain-community跟pip install -qU langchain-community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",
)
API 参考：NeuralDBVectorStore

插入文档源

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 vectorstore，可以使用标准的 LangChain vectorstore 方法similarity_search，它返回 LangChain Document 对象的列表。每个 document 对象都表示索引文件中的一段文本。例如，它可能包含来自某个已编制索引的 PDF 文件的段落。除了文本之外，文档的元数据字段还包含文档的 ID、此文档的来源（它来自哪个文件）以及文档的分数等信息。

# 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：vectorstore 将源短语与目标短语相关联。当 vectorstore 看到源短语时，它还会考虑与目标短语相关的结果。
  2. Upvoting：vectorstore 会提高特定查询的文档分数的权重。当您想根据用户行为微调 vectorstore 时，这非常有用。例如，如果用户搜索 “how is a car manufactured” 并喜欢返回的 id 为 52 的文档，那么我们可以对 id 为 52 的文档进行投票，以查询 “how is a car manufactured”。
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),
    ]
)