This service helps users find the most relevant information for their query by using a combination of search and machine learning algorithms to detect "signals" in the data. Built on top of Apache Solr, developers load their data into the service, train a machine learning model based on known relevant results, then leverage this model to provide improved results to their end users based on their question or query.
The Retrieve and Rank Service can be applied to a number of information retrieval scenarios. For example, an experienced technician who is going onsite and requires help troubleshooting a problem, or a contact center agent who needs assistance in dealing with an incoming customer issue, or a project manager finding domain experts from a professional services organization to build out a project team.
Queries (questions) associated with your documents
Service Runtime: User questions and queries
Indexed documents for retrieval
Machine learning model (Rank)
Service Runtime: A list of relevant documents and metadata
Retrieve: One Solr cluster with up to 50 MB of storage is FREE. Highly available clusters cost $0.30 per instance hour for a cluster of 4 GB memory and 32 GB of storage. You can create a cluster up to 7X that size. For example, a cluster size 5 with 20 GB of memory and 160 GB of storage costs $1.50 per instance hour. Additional clusters are charged for on an hourly basis.
Ranker Models: One ranker model is FREE per month. Additional rank models are $10.00 per rank model.
Rank API Calls
First one thousand API calls per month are FREE. Additional calls are $0.0009 per call.
You are charged only for the /rankers methods.
Rank Training Events
First four training events per month are FREE. Additional training events are $2.00 per training event.
Training events are tracked and charged for on a monthly basis.