Milvus

pip install -qU langchain-milvus

Note: you may need to restart the kernel to use updated packages.

# | output: false
# | echo: false
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(model="text-embedding-3-large")

from langchain_milvus import Milvus

URI = "./milvus_example.db"

vector_store = Milvus(
    embedding_function=embeddings,
    connection_args={"uri": URI},
    index_params={"index_type": "FLAT", "metric_type": "L2"},
)

!curl -sfL https://raw.githubusercontent.com/milvus-io/milvus/master/scripts/standalone_embed.sh -o standalone_embed.sh

!bash standalone_embed.sh start

Password:

from pymilvus import Collection, MilvusException, connections, db, utility

conn = connections.connect(host="127.0.0.1", port=19530)

# Check if the database exists
db_name = "milvus_demo"
try:
    existing_databases = db.list_database()
    if db_name in existing_databases:
        print(f"Database '{db_name}' already exists.")

        # Use the database context
        db.using_database(db_name)

        # Drop all collections in the database
        collections = utility.list_collections()
        for collection_name in collections:
            collection = Collection(name=collection_name)
            collection.drop()
            print(f"Collection '{collection_name}' has been dropped.")

        db.drop_database(db_name)
        print(f"Database '{db_name}' has been deleted.")
    else:
        print(f"Database '{db_name}' does not exist.")
        database = db.create_database(db_name)
        print(f"Database '{db_name}' created successfully.")
except MilvusException as e:
    print(f"An error occurred: {e}")

Database 'milvus_demo' does not exist.
Database 'milvus_demo' created successfully.

from langchain_milvus import BM25BuiltInFunction, Milvus

URI = "https://:19530"

vectorstore = Milvus(
    embedding_function=embeddings,
    connection_args={"uri": URI, "token": "root:Milvus", "db_name": "milvus_demo"},
    index_params={"index_type": "FLAT", "metric_type": "L2"},
    consistency_level="Strong",
    drop_old=False,  # set to True if seeking to drop the collection with that name if it exists
)

from langchain_core.documents import Document

vector_store_saved = Milvus.from_documents(
    [Document(page_content="foo!")],
    embeddings,
    collection_name="langchain_example",
    connection_args={"uri": URI},
)

vector_store_loaded = Milvus(
    embeddings,
    connection_args={"uri": URI},
    collection_name="langchain_example",
)

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
    page_content="I had chocolate chip pancakes and scrambled eggs for breakfast this morning.",
    metadata={"source": "tweet"},
)

document_2 = Document(
    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
    metadata={"source": "news"},
)

document_3 = Document(
    page_content="Building an exciting new project with LangChain - come check it out!",
    metadata={"source": "tweet"},
)

document_4 = Document(
    page_content="Robbers broke into the city bank and stole $1 million in cash.",
    metadata={"source": "news"},
)

document_5 = Document(
    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
    metadata={"source": "tweet"},
)

document_6 = Document(
    page_content="Is the new iPhone worth the price? Read this review to find out.",
    metadata={"source": "website"},
)

document_7 = Document(
    page_content="The top 10 soccer players in the world right now.",
    metadata={"source": "website"},
)

document_8 = Document(
    page_content="LangGraph is the best framework for building stateful, agentic applications!",
    metadata={"source": "tweet"},
)

document_9 = Document(
    page_content="The stock market is down 500 points today due to fears of a recession.",
    metadata={"source": "news"},
)

document_10 = Document(
    page_content="I have a bad feeling I am going to get deleted :(",
    metadata={"source": "tweet"},
)

documents = [
    document_1,
    document_2,
    document_3,
    document_4,
    document_5,
    document_6,
    document_7,
    document_8,
    document_9,
    document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]

vector_store.add_documents(documents=documents, ids=uuids)

vector_store.delete(ids=[uuids[-1]])

(insert count: 0, delete count: 1, upsert count: 0, timestamp: 0, success count: 0, err count: 0, cost: 0)

results = vector_store.similarity_search(
    "LangChain provides abstractions to make working with LLMs easy",
    k=2,
    expr='source == "tweet"',
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

* Building an exciting new project with LangChain - come check it out! [{'pk': '9905001c-a4a3-455e-ab94-72d0ed11b476', 'source': 'tweet'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'pk': '1206d237-ee3a-484f-baf2-b5ac38eeb314', 'source': 'tweet'}]

results = vector_store.similarity_search_with_score(
    "Will it be hot tomorrow?", k=1, expr='source == "news"'
)
for res, score in results:
    print(f"* [SIM={score:3f}] {res.page_content} [{res.metadata}]")

* [SIM=21192.628906] bar [{'pk': '2', 'source': 'https://example.com'}]

retriever = vector_store.as_retriever(search_type="mmr", search_kwargs={"k": 1})
retriever.invoke("Stealing from the bank is a crime", filter={"source": "news"})

[Document(metadata={'pk': 'eacc7256-d7fa-4036-b1f7-83d7a4bee0c5', 'source': 'news'}, page_content='Robbers broke into the city bank and stole $1 million in cash.')]

from langchain_milvus import BM25BuiltInFunction, Milvus
from langchain_openai import OpenAIEmbeddings

vectorstore = Milvus.from_documents(
    documents=documents,
    embedding=OpenAIEmbeddings(),
    builtin_function=BM25BuiltInFunction(),
    # `dense` is for OpenAI embeddings, `sparse` is the output field of BM25 function
    vector_field=["dense", "sparse"],
    connection_args={
        "uri": URI,
    },
    consistency_level="Strong",
    drop_old=True,
)

query = "What are the novels Lila has written and what are their contents?"

vectorstore.similarity_search(
    query, k=1, ranker_type="weighted", ranker_params={"weights": [0.6, 0.4]}
)

from langchain_core.documents import Document

docs = [
    Document(page_content="i worked at kensho", metadata={"namespace": "harrison"}),
    Document(page_content="i worked at facebook", metadata={"namespace": "ankush"}),
]
vectorstore = Milvus.from_documents(
    docs,
    embeddings,
    connection_args={"uri": URI},
    drop_old=True,
    partition_key_field="namespace",  # Use the "namespace" field as the partition key
)

# This will only get documents for Ankush
vectorstore.as_retriever(search_kwargs={"expr": 'namespace == "ankush"'}).invoke(
    "where did i work?"
)

[Document(page_content='i worked at facebook', metadata={'namespace': 'ankush'})]

# This will only get documents for Harrison
vectorstore.as_retriever(search_kwargs={"expr": 'namespace == "harrison"'}).invoke(
    "where did i work?"
)

[Document(page_content='i worked at kensho', metadata={'namespace': 'harrison'})]