i have postgres vector extension no clue how to structure my embeddings though
#how would one store chunked embeddings with ts in postgres pgvector and access them in python
old jacinth
civic wedgeBOT
Hi @old jacinth. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
I'm sorry, but the provided knowledge sources do not contain specific information on how to store chunked embeddings with TypeScript in a PostgreSQL database using the pgvector extension and then access them in Python.
However, I can guide you on how to work with embeddings in Python and TypeScript using the Nomic platform.
In Python, you can create an embeddings dataset and interact with it using the nomic library. Here's an example of how to create an embeddings dataset:
from nomic import atlas
import numpy as np
num_embeddings = 10000
embeddings = np.random.rand(num_embeddings, 512)
dataset = atlas.map_data(embeddings=embeddings)
print(dataset)
(Source: Nomic Documentation - Data upload (https://docs.nomic.ai/atlas/introduction/data-upload))
You can also access your dataset's embeddings with map.embeddings:
from nomic import AtlasDataset
map = AtlasDataset('my-dataset').maps[0]
# projected embeddings are your 2D embeddings
projected_embeddings = map.embeddings.projected
# latent embeddings are your high-dim vectors
latent_embeddings = map.embeddings.latent
(Source: Nomic Documentation - Accessing Dataset State (https://docs.nomic.ai/reference/python-api/access-map-data))
In TypeScript, you can use the official TypeScript bindings to interact with the Nomic Atlas platform:
import { embed } from '@nomic-ai/atlas';
embed(['so much depends upon', 'a red wheel barrow'], `nk-123456789`).then(
(embeddings) => console.log({ embeddings })
);
(Source: Nomic Documentation - Typescript-api Overview (https://docs.nomic.ai/reference/typescript-api/overview))