QdrantVectorStore

Setup:

Install langchain-qdrant package.

pip install -qU langchain-qdrant

Key init args — indexing params: collection_name: Name of the collection. embedding: Embedding function to use. sparse_embedding: Optional sparse embedding function to use.

Key init args — client params: client: Qdrant client to use. retrieval_mode: Retrieval mode to use.

Instantiate:

from langchain_qdrant import QdrantVectorStore
from qdrant_client import QdrantClient
from qdrant_client.http.models import Distance, VectorParams
from langchain_openai import OpenAIEmbeddings

client = QdrantClient(":memory:")

client.create_collection(
    collection_name="demo_collection",
    vectors_config=VectorParams(size=1536, distance=Distance.COSINE),
)

vector_store = QdrantVectorStore(
    client=client,
    collection_name="demo_collection",
    embedding=OpenAIEmbeddings(),
)

Add Documents:

from langchain_core.documents import Document
from uuid import uuid4

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

documents = [document_1, document_2, document_3]
ids = [str(uuid4()) for _ in range(len(documents))]
vector_store.add_documents(documents=documents, ids=ids)

Delete Documents:

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

Search:

results = vector_store.similarity_search(
    query="thud",
    k=1,
)
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

*thud[
    {
        "bar": "baz",
        "_id": "0d706099-6dd9-412a-9df6-a71043e020de",
        "_collection_name": "demo_collection",
    }
]

Search with filter:

from qdrant_client.http import models

results = vector_store.similarity_search(
    query="thud",
    k=1,
    filter=models.Filter(
        must=[
            models.FieldCondition(
                key="metadata.bar",
                match=models.MatchValue(value="baz"),
            )
        ]
    ),
)
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

*thud[
    {
        "bar": "baz",
        "_id": "0d706099-6dd9-412a-9df6-a71043e020de",
        "_collection_name": "demo_collection",
    }
]

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=0.832268] foo [{'baz': 'bar', '_id': '44ec7094-b061-45ac-8fbf-014b0f18e8aa', '_collection_name': 'demo_collection'}]

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=0.832268] foo [{'baz': 'bar', '_id': '44ec7094-b061-45ac-8fbf-014b0f18e8aa', '_collection_name': 'demo_collection'}]

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={
            "bar": "baz",
            "_id": "0d706099-6dd9-412a-9df6-a71043e020de",
            "_collection_name": "demo_collection",
        },
        page_content="thud",
    )
]