Stack Overflow
Stack Overflow

Questions tagged [retrieve-and-rank]

Use the Retrieve and Rank tag when the question is about the IBM Watson Retrieve and rank service.

The IBM Watson Retrieve and Rank 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.

Documentation: http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/doc/retrieve-rank/

95 questions
0
votes
1 answer

Why does Retrieve and Rank ignore my indexes when querying a collection?

We have a Solr collection in Retrieve and Rank which contains, among others, a field called document_sub_type. This field is indexed in the Solr schema, but does not have a field type value (I understand that fields intended to be used by the…
David Powell
  • 537
  • 1
  • 4
  • 16
0
votes
0 answers

solr version that retrieve and rank uses on bluemix

How to verify what version of solr is being used by Retrieve and Rank service on Bluemix in order to refer exact version of solr api and documentation of Solr.
Sasikanth PVS
  • 1
0
votes
1 answer

Watson Retrieve & Rank : Difference in answer when asked using Web UI versus an application

Please see this JSON returned when asked the question : What are the basic methods of Optional ? This is not the perfect match answer that is being returned in the Retrieve and Rank Tooling ( pasted below this JSON snippet). Can you please help me…
Sandhya Kapoor
  • 170
  • 9
0
votes
1 answer

Trained Watson retrieve and rank service with 80 questions : can I create a ranker?

I am not getting the answer from Retrieve and Rank which is a perfect match to the question( I get the perfectly matched answer in the Retrieve and Rank WebUI. The data is trained with 80 questions, creating a ranker will help in getting the…
Sandhya Kapoor
  • 170
  • 9
0
votes
1 answer

Solr Cloud Config not uploading

I'm running curl. I'm not getting an error. curl -X POST -u "username":"pwd" "https://gateway.watsonplatform.net/retrieve-and-rank/api/v1/solr_clusters/scc2c46f2f_a84c_42d7_8857_a9999704dde4/config/Kbase" --data-binary @solr_config.zip However,…
user269964
  • 159
  • 11
0
votes
1 answer

IBM Watson - Rank items based users reveled preferences

In an ecommerce website, users can bookmark products and bookmark other users. I'd like to display a custom feed of products for logged-in users. Questions: 1) How to get products user would like most, based on the similarity of products they…
Francisco Campaña
  • 198
  • 1
  • 11
0
votes
2 answers

Why can't I have a colon in a Retrieve and Rank Solr query?

If I send a natural-language query to Retrieve and Rank (Solr), it will return an error if the query contains a colon. It seems to be attempting to interpret the word just prior to the colon as a field name. Is there any way to prevent this, and are…
David Powell
  • 537
  • 1
  • 4
  • 16
0
votes
1 answer

Delete document from watson rank and retrieve

I've created a watson rank and retrieve collection. I was able to add a document and I can search it, but it was a test document. How do I delete it? This is what I want to delete: // add a document var doc = { id : 1234, title_t : 'Hello',…
user269964
  • 159
  • 11
0
votes
1 answer

Why isn't the document with an exact match the first result in a Retrieve and Rank Solr query?

We have taken a large quantity of documents, broken them up into segments ("answer units") using Watson's Document Conversion service, and added them to a Retrieve and Rank Solr collection. If I run a query against the collection using a copy/paste…
David Powell
  • 537
  • 1
  • 4
  • 16
0
votes
1 answer

Upload documents into Watson's Retrieve & Rank service

I'm implementing a solution using Watson's Retrieve & Rank service. When I use the tooling interface, I upload my documents and they appear as a list, where I can click on any of them to open up all the Titles that are inside the document ( Answer…
Archerspk
  • 137
  • 11
0
votes
1 answer

Search by proximity and Ranker

I want to know if Retrieve & Rank service, and especially during the ranking, allows searching by proximity. Example : Ranker learned : a. Query = "I have a problem with my mailbox" b. Documents with pertinence score : "Doc1":3, "Doc2":4",…
Julien Preisner
  • 1
  • 1
  • 5
0
votes
1 answer

Rename Rank and Retrieve Cluster Name

So I created a Solr Cluster via the Rank and Retrieve web tooling. The name of the cluster is similar to "Cluster Client". Problem here is the online tooling allows names with blanks. Now, after training the ranker I want to access the query…
DerCommodore
  • 88
  • 1
  • 10
0
votes
1 answer

How to execute searchAndRank method in IBM Watson Retrieve And Rank API through Java wrapper

I am trying to perform a retrieveAndRank query using Java wrapper. I follow the online javadocs for Retrieve and Rank API. The example there for SearchAndRank…
icordoba
  • 1,834
  • 2
  • 33
  • 60
0
votes
1 answer

Element type \"field\" must be followed by either attribute specifications, \">\" or \"/>\"."

I am try to make a collection with my solr _config. I get the following error: { "failure": { "10.47.24.19:5285_solr": "org.apache.solr.client.solrj.impl.HttpSolrClient$RemoteSolrException:Error from server at…
S.Doe
  • 49
  • 1
  • 10
0
votes
1 answer

Post to Bluemix Retrieve_and_Rank gives status 0, but does not work

I am trying to index some web pages in Bluemix Retrieve and Rank service. So I did crawled my seeds with nutch 1.11, dumped the crawled data(about 9000 URLs) as files, posted those that are possible e.g xml files to my Collection: Post_url =…
S.Doe
  • 49
  • 1
  • 10
1 2 3 4
5
6 7