DashVector

%pip install --upgrade --quiet  lark dashvector

import os

import dashvector

client = dashvector.Client(api_key=os.environ["DASHVECTOR_API_KEY"])

from langchain_community.embeddings import DashScopeEmbeddings
from langchain_community.vectorstores import DashVector
from langchain_core.documents import Document

embeddings = DashScopeEmbeddings()

# create DashVector collection
client.create("langchain-self-retriever-demo", dimension=1536)

docs = [
    Document(
        page_content="A bunch of scientists bring back dinosaurs and mayhem breaks loose",
        metadata={"year": 1993, "rating": 7.7, "genre": "action"},
    ),
    Document(
        page_content="Leo DiCaprio gets lost in a dream within a dream within a dream within a ...",
        metadata={"year": 2010, "director": "Christopher Nolan", "rating": 8.2},
    ),
    Document(
        page_content="A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea",
        metadata={"year": 2006, "director": "Satoshi Kon", "rating": 8.6},
    ),
    Document(
        page_content="A bunch of normal-sized women are supremely wholesome and some men pine after them",
        metadata={"year": 2019, "director": "Greta Gerwig", "rating": 8.3},
    ),
    Document(
        page_content="Toys come alive and have a blast doing so",
        metadata={"year": 1995, "genre": "animated"},
    ),
    Document(
        page_content="Three men walk into the Zone, three men walk out of the Zone",
        metadata={
            "year": 1979,
            "director": "Andrei Tarkovsky",
            "genre": "science fiction",
            "rating": 9.9,
        },
    ),
]
vectorstore = DashVector.from_documents(
    docs, embeddings, collection_name="langchain-self-retriever-demo"
)

from langchain.chains.query_constructor.schema import AttributeInfo
from langchain.retrievers.self_query.base import SelfQueryRetriever
from langchain_community.llms import Tongyi

metadata_field_info = [
    AttributeInfo(
        name="genre",
        description="The genre of the movie",
        type="string or list[string]",
    ),
    AttributeInfo(
        name="year",
        description="The year the movie was released",
        type="integer",
    ),
    AttributeInfo(
        name="director",
        description="The name of the movie director",
        type="string",
    ),
    AttributeInfo(
        name="rating", description="A 1-10 rating for the movie", type="float"
    ),
]
document_content_description = "Brief summary of a movie"
llm = Tongyi(temperature=0)
retriever = SelfQueryRetriever.from_llm(
    llm, vectorstore, document_content_description, metadata_field_info, verbose=True
)

# This example only specifies a relevant query
retriever.invoke("What are some movies about dinosaurs")

# This example only specifies a filter
retriever.invoke("I want to watch a movie rated higher than 8.5")

# This example specifies a query and a filter
retriever.invoke("Has Greta Gerwig directed any movies about women")

# This example specifies a composite filter
retriever.invoke("What's a highly rated (above 8.5) science fiction film?")

retriever = SelfQueryRetriever.from_llm(
    llm,
    vectorstore,
    document_content_description,
    metadata_field_info,
    enable_limit=True,
    verbose=True,
)

# This example only specifies a relevant query
retriever.invoke("what are two movies about dinosaurs")