Lantern 向量存储（自动检索器）

This guide shows how to perform auto-retrieval in LlamaIndex.

许多流行的向量数据库除了支持语义搜索的查询字符串外，还支持一组元数据过滤器。给定一个自然语言查询，我们首先使用LLM推断出一组元数据过滤器以及传递给向量数据库的正确查询字符串（两者也可以为空）。然后针对向量数据库执行这个完整的查询包。

这允许实现比前k个语义搜索更动态、更具表现力的检索形式。对于给定查询的相关上下文可能仅需对元数据标签进行过滤，或需要在过滤后的集合中进行过滤+语义搜索的联合组合，或仅需原始语义搜索。

我们以 Lantern 为例进行演示，但自动检索功能也已实现在许多其他向量数据库中（例如 Pinecone、Chroma、Weaviate 等）。

如果您在 Colab 上打开这个笔记本，您可能需要安装 LlamaIndex 🦙。

%pip install llama-index-vector-stores-lantern

!pip install llama-index psycopg2-binary asyncpg

import logging
import sys

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

# set up OpenAI
import os

os.environ["OPENAI_API_KEY"] = "<your-api-key>"

import openai

openai.api_key = os.environ["OPENAI_API_KEY"]

import psycopg2
from sqlalchemy import make_url

connection_string = "postgresql://postgres:postgres@localhost:5432"

url = make_url(connection_string)

db_name = "postgres"
conn = psycopg2.connect(connection_string)
conn.autocommit = True

from llama_index.core import VectorStoreIndex, StorageContext
from llama_index.vector_stores.lantern import LanternVectorStore

from llama_index.core.schema import TextNode

nodes = [
    TextNode(
        text=(
            "Michael Jordan is a retired professional basketball player,"
            " widely regarded as one of the greatest basketball players of all"
            " time."
        ),
        metadata={
            "category": "Sports",
            "country": "United States",
        },
    ),
    TextNode(
        text=(
            "Angelina Jolie is an American actress, filmmaker, and"
            " humanitarian. She has received numerous awards for her acting"
            " and is known for her philanthropic work."
        ),
        metadata={
            "category": "Entertainment",
            "country": "United States",
        },
    ),
    TextNode(
        text=(
            "Elon Musk is a business magnate, industrial designer, and"
            " engineer. He is the founder, CEO, and lead designer of SpaceX,"
            " Tesla, Inc., Neuralink, and The Boring Company."
        ),
        metadata={
            "category": "Business",
            "country": "United States",
        },
    ),
    TextNode(
        text=(
            "Rihanna is a Barbadian singer, actress, and businesswoman. She"
            " has achieved significant success in the music industry and is"
            " known for her versatile musical style."
        ),
        metadata={
            "category": "Music",
            "country": "Barbados",
        },
    ),
    TextNode(
        text=(
            "Cristiano Ronaldo is a Portuguese professional footballer who is"
            " considered one of the greatest football players of all time. He"
            " has won numerous awards and set multiple records during his"
            " career."
        ),
        metadata={
            "category": "Sports",
            "country": "Portugal",
        },
    ),
]

使用 Lantern 向量存储构建向量索引

这里我们将数据加载到向量存储中。如上所述，每个节点的文本和元数据都将在Lantern中转换为相应的表示形式。我们现在可以通过Lantern对这些数据运行语义查询和元数据过滤。

vector_store = LanternVectorStore.from_params(
    database=db_name,
    host=url.host,
    password=url.password,
    port=url.port,
    user=url.username,
    table_name="famous_people",
    embed_dim=1536,  # openai embedding dimension
    m=16,  # HNSW M parameter
    ef_construction=128,  # HNSW ef construction parameter
    ef=64,  # HNSW ef search parameter
)

storage_context = StorageContext.from_defaults(vector_store=vector_store)

index = VectorStoreIndex(nodes, storage_context=storage_context)

定义 VectorIndexAutoRetriever`VectorIndexAutoRetriever`

We define our core VectorIndexAutoRetriever module. The module takes in VectorStoreInfo, which contains a structured description of the vector store collection and the metadata filters it supports. This information will then be used in the auto-retrieval prompt where the LLM infers metadata filters.

from llama_index.core.retrievers import VectorIndexAutoRetriever
from llama_index.core.vector_stores import MetadataInfo, VectorStoreInfo


vector_store_info = VectorStoreInfo(
    content_info="brief biography of celebrities",
    metadata_info=[
        MetadataInfo(
            name="category",
            type="str",
            description=(
                "Category of the celebrity, one of [Sports, Entertainment,"
                " Business, Music]"
            ),
        ),
        MetadataInfo(
            name="country",
            type="str",
            description=(
                "Country of the celebrity, one of [United States, Barbados,"
                " Portugal]"
            ),
        ),
    ],
)
retriever = VectorIndexAutoRetriever(
    index, vector_store_info=vector_store_info
)

运行一些示例数据

我们尝试对一些示例数据进行运行。请注意元数据过滤器是如何被推断的 - 这有助于实现更精确的检索！

retriever.retrieve("Tell me about two celebrities from United States")

Lantern 向量存储（自动检索器）

使用 Lantern 向量存储构建向量索引

定义 VectorIndexAutoRetrieverVectorIndexAutoRetriever

运行一些示例数据

定义 VectorIndexAutoRetriever`VectorIndexAutoRetriever`