feed and Index
The following instructions explain how you can import files to feed to Haystack index to find answers to users questions.
Feed the Index
Haystack will use the documents pushed into its index to find answers to the user questions
To feed this index:
- Open the SmartHub Administration page at http(s)://<web-app-url>/_admin.
- Go to Questions and Answers > Feed And Index.
- Drag-and-drop text documents (files must have extension .txt) into the box.
Remove All Files from Index
All pushed files into Haystack can be deleted.
Right after this action, the Auto Q&A system will not be able to answer to any question.
WARNING! Removing all files cannot be undone!
To purge the index:
- Open the SmartHub Administration page at http(s)://<web-app-url>/_admin.
- Go to Questions and Answers > Feed And Index.
- Click on Remove under Remove files from Auto Q&A provider system.
Set Up Using an AutoClassifier Pipeline Stage
As an alternative, you can feed the index at crawl time using Connectivity Hub and AutoClassifier.
-
In AutoClassifier, add a SmartHub Q&A Document Feeder stage.
The stage assumes Haystack is set up to use Elasticsearch for indexing.
Parameters required include:
- Elasticsearch address
- Index name
Source document property name represents the metadata name from Connectivity Hub.
The connection between Connectivity Hub and AutoClassifier is done through the enrichment component.
See here how to set it up.
How to Set Up Haystack
In order to install, configure, and run Haystack, please follow the How to install and configure Haystack steps.