将MongoDB与 LangChain 集成

from langchain_mongodb.vectorstores import MongoDBAtlasVectorSearch
from langchain_voyageai import VoyageAIEmbeddings
# Instantiate the vector store
vector_store = MongoDBAtlasVectorSearch.from_connection_string(
    connection_string="<connection-string>",  # MongoDB cluster URI
    namespace="<database-name>.<collection-name>",  # Database and collection name
    embedding=VoyageAIEmbeddings(model="voyage-3-large"),  # Embedding model to use
    index_name="vector_index",  # Name of the vector search index
)
# Use the vector store as a retriever
retriever = vector_store.as_retriever()
# Define your query
query = "some search query"
# Print results
documents = retriever.invoke(query)
for doc in documents:
    print(doc)

from langchain_mongodb.retrievers.full_text_search import (
    MongoDBAtlasFullTextSearchRetriever,
)
from pymongo import MongoClient
# Connect to your MongoDB cluster
client = MongoClient("<connection-string>")
collection = client["<database-name>"]["<collection-name>"]
# Initialize the retriever
retriever = MongoDBAtlasFullTextSearchRetriever(
    collection=collection,  # MongoDB Collection in Atlas
    search_field="<field-name>",  # Name of the field to search
    search_index_name="<index-name>",  # Name of the search index
)
# Define your query
query = "some search query"
# Print results
documents = retriever.invoke(query)
for doc in documents:
    print(doc)

from langchain_mongodb.retrievers.hybrid_search import (
    MongoDBAtlasHybridSearchRetriever,
)
from langchain_mongodb.vectorstores import MongoDBAtlasVectorSearch
from langchain_voyageai import VoyageAIEmbeddings
# Instantiate the vector store
vector_store = MongoDBAtlasVectorSearch.from_connection_string(
    connection_string="<connection-string>",  # MongoDB cluster URI
    namespace="<database-name>.<collection-name>",  # Database and collection name
    embedding=VoyageAIEmbeddings(model="voyage-3-large"),  # Embedding model to use
    index_name="vector_index",  # Name of the vector search index
)
# Initialize the retriever
retriever = MongoDBAtlasHybridSearchRetriever(
    vectorstore=vector_store,  # Vector store instance
    search_index_name="<index-name>",  # Name of the MongoDB Search index
    top_k=5,  # Number of documents to return
    fulltext_penalty=60.0,  # Penalty for full-text search
    vector_penalty=60.0,  # Penalty for vector search
)
# Define your query
query = "some search query"
# Print results
documents = retriever.invoke(query)
for doc in documents:
    print(doc)

from langchain_mongodb.retrievers import MongoDBAtlasParentDocumentRetriever
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_voyageai import VoyageAIEmbeddings
retriever = MongoDBAtlasParentDocumentRetriever.from_connection_string(
    connection_string="<connection-string>",  # MongoDB cluster URI
    embedding_model=VoyageAIEmbeddings(  # Embedding model to use
        model="voyage-3-large"
    ),
    child_splitter=RecursiveCharacterTextSplitter(),  # Text splitter to use
    database_name="<database-name>",  # Database to store the collection
    collection_name="<collection-name>",  # Collection to store the collection
    text_key="page_content",  # Match the key the parent document store uses
    # Additional vector store or parent class arguments...
)
# Define your query
query = "some search query"
# Print results
documents = retriever.invoke(query)
for doc in documents:
    print(doc)

from langchain_mongodb.retrievers import MongoDBAtlasSelfQueryRetriever
from langchain_mongodb import MongoDBAtlasVectorSearch
from langchain_classic.chains.query_constructor.schema import AttributeInfo
from langchain_voyageai import VoyageAIEmbeddings
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="gpt-4o", temperature=0)
vector_store = MongoDBAtlasVectorSearch.from_connection_string(
    connection_string="<connection-string>",
    namespace="langchain_db.movies",
    embedding=VoyageAIEmbeddings(model="voyage-3-large"),
    index_name="vector_index",
)
# Given an existing vector store with movies data, define metadata describing the data
metadata_field_info = [
    AttributeInfo(
        name="genre",
        description="The genre of the movie. One of ['science fiction', 'comedy', 'drama', 'thriller', 'romance', 'animated']",
        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"
    ),
]
# Create the retriever from the VectorStore, an LLM and info about the documents
retriever = MongoDBAtlasSelfQueryRetriever.from_llm(
    llm=llm,
    vectorstore=vector_store,
    metadata_field_info=metadata_field_info,
    document_contents="Descriptions of movies",
    enable_limit=True,
)
# This example results in the following composite filter sent to $vectorSearch:
# {'filter': {'$and': [{'year': {'$lt': 1960}}, {'rating': {'$gt': 8}}]}}
documents = retriever.invoke("Movies made before 1960 that are rated higher than 8")
print(documents)

from langchain_mongodb import MongoDBCache
from langchain_core.globals import set_llm_cache
set_llm_cache(
    MongoDBCache(
        connection_string="<connection-string>",  # MongoDB cluster URI
        database_name="langchain_db",  # Database to store the cache
        collection_name="cache",  # Collection to store the cache
    )
)

from langchain_mongodb import MongoDBAtlasSemanticCache
from langchain_core.globals import set_llm_cache
from langchain_voyageai import VoyageAIEmbeddings
set_llm_cache(
    MongoDBAtlasSemanticCache(
        embedding=VoyageAIEmbeddings(model="voyage-3-large"),  # Embedding model
        connection_string="<connection-string>",  # MongoDB cluster URI
        database_name="langchain_db",  # Database to store the cache
        collection_name="semantic_cache",  # Collection to store the cache
    )
)

from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
from langchain_mongodb.agent_toolkit import (
    MONGODB_AGENT_SYSTEM_PROMPT,
    MongoDBDatabase,
    MongoDBDatabaseToolkit,
)
db_wrapper = MongoDBDatabase.from_connection_string(
    "<connection-string>", database="<database-name>"
)
llm = ChatOpenAI(model="gpt-4o-mini", timeout=60)
toolkit = MongoDBDatabaseToolkit(db=db_wrapper, llm=llm)
system_message = MONGODB_AGENT_SYSTEM_PROMPT.format(top_k=5)
test_query = "Which country's customers spent the most?"
agent = create_react_agent(llm, toolkit.get_tools(), prompt=system_message)
agent.step_timeout = 60
events = agent.stream(
    {"messages": [("user", test_query)]},
    stream_mode="values",
)
messages = []
for event in events:
    messages.extend(event["messages"])
print(messages[-1].content)

from langchain_mongodb.docstores import MongoDBDocStore
# Replace with your MongoDB connection string and namespace
connection_string = "<connection-string>"
namespace = "<database-name>.<collection-name>"
# Initialize the MongoDBDocStore
docstore = MongoDBDocStore.from_connection_string(connection_string, namespace)