Skip to main content


BagelDB (Open Vector Database for AI), is like GitHub for AI data. It is a collaborative platform where users can create, share, and manage vector datasets. It can support private projects for independent developers, internal collaborations for enterprises, and public contributions for data DAOs.

Installation and Setup

pip install betabageldb

Create VectorStore from texts

from langchain_community.vectorstores import Bagel

texts = ["hello bagel", "hello langchain", "I love salad", "my car", "a dog"]
# create cluster and add texts
cluster = Bagel.from_texts(cluster_name="testing", texts=texts)
# similarity search
cluster.similarity_search("bagel", k=3)
[Document(page_content='hello bagel', metadata={}),
Document(page_content='my car', metadata={}),
Document(page_content='I love salad', metadata={})]
# the score is a distance metric, so lower is better
cluster.similarity_search_with_score("bagel", k=3)
[(Document(page_content='hello bagel', metadata={}), 0.27392977476119995),
(Document(page_content='my car', metadata={}), 1.4783176183700562),
(Document(page_content='I love salad', metadata={}), 1.5342965126037598)]
# delete the cluster

Create VectorStore from docs

from langchain.text_splitter import CharacterTextSplitter
from langchain_community.document_loaders import TextLoader

loader = TextLoader("../../modules/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)[:10]
# create cluster with docs
cluster = Bagel.from_documents(cluster_name="testing_with_docs", documents=docs)
# similarity search
query = "What did the president say about Ketanji Brown Jackson"
docs = cluster.similarity_search(query)
Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the 

Get all text/doc from Cluster

texts = ["hello bagel", "this is langchain"]
cluster = Bagel.from_texts(cluster_name="testing", texts=texts)
cluster_data = cluster.get()
# all keys
dict_keys(['ids', 'embeddings', 'metadatas', 'documents'])
# all values and keys
{'ids': ['578c6d24-3763-11ee-a8ab-b7b7b34f99ba',
'embeddings': None,
'metadatas': [{}, {}, {}, {}, {}, {}, {}, {}],
'documents': ['hello bagel',
'this is langchain',
'hello bagel',
'this is langchain',
'hello bagel',
'this is langchain',
'hello bagel',
'this is langchain']}

Create cluster with metadata & filter using metadata

texts = ["hello bagel", "this is langchain"]
metadatas = [{"source": "notion"}, {"source": "google"}]

cluster = Bagel.from_texts(cluster_name="testing", texts=texts, metadatas=metadatas)
cluster.similarity_search_with_score("hello bagel", where={"source": "notion"})
[(Document(page_content='hello bagel', metadata={'source': 'notion'}), 0.0)]
# delete the cluster