Skip to main content

Milvus

Milvus is a database that stores, indexes, and manages massive embedding vectors generated by deep neural networks and other machine learning (ML) models.

This notebook shows how to use functionality related to the Milvus vector database.

You'll need to install langchain-milvus with pip install -qU langchain-milvus to use this integration

%pip install --upgrade --quiet  langchain_milvus

The latest version of pymilvus comes with a local vector database Milvus Lite, good for prototyping. If you have large scale of data such as more than a million docs, we recommend setting up a more performant Milvus server on docker or kubernetes.

We want to use OpenAIEmbeddings so we have to get the OpenAI API Key.

import getpass
import os

os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
from langchain_community.document_loaders import TextLoader
from langchain_milvus.vectorstores import Milvus
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter
loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()
# The easiest way is to use Milvus Lite where everything is stored in a local file.
# If you have a Milvus server you can use the server URI such as "http://localhost:19530".
URI = "./milvus_demo.db"

vector_db = Milvus.from_documents(
    docs,
    embeddings,
    connection_args={"uri": URI},
)
query = "What did the president say about Ketanji Brown Jackson"
docs = vector_db.similarity_search(query)
docs[0].page_content
'Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.'

Compartmentalize the data with Milvus Collections​

You can store different unrelated documents in different collections within same Milvus instance to maintain the context

Here's how you can create a new collection

vector_db = Milvus.from_documents(
    docs,
    embeddings,
    collection_name="collection_1",
    connection_args={"uri": URI},
)

And here is how you retrieve that stored collection

vector_db = Milvus(
    embeddings,
    connection_args={"uri": URI},
    collection_name="collection_1",
)

After retrieval you can go on querying it as usual.

Per-User Retrieval​

When building a retrieval app, you often have to build it with multiple users in mind. This means that you may be storing data not just for one user, but for many different users, and they should not be able to see eachother’s data.

Milvus recommends using partition_key to implement multi-tenancy, here is an example.

The feature of Partition key is now not available in Milvus Lite, if you want to use it, you need to start Milvus server from docker or kubernetes.

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
)
API Reference:Document

To conduct a search using the partition key, you should include either of the following in the boolean expression of the search request:

search_kwargs={"expr": '<partition_key> == "xxxx"'}

search_kwargs={"expr": '<partition_key> == in ["xxx", "xxx"]'}

Do replace <partition_key> with the name of the field that is designated as the partition key.

Milvus changes to a partition based on the specified partition key, filters entities according to the partition key, and searches among the filtered entities.

# 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'})]

To delete or upsert (update/insert) one or more entities​

from langchain_core.documents import Document

# Insert data sample
docs = [
    Document(page_content="foo", metadata={"id": 1}),
    Document(page_content="bar", metadata={"id": 2}),
    Document(page_content="baz", metadata={"id": 3}),
]
vector_db = Milvus.from_documents(
    docs,
    embeddings,
    connection_args={"uri": URI},
)

# Search pks (primary keys) using expression
expr = "id in [1,2]"
pks = vector_db.get_pks(expr)

# Delete entities by pks
result = vector_db.delete(pks)

# Upsert (Update/Insert)
new_docs = [
    Document(page_content="new_foo", metadata={"id": 1}),
    Document(page_content="new_bar", metadata={"id": 2}),
    Document(page_content="upserted_bak", metadata={"id": 3}),
]
upserted_pks = vector_db.upsert(pks, new_docs)
API Reference:Document

Was this page helpful?


You can also leave detailed feedback on GitHub.