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

How to invoke/use the ranker ID from within the nodeJs code to call Retrieve & Rank API?

I have tried a successful approach in Watson Retrieve and Rank, to set the 'ranker_id' from within the code snippet versus setting it as an environment variable. Below is the code snippet: var qs = require('querystring'); // search…
Saurav Raiguru
  • 1
0
votes
1 answer

Is my ranker properly trained?

I asked a question What is the ...? using /fcselect handler without ranker ID and got the following docs : "docs": [ {"id": "100"}, // ranked first {"id": "101"}, // ranked second ... {"id": "198"}, // ranked second from last (99th) …
takehilo
  • 21
  • 4
0
votes
1 answer

Training a ranker with train.py script

I'm currently trying to create a ranker by running the train.py script provided by the Retrieve & Rank Documentation. I issue the following command when trying to create the ranker: train.py -u usernameHere:PasswordHere -i …
Archerspk
  • 137
  • 11
0
votes
1 answer

Can I use other similarity class?

I'm trying to configure schema.xml included in blank-example-solr-config.zip. I found the schema.xml has the following line: Is it necessary to use this similarity…
takehilo
  • 21
  • 4
0
votes
1 answer

Retrieve and rank cluster size

will there be any impact of ingested contents when we do resize of cluster size of Retrieve and Rank service from 2 units to 4 units? Also how can we get current index size of RnR cluster?
Shivam
  • 13
  • 3
0
votes
0 answers

Creating Cluster for Watson Retrieve & Rank service

I am new to retrieve & rank api. Just started working on my first tutorial. When I try to create a new cluster (free) with 50 mb storage, I get the following error: Unable to create new Cluster: Incorrect If-Match header Reproduction steps: 1) Click…
Nadia Karch
  • 1
0
votes
1 answer

With Bluemix Retrieve&Rank, How do we implement a system to continuously learn?

With reference to the Web page below, using the Retrieve & Rank service of IBM Bluemix, we are creating a bot that can respond to inquiries. Question: After learning the ranker once, based on the user's response to the inquiry, how can we construct…
Shota.N
  • 1
0
votes
1 answer

Where can I find the simple information of the format for uploading questions?

Situation: I want to train and simple configure the retrieve and rank service. I just uploaded some PDFs and now I want to upload some questions. In the documentation I do not find a simple information how the csv file must be structured and which…
Thomas Suedbroecker
  • 454
  • 6
  • 23
0
votes
1 answer

R&R not authorized for cluster error

I'm getting a not authorized when accessing one of the clusters I created. I can't even delete it. Error from server at https://gateway.watsonplatform.net/retrieve-and-rank/api/v1/solr_clusters/sc7eb72dcd_f6c6_4608_a9d4_4a406c0bbc2d/solr:…
Jeff Boston
  • 1
  • 3
0
votes
1 answer

Upload questions to Retrieve and Rank using cURL, visible in webtool

Is there a way to upload questions to "Retrieve and Rank" (R&R) using cURL and have them be visible in the web tool? I started testing R&R using web tool (which I find very intuitive). Now, I have started testing the command line interface (CLI)…
Chi Kwong Tang
  • 1
0
votes
2 answers

Synonyms maintenance: How to delete synonyms?

We are trying to delete synonyms using the following curl command. curl -v -X DELETE -u "username":"password"…
Daniel Moura
  • 21
  • 5
0
votes
1 answer

Search engine with few documents just imported

I'm wondering if it's possible to search with the Retrieve and Rank service on few PDF documents you just imported ? Example : I want to search informations on 4 PDF documents, so I import documents in the system and use my search engine to find my…
pierre_comalada
  • 300
  • 3
  • 11
0
votes
1 answer

IBM Watson - Retrieve and Rank: How to tell that a text in a PDF document should be considered a field?

I am loading lots of PDF documents in a Retrieve and Rank service but I do not know to to tell Solr or IBM Retrieve and Rank service that a specific part of my PDF document should be considered as a field for later query, for example, a name, or a…
Wagner Santana
  • 3
  • 3
0
votes
2 answers

How can I download all documents from Retrieve and Rank (Solr)?

We have a Cloudant database on Bluemix that contains a large number of documents that are answer units built by the Document Conversion service. These answer units are used to populate a Solr Retrieve and Rank collection for our application. The…
David Powell
  • 537
  • 1
  • 4
  • 16
0
votes
1 answer

Watson Retrieve and Rank does not show uploaded document in the list of answers to be ranked

This is the html document created using https://document-conversion-demo.mybluemix.net/ .Uploaded this documents using R&R WebUI, when I rank a question: What is spring boot? this document is not displayed in the list of answers. Has this document…
Sandhya Kapoor
  • 170
  • 9
1 2 3
4
5 6 7