Insert text data into Milvus.
Insert text data with embeddings vectors into Milvus.
Perform a similarity search against the query string.
Perform a similarity search against the query string.
Perform a search on a query string and return results with score.
Perform a search on an embedding and return results with score.
Perform a search and return results that are reordered by MMR.
Perform a search and return results that are reordered by MMR.
Delete by vector ID or boolean expression.
Delete all the content in the index, by dropping the collection.
Create a Milvus collection, indexes it with HNSW, and insert data.
Run more documents through the embeddings and add to the vectorstore.
Get primary keys with expression
Update/Insert documents to the vectorstore.
Searches the Milvus vector store based on metadata conditions.
Insert text data into Milvus asynchronously.
Insert text data with embeddings vectors into Milvus asynchronously.
Perform an async similarity search against the query string.
Perform an async similarity search against the query vector.
Perform an async search on a query string and return results with score.
Perform an async search on an embedding and return results with score.
Perform an async search and return results that are reordered by MMR.
Perform an async search and return results that are reordered by MMR.
Async delete by vector ID or boolean expression.
Create a Milvus collection, indexes it with HNSW, and insert data
Run more documents through the embeddings and add to the vectorstore
Async get primary keys with expression
Update/Insert documents to the vectorstore asynchronously.
Async searches the Milvus vector store based on metadata conditions.
| Name | Type | Description |
|---|---|---|
*args | Any | Default: ()Variable length argument list passed to the parent Milvus class. |
**kwargs | Any | Default: {}Arbitrary keyword arguments passed to the parent Milvus class.
See Milvus class documentation for supported parameters including:
|
Zilliz vector store.
You need to have pymilvus installed and a
running Zilliz database.
See the following documentation for how to run a Zilliz instance: https://docs.zilliz.com/docs/create-cluster
IF USING L2/IP metric IT IS HIGHLY SUGGESTED TO NORMALIZE YOUR DATA.
The connection args used for this class comes in the form of a dict, the two major arguments are: uri (str): The Public Endpoint of Zilliz instance. Example uri: "https://in03-ba4234asae.api.gcp-us-west1.zillizcloud.com", token (str): API key, for serverless clusters which can be used as replacements for user and password. For more information, please refer to: https://docs.zilliz.com/docs/on-zilliz-cloud-console#cluster-details and https://docs.zilliz.com/reference/python/python/Connections-connect
Example:
from langchain_milvus import Zilliz
from langchain_openai import OpenAIEmbeddings
embedding = OpenAIEmbeddings()
# Connect to a Zilliz instance
milvus_store = Zilliz(
embedding_function = embedding,
collection_name = "LangChainCollection",
connection_args = {
"uri": "https://in03-ba4234asae.api.gcp-us-west1.zillizcloud.com",
"token": "temp", # API key
}
drop_old: True,
)