- Level: Beginner
- Time to complete: 10 minutes
- This tutorial assumes a basic knowledge of NLP.
- You must be an Admin to complete this tutorial.
- Goal: After completing this tutorial, you will have built a complete English question answering app that can answer a variety of questions about jazz.
You need files the search will run on.
- Download the .zip file from gdrive and unpack it on your computer.
- Log in to deepset Cloud and go to Data>Files.
- Click Upload Files.
- Drop the files you unpacked in step 1 on the Upload Your Files page and click Upload. You should have 344 files. You can check that on the Dashboard.
Result: Your files are in your workspace and you can see them on the Files page.
In this step, you define how your search is going to run. We'll use a question answering pipeline template to create our pipeline.
- Go to Pipelines>New Pipeline.
- Under YAML Editor click Create Pipeline and select From Template.
- When the templates show up, select the English Question Answering template.
- In the Pipeline Designer, change the pipeline name in line 8 to Jazz_English_QA and save the pipeline.
- Click Deploy. This triggers indexing and makes your pipeline ready for running a search.
- Return to the Pipelines page and wait until the status of your pipeline changes to Indexed. This may take a while so please be patient.
Tip: When you hover your mouse over the status, you can see how many files have already been indexed.
Result: You created and deployed a pipeline. Your pipeline shows on the Pipelines page with the status Indexed.
Now it's time to test your pipeline.
- Go to Search.
- Select Jazz_English_QA as the pipeline you want to use.
- Now, search for an answer to this question: "How many people attended Duke Ellington's funeral?"
You should get a number of answers.
Result: There! You have built a live question answering system from beginning to end. You can now ask your app questions related to jazz and it will give you an answer.
Updated about 1 month ago