Milvus#

class langchain_milvus.vectorstores.milvus.Milvus(embedding_function: Embeddings | BaseSparseEmbedding | List[Embeddings | BaseSparseEmbedding], collection_name: str = 'LangChainCollection', collection_description: str = '', collection_properties: dict[str, Any] | None = None, connection_args: dict[str, Any] | None = None, consistency_level: str = 'Session', index_params: dict | List[dict] | None = None, search_params: dict | List[dict] | None = None, drop_old: bool | None = False, auto_id: bool = False, *, primary_field: str = 'pk', text_field: str = 'text', vector_field: str | List[str] = 'vector', enable_dynamic_field: bool = False, metadata_field: str | None = None, partition_key_field: str | None = None, partition_names: list | None = None, replica_number: int = 1, timeout: float | None = None, num_shards: int | None = None, vector_schema: dict[str, Any] | List[dict[str, Any]] | None = None, metadata_schema: dict[str, Any] | None = None)[source]#

Milvus vector store integration.

Setup:

Install langchain_milvus package:

pip install -qU  langchain_milvus
Key init args — indexing params:
collection_name: str

Name of the collection.

collection_description: str

Description of the collection.

embedding_function: Union[Embeddings, BaseSparseEmbedding]

Embedding function to use.

Key init args — client params:
connection_args: Optional[dict]

Connection arguments.

Instantiate:
from langchain_milvus import Milvus
from langchain_openai import OpenAIEmbeddings

URI = "./milvus_example.db"

vector_store = Milvus(
    embedding_function=OpenAIEmbeddings(),
    connection_args={"uri": URI},
)
Add Documents:
from langchain_core.documents import Document

document_1 = Document(page_content="foo", metadata={"baz": "bar"})
document_2 = Document(page_content="thud", metadata={"baz": "baz"})
document_3 = Document(page_content="i will be deleted :(", metadata={"baz": "qux"})

documents = [document_1, document_2, document_3]
ids = ["1", "2", "3"]
vector_store.add_documents(documents=documents, ids=ids)
Delete Documents:
vector_store.delete(ids=["3"])
Search:
results = vector_store.similarity_search(query="thud",k=1)
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

* thud [{'baz': 'baz', 'pk': '2'}]
Search with filter:
results = vector_store.similarity_search(query="thud",k=1,filter={"bar": "baz"})
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

* thud [{'baz': 'baz', 'pk': '2'}]
Search with score:
results = vector_store.similarity_search_with_score(query="qux",k=1)
for doc, score in results:
    print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]")

* [SIM=0.335463] foo [{'baz': 'bar', 'pk': '1'}]
Async:
# add documents
# await vector_store.aadd_documents(documents=documents, ids=ids)

# delete documents
# await vector_store.adelete(ids=["3"])

# search
# results = vector_store.asimilarity_search(query="thud",k=1)

# search with score
results = await vector_store.asimilarity_search_with_score(query="qux",k=1)
for doc,score in results:
    print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]")

* [SIM=0.335463] foo [{'baz': 'bar', 'pk': '1'}]
Use as Retriever:
retriever = vector_store.as_retriever(
    search_type="mmr",
    search_kwargs={"k": 1, "fetch_k": 2, "lambda_mult": 0.5},
)
retriever.invoke("thud")

[Document(metadata={'baz': 'baz', 'pk': '2'}, page_content='thud')]

Initialize the Milvus vector store.

Attributes

client

Get client.

embeddings

Access the query embedding object if available.

Methods

__init__(embedding_function[, ...])

Initialize the Milvus vector store.

aadd_documents(documents, **kwargs)

Run more documents through the embeddings and add to the vectorstore.

aadd_texts(texts[, metadatas, ids])

Async run more texts through the embeddings and add to the vectorstore.

add_documents(documents, **kwargs)

Run more documents through the embeddings and add to the vectorstore.

add_embeddings(texts, embeddings[, ...])

Insert text data with embeddings vectors into Milvus.

add_texts(texts[, metadatas, timeout, ...])

Insert text data into Milvus.

adelete([ids])

Async delete by vector ID or other criteria.

afrom_documents(documents, embedding, **kwargs)

Async return VectorStore initialized from documents and embeddings.

afrom_texts(texts, embedding[, metadatas, ids])

Async return VectorStore initialized from texts and embeddings.

aget_by_ids(ids, /)

Async get documents by their IDs.

amax_marginal_relevance_search(query[, k, ...])

Async return docs selected using the maximal marginal relevance.

amax_marginal_relevance_search_by_vector(...)

Async return docs selected using the maximal marginal relevance.

as_retriever(**kwargs)

Return VectorStoreRetriever initialized from this VectorStore.

asearch(query, search_type, **kwargs)

Async return docs most similar to query using a specified search type.

asimilarity_search(query[, k])

Async return docs most similar to query.

asimilarity_search_by_vector(embedding[, k])

Async return docs most similar to embedding vector.

asimilarity_search_with_relevance_scores(query)

Async return docs and relevance scores in the range [0, 1].

asimilarity_search_with_score(*args, **kwargs)

Async run similarity search with distance.

delete([ids, expr])

Delete by vector ID or boolean expression.

from_documents(documents, embedding, **kwargs)

Return VectorStore initialized from documents and embeddings.

from_texts(texts, embedding[, metadatas, ...])

Create a Milvus collection, indexes it with HNSW, and insert data.

get_by_ids(ids, /)

Get documents by their IDs.

get_pks(expr, **kwargs)

Get primary keys with expression

max_marginal_relevance_search(query[, k, ...])

Perform a search and return results that are reordered by MMR.

max_marginal_relevance_search_by_vector(...)

Perform a search and return results that are reordered by MMR.

search(query, search_type, **kwargs)

Return docs most similar to query using a specified search type.

similarity_search(query[, k, param, expr, ...])

Perform a similarity search against the query string.

similarity_search_by_vector(embedding[, k, ...])

Perform a similarity search against the query string.

similarity_search_with_relevance_scores(query)

Return docs and relevance scores in the range [0, 1].

similarity_search_with_score(query[, k, ...])

Perform a search on a query string and return results with score.

similarity_search_with_score_by_vector(embedding)

Perform a search on an embedding and return results with score.

upsert([ids, documents])

Update/Insert documents to the vectorstore.
Parameters:

  • embedding_function (Union[EmbeddingType, List[EmbeddingType]])

  • collection_name (str)

  • collection_description (str)

  • collection_properties (Optional[dict[str, Any]])

  • connection_args (Optional[dict[str, Any]])

  • consistency_level (str)

  • index_params (Optional[Union[dict, List[dict]]])

  • search_params (Optional[Union[dict, List[dict]]])

  • drop_old (Optional[bool])

  • auto_id (bool)

  • primary_field (str)

  • text_field (str)

  • vector_field (Union[str, List[str]])

  • enable_dynamic_field (bool)

  • metadata_field (Optional[str])

  • partition_key_field (Optional[str])

  • partition_names (Optional[list])

  • replica_number (int)

  • timeout (Optional[float])

  • num_shards (Optional[int])

  • vector_schema (Optional[Union[dict[str, Any], List[dict[str, Any]]]])

  • metadata_schema (Optional[dict[str, Any]])

__init__(embedding_function: Embeddings | BaseSparseEmbedding | List[Embeddings | BaseSparseEmbedding], collection_name: str = 'LangChainCollection', collection_description: str = '', collection_properties: dict[str, Any] | None = None, connection_args: dict[str, Any] | None = None, consistency_level: str = 'Session', index_params: dict | List[dict] | None = None, search_params: dict | List[dict] | None = None, drop_old: bool | None = False, auto_id: bool = False, *, primary_field: str = 'pk', text_field: str = 'text', vector_field: str | List[str] = 'vector', enable_dynamic_field: bool = False, metadata_field: str | None = None, partition_key_field: str | None = None, partition_names: list | None = None, replica_number: int = 1, timeout: float | None = None, num_shards: int | None = None, vector_schema: dict[str, Any] | List[dict[str, Any]] | None = None, metadata_schema: dict[str, Any] | None = None)[source]#

Initialize the Milvus vector store.

Parameters:

  • embedding_function (Embeddings | BaseSparseEmbedding | List[Embeddings | BaseSparseEmbedding])

  • collection_name (str)

  • collection_description (str)

  • collection_properties (dict[str, Any] | None)

  • connection_args (dict[str, Any] | None)

  • consistency_level (str)

  • index_params (dict | List[dict] | None)

  • search_params (dict | List[dict] | None)

  • drop_old (bool | None)

  • auto_id (bool)

  • primary_field (str)

  • text_field (str)

  • vector_field (str | List[str])

  • enable_dynamic_field (bool)

  • metadata_field (str | None)

  • partition_key_field (str | None)

  • partition_names (list | None)

  • replica_number (int)

  • timeout (float | None)

  • num_shards (int | None)

  • vector_schema (dict[str, Any] | List[dict[str, Any]] | None)

  • metadata_schema (dict[str, Any] | None)

async aadd_documents(documents: List[Document], **kwargs: Any) → List[str][source]#

Run more documents through the embeddings and add to the vectorstore.

Parameters:

  • documents (List[Document]) – Documents to add to the vectorstore.

  • kwargs (Any)

Returns:

List of IDs of the added texts.

Return type:

List[str]

async aadd_texts(texts: Iterable[str], metadatas: list[dict] | None = None, *, ids: list[str] | None = None, **kwargs: Any) → list[str]#

Async run more texts through the embeddings and add to the vectorstore.

Parameters:

  • texts (Iterable[str]) – Iterable of strings to add to the vectorstore.

  • metadatas (list[dict] | None) – Optional list of metadatas associated with the texts. Default is None.

  • ids (list[str] | None) – Optional list

  • **kwargs (Any) – vectorstore specific parameters.

Returns:

List of ids from adding the texts into the vectorstore.

Raises:

  • ValueError – If the number of metadatas does not match the number of texts.

  • ValueError – If the number of ids does not match the number of texts.

Return type:

list[str]

add_documents(documents: List[Document], **kwargs: Any) → List[str][source]#

Run more documents through the embeddings and add to the vectorstore.

Parameters:

  • documents (List[Document]) – Documents to add to the vectorstore.

  • kwargs (Any)

Returns:

List of IDs of the added texts.

Return type:

List[str]

add_embeddings(texts: List[str], embeddings: List[List[float]] | List[List[List[float]]], metadatas: List[dict] | None = None, timeout: float | None = None, batch_size: int = 1000, *, ids: List[str] | None = None, **kwargs: Any) → List[str][source]#

Insert text data with embeddings vectors into Milvus.

This method inserts a batch of text embeddings into a Milvus collection. If the collection is not initialized, it will automatically initialize the collection based on the embeddings,metadatas, and other parameters. The embeddings are expected to be pre-generated using compatible embedding functions, and the metadata associated with each text is optional but must match the number of texts.

Parameters:

  • texts (List[str]) – the texts to insert

  • embeddings (List[List[Union[float, List[float]]]]) – A vector embeddings for each text (in case of a single vector) or list of vectors for each text (in case of multi-vector)

  • metadatas (Optional[List[dict]]) – Metadata dicts attached to each of the texts. Defaults to None.

  • False. (should be less than 65535 bytes. Required and work when auto_id is)

  • timeout (Optional[float]) – Timeout for each batch insert. Defaults to None.

  • batch_size (int, optional) – Batch size to use for insertion. Defaults to 1000.

  • ids (Optional[List[str]]) – List of text ids. The length of each item

  • kwargs (Any)

Raises:

MilvusException – Failure to add texts and embeddings

Returns:

The resulting keys for each inserted element.

Return type:

List[str]

add_texts(texts: Iterable[str], metadatas: List[dict] | None = None, timeout: float | None = None, batch_size: int = 1000, *, ids: List[str] | None = None, **kwargs: Any) → List[str][source]#

Insert text data into Milvus.

Inserting data when the collection has not be made yet will result in creating a new Collection. The data of the first entity decides the schema of the new collection, the dim is extracted from the first embedding and the columns are decided by the first metadata dict. Metadata keys will need to be present for all inserted values. At the moment there is no None equivalent in Milvus.

Parameters:

  • texts (Iterable[str]) – The texts to embed, it is assumed that they all fit in memory.

  • metadatas (Optional[List[dict]]) – Metadata dicts attached to each of the texts. Defaults to None.

  • False. (should be less than 65535 bytes. Required and work when auto_id is)

  • timeout (Optional[float]) – Timeout for each batch insert. Defaults to None.

  • batch_size (int, optional) – Batch size to use for insertion. Defaults to 1000.

  • ids (Optional[List[str]]) – List of text ids. The length of each item

  • kwargs (Any)

Raises:

MilvusException – Failure to add texts

Returns:

The resulting keys for each inserted element.

Return type:

List[str]

async adelete(ids: list[str] | None = None, **kwargs: Any) → bool | None#

Async delete by vector ID or other criteria.

Parameters:

  • ids (list[str] | None) – List of ids to delete. If None, delete all. Default is None.

  • **kwargs (Any) – Other keyword arguments that subclasses might use.

Returns:

True if deletion is successful, False otherwise, None if not implemented.

Return type:

Optional[bool]

async classmethod afrom_documents(documents: list[Document], embedding: Embeddings, **kwargs: Any) → VST#

Async return VectorStore initialized from documents and embeddings.

Parameters:

  • documents (list[Document]) – List of Documents to add to the vectorstore.

  • embedding (Embeddings) – Embedding function to use.

  • kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from documents and embeddings.

Return type:

VectorStore

async classmethod afrom_texts(texts: list[str], embedding: Embeddings, metadatas: list[dict] | None = None, *, ids: list[str] | None = None, **kwargs: Any) → VST#

Async return VectorStore initialized from texts and embeddings.

Parameters:

  • texts (list[str]) – Texts to add to the vectorstore.

  • embedding (Embeddings) – Embedding function to use.

  • metadatas (list[dict] | None) – Optional list of metadatas associated with the texts. Default is None.

  • ids (list[str] | None) – Optional list of IDs associated with the texts.

  • kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from texts and embeddings.

Return type:

VectorStore

async aget_by_ids(ids: Sequence[str], /) → list[Document]#

Async get documents by their IDs.

The returned documents are expected to have the ID field set to the ID of the document in the vector store.

Fewer documents may be returned than requested if some IDs are not found or if there are duplicated IDs.

Users should not assume that the order of the returned documents matches the order of the input IDs. Instead, users should rely on the ID field of the returned documents.

This method should NOT raise exceptions if no documents are found for some IDs.

Parameters:

ids (Sequence[str]) – List of ids to retrieve.

Returns:

List of Documents.

Return type:

list[Document]

Added in version 0.2.11.

Async return docs selected using the maximal marginal relevance.

Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

Parameters:

  • query (str) – Text to look up documents similar to.

  • k (int) – Number of Documents to return. Defaults to 4.

  • fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm. Default is 20.

  • lambda_mult (float) – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.

  • kwargs (Any)

Returns:

List of Documents selected by maximal marginal relevance.

Return type:

list[Document]

async amax_marginal_relevance_search_by_vector(embedding: list[float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any) → list[Document]#

Async return docs selected using the maximal marginal relevance.

Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

Parameters:

  • embedding (list[float]) – Embedding to look up documents similar to.

  • k (int) – Number of Documents to return. Defaults to 4.

  • fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm. Default is 20.

  • lambda_mult (float) – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.

  • **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents selected by maximal marginal relevance.

Return type:

list[Document]

as_retriever(**kwargs: Any) → VectorStoreRetriever#

Return VectorStoreRetriever initialized from this VectorStore.

Parameters:

**kwargs (Any) –

Keyword arguments to pass to the search function. Can include: search_type (Optional[str]): Defines the type of search that

the Retriever should perform. Can be “similarity” (default), “mmr”, or “similarity_score_threshold”.

search_kwargs (Optional[Dict]): Keyword arguments to pass to the
search function. Can include things like:

k: Amount of documents to return (Default: 4) score_threshold: Minimum relevance threshold

for similarity_score_threshold

fetch_k: Amount of documents to pass to MMR algorithm

(Default: 20)

lambda_mult: Diversity of results returned by MMR;

1 for minimum diversity and 0 for maximum. (Default: 0.5)

filter: Filter by document metadata

Returns:

Retriever class for VectorStore.

Return type:

VectorStoreRetriever

Examples:

# Retrieve more documents with higher diversity
# Useful if your dataset has many similar documents
docsearch.as_retriever(
    search_type="mmr",
    search_kwargs={'k': 6, 'lambda_mult': 0.25}
)

# Fetch more documents for the MMR algorithm to consider
# But only return the top 5
docsearch.as_retriever(
    search_type="mmr",
    search_kwargs={'k': 5, 'fetch_k': 50}
)

# Only retrieve documents that have a relevance score
# Above a certain threshold
docsearch.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={'score_threshold': 0.8}
)

# Only get the single most similar document from the dataset
docsearch.as_retriever(search_kwargs={'k': 1})

# Use a filter to only retrieve documents from a specific paper
docsearch.as_retriever(
    search_kwargs={'filter': {'paper_title':'GPT-4 Technical Report'}}
)
async asearch(query: str, search_type: str, **kwargs: Any) → list[Document]#

Async return docs most similar to query using a specified search type.

Parameters:

  • query (str) – Input text.

  • search_type (str) – Type of search to perform. Can be “similarity”, “mmr”, or “similarity_score_threshold”.

  • **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Raises:

ValueError – If search_type is not one of “similarity”, “mmr”, or “similarity_score_threshold”.

Return type:

list[Document]

Async return docs most similar to query.

Parameters:

  • query (str) – Input text.

  • k (int) – Number of Documents to return. Defaults to 4.

  • **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Return type:

list[Document]

async asimilarity_search_by_vector(embedding: list[float], k: int = 4, **kwargs: Any) → list[Document]#

Async return docs most similar to embedding vector.

Parameters:

  • embedding (list[float]) – Embedding to look up documents similar to.

  • k (int) – Number of Documents to return. Defaults to 4.

  • **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query vector.

Return type:

list[Document]

async asimilarity_search_with_relevance_scores(query: str, k: int = 4, **kwargs: Any) → list[tuple[Document, float]]#

Async return docs and relevance scores in the range [0, 1].

0 is dissimilar, 1 is most similar.

Parameters:

  • query (str) – Input text.

  • k (int) – Number of Documents to return. Defaults to 4.

  • **kwargs (Any) –

    kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to

    filter the resulting set of retrieved docs

Returns:

List of Tuples of (doc, similarity_score)

Return type:

list[tuple[Document, float]]

async asimilarity_search_with_score(*args: Any, **kwargs: Any) → list[tuple[Document, float]]#

Async run similarity search with distance.

Parameters:

  • *args (Any) – Arguments to pass to the search method.

  • **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Tuples of (doc, similarity_score).

Return type:

list[tuple[Document, float]]

delete(ids: List[str] | None = None, expr: str | None = None, **kwargs: str)[source]#

Delete by vector ID or boolean expression. Refer to [Milvus documentation](https://milvus.io/docs/delete_data.md) for notes and examples of expressions.

Parameters:

  • ids (List[str] | None) – List of ids to delete.

  • expr (str | None) – Boolean expression that specifies the entities to delete.

  • kwargs (str) – Other parameters in Milvus delete api.

classmethod from_documents(documents: list[Document], embedding: Embeddings, **kwargs: Any) → VST#

Return VectorStore initialized from documents and embeddings.

Parameters:

  • documents (list[Document]) – List of Documents to add to the vectorstore.

  • embedding (Embeddings) – Embedding function to use.

  • kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from documents and embeddings.

Return type:

VectorStore

classmethod from_texts(texts: List[str], embedding: Embeddings | BaseSparseEmbedding | List[Embeddings | BaseSparseEmbedding], metadatas: List[dict] | None = None, collection_name: str = 'LangChainCollection', connection_args: Dict[str, Any] | None = None, consistency_level: str = 'Session', index_params: dict | List[dict] | None = None, search_params: dict | List[dict] | None = None, drop_old: bool = False, *, ids: List[str] | None = None, auto_id: bool = False, **kwargs: Any) → Milvus[source]#

Create a Milvus collection, indexes it with HNSW, and insert data.

Parameters:

  • texts (List[str]) – Text data.

  • embedding (Union[Embeddings, BaseSparseEmbedding]) – Embedding function.

  • metadatas (Optional[List[dict]]) – Metadata for each text if it exists. Defaults to None.

  • collection_name (str, optional) – Collection name to use. Defaults to “LangChainCollection”.

  • connection_args (dict[str, Any], optional) – Connection args to use. Defaults to DEFAULT_MILVUS_CONNECTION.

  • consistency_level (str, optional) – Which consistency level to use. Defaults to “Session”.

  • index_params (Optional[dict], optional) – Which index_params to use. Defaults to None.

  • search_params (Optional[dict], optional) – Which search params to use. Defaults to None.

  • drop_old (Optional[bool], optional) – Whether to drop the collection with that name if it exists. Defaults to False.

  • ids (Optional[List[str]]) – List of text ids. Defaults to None.

  • auto_id (bool) – Whether to enable auto id for primary key. Defaults to False. If False, you need to provide text ids (string less than 65535 bytes). If True, Milvus will generate unique integers as primary keys.

  • kwargs (Any)

Returns:

Milvus Vector Store

Return type:

Milvus

get_by_ids(ids: Sequence[str], /) → list[Document]#

Get documents by their IDs.

The returned documents are expected to have the ID field set to the ID of the document in the vector store.

Fewer documents may be returned than requested if some IDs are not found or if there are duplicated IDs.

Users should not assume that the order of the returned documents matches the order of the input IDs. Instead, users should rely on the ID field of the returned documents.

This method should NOT raise exceptions if no documents are found for some IDs.

Parameters:

ids (Sequence[str]) – List of ids to retrieve.

Returns:

List of Documents.

Return type:

list[Document]

Added in version 0.2.11.

get_pks(expr: str, **kwargs: Any) → List[int] | None[source]#

Get primary keys with expression

Parameters:

  • expr (str) – Expression - E.g: “id in [1, 2]”, or “title LIKE ‘Abc%’”

  • kwargs (Any)

Returns:

List of IDs (Primary Keys)

Return type:

List[int]

Perform a search and return results that are reordered by MMR.

Parameters:

  • query (str) – The text being searched.

  • k (int, optional) – How many results to give. Defaults to 4.

  • fetch_k (int, optional) – Total results to select k from. Defaults to 20.

  • lambda_mult (float) – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5

  • param (dict, optional) – The search params for the specified index. Defaults to None.

  • expr (str, optional) – Filtering expression. Defaults to None.

  • timeout (float, optional) – How long to wait before timeout error. Defaults to None.

  • kwargs (Any) – Collection.search() keyword arguments.

Returns:

Document results for search.

Return type:

List[Document]

max_marginal_relevance_search_by_vector(embedding: list[float] | dict[int, float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, param: dict | None = None, expr: str | None = None, timeout: float | None = None, **kwargs: Any) → List[Document][source]#

Perform a search and return results that are reordered by MMR.

Parameters:

  • embedding (list[float] | dict[int, float]) – The embedding vector being searched.

  • k (int, optional) – How many results to give. Defaults to 4.

  • fetch_k (int, optional) – Total results to select k from. Defaults to 20.

  • lambda_mult (float) – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5

  • param (dict, optional) – The search params for the specified index. Defaults to None.

  • expr (str, optional) – Filtering expression. Defaults to None.

  • timeout (float, optional) – How long to wait before timeout error. Defaults to None.

  • kwargs (Any) – Collection.search() keyword arguments.

Returns:

Document results for search.

Return type:

List[Document]

search(query: str, search_type: str, **kwargs: Any) → list[Document]#

Return docs most similar to query using a specified search type.

Parameters:

  • query (str) – Input text

  • search_type (str) – Type of search to perform. Can be “similarity”, “mmr”, or “similarity_score_threshold”.

  • **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Raises:

ValueError – If search_type is not one of “similarity”, “mmr”, or “similarity_score_threshold”.

Return type:

list[Document]

Perform a similarity search against the query string.

Parameters:

  • query (str) – The text to search.

  • k (int, optional) – How many results to return. Defaults to 4.

  • param (dict, optional) – The search params for the index type. Defaults to None.

  • expr (str, optional) – Filtering expression. Defaults to None.

  • timeout (int, optional) – How long to wait before timeout error. Defaults to None.

  • kwargs (Any) – Collection.search() keyword arguments.

Returns:

Document results for search.

Return type:

List[Document]

similarity_search_by_vector(embedding: List[float], k: int = 4, param: dict | None = None, expr: str | None = None, timeout: float | None = None, **kwargs: Any) → List[Document][source]#

Perform a similarity search against the query string.

Parameters:

  • embedding (List[float]) – The embedding vector to search.

  • k (int, optional) – How many results to return. Defaults to 4.

  • param (dict, optional) – The search params for the index type. Defaults to None.

  • expr (str, optional) – Filtering expression. Defaults to None.

  • timeout (int, optional) – How long to wait before timeout error. Defaults to None.

  • kwargs (Any) – Collection.search() keyword arguments.

Returns:

Document results for search.

Return type:

List[Document]

similarity_search_with_relevance_scores(query: str, k: int = 4, **kwargs: Any) → list[tuple[Document, float]]#

Return docs and relevance scores in the range [0, 1].

0 is dissimilar, 1 is most similar.

Parameters:

  • query (str) – Input text.

  • k (int) – Number of Documents to return. Defaults to 4.

  • **kwargs (Any) –

    kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to

    filter the resulting set of retrieved docs.

Returns:

List of Tuples of (doc, similarity_score).

Return type:

list[tuple[Document, float]]

similarity_search_with_score(query: str, k: int = 4, param: dict | None = None, expr: str | None = None, timeout: float | None = None, **kwargs: Any) → List[Tuple[Document, float]][source]#

Perform a search on a query string and return results with score.

For more information about the search parameters, take a look at the pymilvus documentation found here: https://milvus.io/api-reference/pymilvus/v2.4.x/ORM/Collection/search.md

Parameters:

  • query (str) – The text being searched.

  • k (int, optional) – The amount of results to return. Defaults to 4.

  • param (dict) – The search params for the specified index. Defaults to None.

  • expr (str, optional) – Filtering expression. Defaults to None.

  • timeout (float, optional) – How long to wait before timeout error. Defaults to None.

  • kwargs (Any) – Collection.search() keyword arguments.

Return type:

List[float], List[Tuple[Document, any, any]]

similarity_search_with_score_by_vector(embedding: List[float] | Dict[int, float], k: int = 4, param: dict | None = None, expr: str | None = None, timeout: float | None = None, **kwargs: Any) → List[Tuple[Document, float]][source]#

Perform a search on an embedding and return results with score.

For more information about the search parameters, take a look at the pymilvus documentation found here: https://milvus.io/api-reference/pymilvus/v2.4.x/ORM/Collection/search.md

Parameters:

  • embedding (List[float] | Dict[int, float]) – The embedding vector being searched.

  • k (int, optional) – The amount of results to return. Defaults to 4.

  • param (dict) – The search params for the specified index. Defaults to None.

  • expr (str, optional) – Filtering expression. Defaults to None.

  • timeout (float, optional) – How long to wait before timeout error. Defaults to None.

  • kwargs (Any) – Collection.search() keyword arguments.

Returns:

Result doc and score.

Return type:

List[Tuple[Document, float]]

upsert(ids: List[str] | None = None, documents: List[Document] | None = None, **kwargs: Any) → List[str] | None[source]#

Update/Insert documents to the vectorstore.

Parameters:

  • ids (List[str] | None) – IDs to update - Let’s call get_pks to get ids with expression

  • documents (List[Document]) – Documents to add to the vectorstore.

  • kwargs (Any)

Returns:

IDs of the added texts.

Return type:

List[str]

Examples using Milvus