使用MongoDB和 LangChain 执行自查询检索

from langchain_mongodb import MongoDBAtlasVectorSearch
from langchain_voyageai import VoyageAIEmbeddings
# Use the voyage-3-large embedding model
embedding_model = VoyageAIEmbeddings(model="voyage-3-large")
# Create the vector store
vector_store = MongoDBAtlasVectorSearch.from_connection_string(
   connection_string = MONGODB_URI,
   embedding = embedding_model,
   namespace = "langchain_db.self_query",
   text_key = "page_content"
)

from langchain_core.documents import Document
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="A fight club that is not a fight club, but is a fight club",
        metadata={"year": 1994, "rating": 8.7, "genre": "action"},
    ),
    Document(
        page_content="Leo DiCaprio gets lost in a dream within a dream within a dream within a ...",
        metadata={"year": 2010, "genre": "thriller", "rating": 8.2},
    ),
    Document(
        page_content="A bunch of normal-sized women are supremely wholesome and some men pine after them",
        metadata={"year": 2019, "rating": 8.3, "genre": "drama"},
    ),
    Document(
        page_content="Three men walk into the Zone, three men walk out of the Zone",
        metadata={"year": 1979, "rating": 9.9, "genre": "science fiction"},
    ),
    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, "genre": "thriller", "rating": 9.0},
    ),
    Document(
        page_content="Toys come alive and have a blast doing so",
        metadata={"year": 1995, "genre": "animated", "rating": 9.3},
    ),
    Document(
        page_content="The toys come together to save their friend from a kid who doesn't know how to play with them",
        metadata={"year": 1997, "genre": "animated", "rating": 9.1},
    ),
]
# Add data to the vector store, which automaticaly embeds the documents
vector_store.add_documents(docs)

# Use LangChain helper method to create the vector search index
vector_store.create_vector_search_index(
   dimensions = 1024, # The dimensions of the vector embeddings to be indexed
   filters = [ "genre", "rating", "year" ], # The metadata fields to be indexed for filtering
   wait_until_complete = 60 # Number of seconds to wait for the index to build (can take around a minute)
)

from langchain.chains.query_constructor.schema import AttributeInfo
# Define the document content description 
document_content_description = "Brief summary of a movie"
# Define the metadata fields to filter on
metadata_field_info = [
    AttributeInfo(
        name="genre",
        description="The genre of the movie",
        type="string",
    ),
    AttributeInfo(
        name="year",
        description="The year the movie was released",
        type="integer",
    ),
    AttributeInfo(
        name="rating", 
        description="A 1-10 rating for the movie", 
        type="float"
    ),
]

from langchain_mongodb.retrievers import MongoDBAtlasSelfQueryRetriever
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="gpt-4o")
retriever = MongoDBAtlasSelfQueryRetriever.from_llm(
    llm=llm,
    vectorstore=vector_store,
    metadata_field_info=metadata_field_info,
    document_contents=document_content_description
)