Amazon Kendra is a extremely correct and easy-to-use clever search service powered by machine studying (ML). Amazon Kendra affords a collection of knowledge supply connectors to simplify the method of ingesting and indexing your content material, wherever it resides.
For a lot of organizations, Field Content material Cloud is a core a part of their content material storage and lifecycle administration technique. An enterprise Field account typically comprises a treasure trove of belongings, corresponding to paperwork, displays, data articles, and extra. Now, with the brand new Amazon Kendra knowledge supply connector for Field, these belongings and any related duties or feedback could be listed by Amazon Kendra’s clever search service to disclose content material and unlock solutions in response to customers’ queries.
On this put up, we present you the best way to arrange the brand new Amazon Kendra Field connector to selectively index content material out of your Field Enterprise repository.
Resolution overview
The answer consists of the next high-level steps:
- Create a Field app for Amazon Kendra through the Field Developer Console.
- Add pattern paperwork to your Field account.
- Create a Field knowledge supply through the Amazon Kendra console.
- Index the pattern paperwork from the Field account.
Stipulations
To check out the Amazon Kendra connector for Field, you want the next:
Create a Field app for Amazon Kendra
Earlier than you configure an Amazon Kendra Field knowledge supply connector, you should first create a Field app.
- Log in to the Field Enterprise Developer Console.
- Select Create New App.
- Select Customized App.
- Select Server Authentication (with JWT).
- Enter a reputation in your app. For instance,
KendraConnector
. - Select Create App.
- In your created app in My Apps, select the Configuration tab.
- Within the App Entry Stage part, select App + Enterprise Entry.
- Within the Software Scopes part, examine that the next permissions are enabled:
- Within the Superior Options part, choose Make API calls utilizing the as-user header.
- Within the Add and Handle Public Keys part, select Generate a Public/Non-public Keypair.
This requires two-step verification. A JSON textual content file is downloaded to your laptop.
- Select OK to simply accept this obtain.
- Select Save Modifications.
- On the Authorization tab, select Overview and Submit.
- Choose Submit app inside this enterprise and select Submit.
Your Field Enterprise proprietor must approve the app earlier than you should use it.
Go to the downloads listing in your laptop to evaluation the downloaded JSON file. It comprises the shopper ID, shopper secret, public key ID, non-public key, move phrase, and enterprise ID. You want these values to create the Field knowledge supply in a later step.
Add pattern paperwork to your Field account
On this step, you add pattern paperwork to your Field account. Later, we use the Amazon Kendra Field knowledge supply to crawl and index these paperwork.
- Obtain AWS_Whitepapers.zip to your laptop.
- Extract the recordsdata to a folder known as
AWS_Whitepapers
. - Add the
AWS_Whitepapers
folder to your Field account.
Create a Field knowledge supply
So as to add an information supply to your Amazon Kendra index utilizing the Field connector, you should use an current Amazon Kendra index, or create a brand new Amazon Kendra index. Then full the next steps to create a Field knowledge supply:
- On the Amazon Kendra console, select Indexes within the navigation pane.
- From the checklist of indexes, select the index that you just wish to add the information supply to.
- Select Add knowledge sources.
- From the checklist of knowledge supply connectors, select Add connector beneath Field.
- On the Specify knowledge supply particulars web page, enter an information supply identify and elective description.
- Select Subsequent.
- Open the JSON file you downloaded from the Field Developer Console.
It comprises values for clientID
, clientSecret
, publicKeyID
, privateKey
, passphrase
, and enterpriseID
.
- On the Outline entry and safety web page, within the Supply part, for Field enterprise ID, enter the worth of the
enterpriseID
subject. - Within the Authentication part, beneath AWS Secrets and techniques Supervisor secret, select Create and add a brand new secret.
- For Secret identify, enter a reputation for the key, for instance,
boxsecret1
. - For the remaining fields, enter the corresponding values from the downloaded JSON file.
- Select Save and add secret.
- Within the IAM position part, select Create a brand new position (Really useful) and enter a job identify, for instance,
box-role
.
For extra data on the required permissions to incorporate within the IAM position, see IAM roles for knowledge sources.
- Select Subsequent.
- On the Configure sync settings web page, within the Sync scope part, you may embody Field net hyperlinks, feedback, and duties in your index, along with file contents. Use the default setting (unchecked) for this put up.
- For Extra configuration (change log) – elective, use the default setting (unchecked).
- For Extra configuration (regex patterns) – elective, select Embrace patterns.
- For Kind, select Path
- For Path – elective, enter the trail to the pattern paperwork you uploaded earlier:
AWS_Whitepapers/
. - Select Add.
- Within the Sync run schedule part, select Run on demand.
- Select Subsequent.
- On the Set fields mapping web page, you may outline how the information supply maps attributes from Field objects to your index. Use the default settings for this put up.
- Select Subsequent.
- On the Overview and create web page, evaluation the main points of your Field knowledge supply.
- To make modifications, select the Edit button subsequent to the merchandise that you just wish to change.
- Whenever you’re achieved, select Add knowledge supply so as to add your Field knowledge supply.
After you select Add knowledge supply, Amazon Kendra begins creating the information supply. It will probably take a number of minutes for the information supply to be created. When it’s full, the standing of the information supply modifications from Creating
to Energetic
.
Index pattern paperwork from the Field account
You configured the information supply sync run schedule to run on demand, so you should begin it manually.
- On the Amazon Kendra console, navigate to your index.
- Select your new knowledge supply.
- Select Sync now.
The present sync state modifications to Syncing – crawling
, then to Syncing – indexing
.
After about 10 minutes, the present sync state modifications to idle
, the final sync standing modifications to Profitable
, and the Sync run historical past panel reveals extra particulars, together with the variety of paperwork added.
Take a look at the answer
Now that you’ve got ingested the AWS whitepapers out of your Field account into your Amazon Kendra index, you may take a look at some queries.
- On the Amazon Kendra console, select Search listed content material within the navigation pane.
- Within the question subject, enter a take a look at question, corresponding to
What databases are supplied by AWS?
You possibly can attempt your individual queries too.
Congratulations! You may have efficiently used Amazon Kendra to floor solutions and insights based mostly on the content material listed out of your Field account.
Clear up
To keep away from incurring future prices, clear up the sources you created as a part of this answer.
- For those who created a brand new Amazon Kendra index whereas testing this answer, delete it.
- For those who added a brand new knowledge supply utilizing the Amazon Kendra connector for Field, delete that knowledge supply.
- Delete the
AWS_Whitepapers
folder and its contents out of your Field account.
Conclusion
With the Amazon Kendra Field connector, organizations could make invaluable data trapped of their Field accounts out there to their customers securely utilizing clever search powered by Amazon Kendra.
On this put up, we launched you to the fundamentals, however there are lots of further options that we didn’t cowl. For instance:
- You possibly can allow user-based entry management in your Amazon Kendra index, and limit entry to Field paperwork based mostly on the entry controls you could have already configured in Field
- You possibly can index further Field object varieties, corresponding to duties, feedback, and net hyperlinks
- You possibly can map Field object attributes to Amazon Kendra index attributes, and allow them for faceting, search, and show within the search outcomes
- You possibly can combine the Field knowledge supply with the Customized Doc Enrichment (CDE) functionality in Amazon Kendra to carry out further attribute mapping logic and even customized content material transformation throughout ingestion
To find out about these prospects and extra, consult with the Amazon Kendra Developer Information.
Concerning the Authors
Bob Strahan is a Principal Options Architect within the AWS Language AI Providers workforce.