Clarifai's patented technology uses AI to automatically index your unstructured data for deep search. Concepts identified by our Armada Predict technology can be used as search terms. Even search with images to find similar images.
Help customers "find more like this" and increase conversion.
Discover similar images based on visual characteristics.
Augment media with metadata to improve search.
Let customers snap a photo to search your catalog.
Order your search results with the intuitive insights of AI. Your model can identify concepts in your data and rank your search results by how confident it is that a given concept is present. You can even rank search results by how similar one input is to another input.
Trim down the amount of data returned in search. For example, you may only want to see inputs that one of your collaborators has labeled with the word “dog”. Or perhaps you want only those inputs that were captured in a certain geographical region.
Combine multiple search parameters. For example, you can find all the inputs within a geographical region with a "weapon" in them, or all annotations assigned to user "Joe", or visually similar product images that are assigned the word "XL" in metadata.
Discover and retrieve the most relevant images from your dataset by searching for the concepts identified by your AI models. Patented technology developed by Clarifai gives you the ability to search for predictions immediately after training—no waiting on re-indexing. Build recommendation systems with rapid retraining cycles for active learning on the fly.
Go beyond simple keyword searches. Draw a direct line from the source of an idea (an image, video, or block of text), to the information you need. No guessing keywords required. Similarly Spacetime Search can be combined with detection models so that you can search for a specific thing a region of an image. You can even use an image to find a specific frame within a video clip.
Combine visual search with location-awareness to organize your data by place. Include latitude and longitude information when you upload your data, and then filter to find all inputs within a given radius. Or even define a region on the map and limit your results to the inputs within that region.
Attach additional information to your inputs as you upload them to the Clarifai platform. Add product IDs, user IDs, or any other relevant information needed to drive specific business outcomes. Metadata is indexed so that the result is filtered down and then ranked according to the ranking criteria you provide.
Annotations are the human-labeled concepts on your inputs. Typically part of your "training" dataset, these inputs are indexed alongside model predictions and similarity search information. Collaboration tools make it easy to track annotations done by different team members.
Provide additional information about annotation sets. For example, you might label a “training split”, a “golden set”, or “data export 73”. Export your data and use annotations for any complex application logic. Include contextual information in the form of generic JSON blobs.
Find all data that is NOT similar to a given input. For example, you can search for all the inputs NOT annotated “dog”. Even combine negated search terms for more advanced tasks.
Work quickly and intuitively. We tell you possible search terms. Autocomplete suggests custom concepts and concepts predicted by the AI models in your default workflow. See autocomplete in action in Clarifai Portal.
Get started with 1,000 free operations each month. Request a free API key and start building today.
curl -X POST \
-H "Authorization: Key YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '
{
"query": {
"ands": [
{
"output": {
"data": {
"concepts": [
{
"name": "people"
}
]
}
}
}
]
}
}'\
https://api.clarifai.com/v2/searches
app.inputs.search({ concept: {name: 'people'} }).then(
function(response) {
// do something with response
},
function(err) {
// there was an error
}
);
from clarifai.rest import ClarifaiApp
app = ClarifaiApp(api_key='YOUR_API_KEY')
# search by public concept
app.inputs.search_by_predicted_concepts(concept='people')
# search by a list of concepts
app.inputs.search_by_predicted_concepts(concepts=['people'])
# search by concept id
app.inputs.search_by_predicted_concepts(concept_id='ai_dP13sXL4')
# search by a list of concept ids
app.inputs.search_by_predicted_concepts(concept_ids=['ai_dP13sXL4'])
client.searchInputs(SearchClause.matchConcept(Concept.forName("people")))
.getPage(1)
.executeSync();
// First create a search term with a concept you want to search.
ClarifaiConcept *conceptFromGeneralModel = [[ClarifaiConcept alloc] initWithConceptName:@"people"];
ClarifaiSearchTerm *searchTerm = [ClarifaiSearchTerm searchByPredictedConcept:conceptFromGeneralModel];
[app search:@[searchTerm] page:@1 perPage:@20 completion:^(NSArray<ClarifaiSearchResult *> *results, NSError *error) {
// Print output of first search result.
NSLog(@"inputID: %@", results[0].inputID);
NSLog(@"URL: %@", results[0].mediaURL);
NSLog(@"probability of public concept: %@", results[0].score);
}];
If you're encountering a technical or payment issue, the customer support team will be happy to assist you.
Contact support© 2023 Clarifai, Inc. Terms of Service Content TakedownPrivacy Policy
© 2023 Clarifai, Inc. Terms of Service Content TakedownPrivacy Policy