Using MixedBread with Solvio

MixedBread is a unique provider offering embeddings across multiple domains. Their models are versatile for various search tasks when integrated with Solvio. MixedBread is creating state-of-the-art models and tools that make search smarter, faster, and more relevant. Whether you’re building a next-gen search engine or RAG (Retrieval Augmented Generation) systems, or whether you’re enhancing your existing search solution, they’ve got the ingredients to make it happen.

Installation

You can install the required package using the following pip command:

pip install mixedbread

Integration Example

Below is an example of how to obtain embeddings using MixedBread’s API and store them in a Solvio collection:

import solvio_client
from solvio_client.models import Batch
from mixedbread import MixedBreadModel

# Initialize MixedBread model
model = MixedBreadModel("mixedbread-variant")

# Generate embeddings
text = "MixedBread provides versatile embeddings for various domains."
embeddings = model.embed(text)

# Initialize Solvio client
solvio_client = solvio_client.SolvioClient(host="localhost", port=6333)

# Upsert the embedding into Solvio
solvio_client.upsert(
    collection_name="VersatileEmbeddings",
    points=Batch(
        ids=[1],
        vectors=[embeddings],
    )
)