AWS Kendra

Intelligent enterprise search service powered by machine learning. Through Langdock’s integration, you can access and manage AWS Kendra directly from your conversations.

Authentication: API Key (AWS Credentials) Category: AI & Search Availability: All workspace plans

Available Actions

Search

awskendra.search

Searches your Kendra index using natural language queries

Requires Confirmation: No

Parameters:

• query (TEXT, Required): Natural language query to search for in your Kendra index. For example: ‘How do I reset my password?’ or ‘sales report Q3 2024’

• pageSize (NUMBER, Optional): Number of results to return per page. Maximum is 100. If not specified, defaults to 10

• attributeFilter (MULTI_LINE_TEXT, Optional): e.g. {"EqualsTo": {"Key": "field", "Value": "text"}}

• queryResultType (SELECT, Optional): Filter results by type. Options: All results, Documents only, Answers only, Questions and answers only

• pageNumber (NUMBER, Optional): Page number to retrieve (1-10 for page size 10, 1-2 for page size 50). Note: AWS Kendra limits total retrievable results to 100

• facets (MULTI_LINE_TEXT, Optional): JSON array of document attribute names to get facet counts. Simple format: <JSON array>. Advanced format with max results: (see example below)

• sortingConfiguration (MULTI_LINE_TEXT, Optional): JSON object to sort results. IMPORTANT: Use “Get Index Configuration” first to verify which fields are sortable. Only fields marked as sortable in your index will work

• spellCorrection (SELECT, Optional): Enable automatic spell correction for queries to improve search accuracy. Options: Enabled, Disabled

• userContext (MULTI_LINE_TEXT, Optional): JSON object for user-specific filtering. GenAI format: JSON: email_id = [email protected]. Standard format: (JSON format)

• visitorId (TEXT, Optional): Unique identifier for tracking user sessions (e.g., a GUID). Do not use personally identifiable information like email

• requestedDocumentAttributes (MULTI_LINE_TEXT, Optional): JSON array of document attribute names to include in response (max 100). Common fields: <JSON array>. Reduces response size by limiting fields

• collapseConfiguration (MULTI_LINE_TEXT, Optional): JSON object to group/collapse similar results. Basic and expansion examples available

• documentRelevanceOverrides (MULTI_LINE_TEXT, Optional): JSON array to boost specific fields/values. Format: (see example below)

Output: Returns search results with the following structure:

• totalResults: Total number of results found

• results: Array of result objects containing:

  • id: Document ID

  • title: Document title

  • excerpt: Document excerpt

  • uri: Document URI

  • score: Relevance score

  • attributes: Document attributes (if available)

• facets: Facet results if requested

• spellSuggestions: Spell correction suggestions if available

• featuredResults: Featured results if available

---

Get Index Configuration

awskendra.getIndexConfiguration

Returns field configuration for your Kendra index. Shows field names, types (STRING, DATE, LONG), and properties (searchable, sortable, facetable). Run this BEFORE searching to know which fields you can use for filtering and sorting.

Requires Confirmation: No

Parameters: None

Output: Returns index configuration with the following structure:

• indexName: Name of the index

• status: Index status

• edition: Index edition

• fields: Array of field objects containing:

  • name: Field name

  • type: Field type (STRING, DATE, LONG, etc.)

  • searchable: Whether field is searchable

  • sortable: Whether field is sortable

  • facetable: Whether field is facetable

  • displayable: Whether field is displayable

  • importance: Field importance score

• summary: Summary statistics including:

  • totalFields: Total number of fields

  • sortableFields: List of sortable field names

  • searchableFields: List of searchable field names

  • dateFields: List of date field names

  • sortableDateFields: List of sortable date field names

Common Use Cases

• Data Management — Manage and organize your AWS Kendra data

• Automation — Automate workflows with AWS Kendra

• Reporting — Generate insights and reports

• Integration — Connect AWS Kendra with other tools

Best Practices

1

Getting Started

• Enable the AWS Kendra integration in your workspace settings

• Authenticate using API Key (AWS Credentials)

• Test the connection with a simple read operation

• Explore available actions for your use case

2

Important Considerations

• Ensure proper authentication credentials

• Respect rate limits and API quotas

• Review data privacy settings

• Test operations in a safe environment first

Troubleshooting

Issue	Solution
Authentication failed	Verify your API Key (AWS Credentials) credentials
Rate limit exceeded	Reduce request frequency
Data not found	Check permissions and data availability
Connection timeout	Verify network connectivity

Support

For additional help with the AWS Kendra integration, contact [email protected]

Additional resources:

• Docs: https://docs.langdock.com/product/introduction

• API: https://docs.langdock.com/api-endpoints/api-introduction

• Learn: https://docs.langdock.com/resources/prompt-elements

Related integrations: Asana · Azure AI Search