Vector stores

​

Overview

​

Interface

• add_documents - Add documents to the store.
• delete - Remove stored documents by ID.
• similarity_search - Query for semantically similar documents.

​

Initialization

from langchain_core.vectorstores import InMemoryVectorStore
vector_store = InMemoryVectorStore(embedding=SomeEmbeddingModel())

​

Adding documents

vector_store.add_documents(documents=[doc1, doc2], ids=["id1", "id2"])

​

Deleting documents

vector_store.delete(ids=["id1"])

​

Similarity search

similar_docs = vector_store.similarity_search("your query here")

• k — number of results to return
• filter — conditional filtering based on metadata

​

Similarity metrics & indexing

• Cosine similarity
• Euclidean distance
• Dot product

​

Metadata filtering

vector_store.similarity_search(
  "query",
  k=3,
  filter={"source": "tweets"}
)

​

Top integrations

pip install -qU langchain-openai

import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
  os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")

from langchain_openai import OpenAIEmbeddings

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

pip install -qU langchain-core

from langchain_core.vectorstores import InMemoryVectorStore

vector_store = InMemoryVectorStore(embeddings)

​

All Vectorstores