Time: 10 minLevel: BeginnerOpen In Colab

Mistral

Qdrant is compatible with the new released Mistral Embed and its official Python SDK that can be installed as any other package:

Setup

Install the client

pip install mistralai

And then we set this up:

from mistralai.client import MistralClient
from qdrant_client import QdrantClient
from qdrant_client.models import PointStruct, VectorParams, Distance

collection_name = "example_collection"

MISTRAL_API_KEY = "your_mistral_api_key"
client = QdrantClient(":memory:")
mistral_client = MistralClient(api_key=MISTRAL_API_KEY)
texts = [
    "Qdrant is the best vector search engine!",
    "Loved by Enterprises and everyone building for low latency, high performance, and scale.",
]

Let’s see how to use the Embedding Model API to embed a document for retrieval.

The following example shows how to embed a document with the models/embedding-001 with the retrieval_document task type:

Embedding a document

result = mistral_client.embeddings(
    model="mistral-embed",
    input=texts,
)

The returned result has a data field with a key: embedding. The value of this key is a list of floats representing the embedding of the document.

Converting this into Qdrant Points

points = [
    PointStruct(
        id=idx,
        vector=response.embedding,
        payload={"text": text},
    )
    for idx, (response, text) in enumerate(zip(result.data, texts))
]

Create a collection and Insert the documents

client.create_collection(collection_name, vectors_config=VectorParams(
        size=1024,
        distance=Distance.COSINE,
    )
)
client.upsert(collection_name, points)

Searching for documents with Qdrant

Once the documents are indexed, you can search for the most relevant documents using the same model with the retrieval_query task type:

client.search(
    collection_name=collection_name,
    query_vector=mistral_client.embeddings(
        model="mistral-embed", input=["What is the best to use for vector search scaling?"]
    ).data[0].embedding,
)

Using Mistral Embedding Models with Binary Quantization

You can use Mistral Embedding Models with Binary Quantization - a technique that allows you to reduce the size of the embeddings by 32 times without losing the quality of the search results too much.

At an oversampling of 3 and a limit of 100, we’ve a 95% recall against the exact nearest neighbors with rescore enabled.

Oversampling112233
RescoreFalseTrueFalseTrueFalseTrue
Limit
100.534440.8577780.5344440.9188890.5333330.941111
200.5083330.8377780.5083330.9038890.5083330.927778
500.4922220.8344440.4922220.9035560.4928890.940889
1000.4991110.8454440.4985560.9183330.4976670.944556

That’s it! You can now use Mistral Embedding Models with Qdrant!

Mistral