💻Your First Text To Image Search!

Now that it is inserted, let's perform our first text to image search!

Now, let us perform our first text to image search!

So what do we need to do? On the previous page, we inserted our documents with vectors. Now, we want to search those same vectors using text.

import requests
def encode_text(text, project, api_key):
    return requests.post(
        url="https://api-dev-aueast.relevance.ai/v1/services/encoders/textimage",
        headers={"Authorization": project+ ":" + api_key},
        json={
            "text": text
        }
    ).json()["vector"]

Store your encoding like below:

vector = encode_text("frogs", project, api_key)

Now that you have the vector, you can perform your first search using the vector search endpoint.

We then run our vector search on our results!

dataset_id = "coco-dataset"
url = "https://api-dev-aueast.relevance.ai/v1/services/search/vector"
response = requests.post(
    url=url,
    headers={"Authorization": project + ":" + api_key},
    json={
        "dataset_id": dataset_id,
        "multivector_query": [{"vector": vector, "fields": ["image_vector_"]}]})
response.json()

Go ahead and try out more searches!