Skip to main content

​
Overview

Azure AI Search is Microsoft’s AI-powered information retrieval platform. Through Langdock’s integration, you can perform semantic vector searches across your indexed documents directly from conversations.
Authentication: API Key
Category: AI & Search
Availability: All workspace plans

​
Prerequisites

Before setting up the integration, make sure you have:
  • An Azure subscription with access to Azure AI Search
  • An Azure AI Search service instance with at least one index
  • An admin API key for your Azure AI Search service
  • Documents uploaded to your index with vector embeddings (1536 dimensions for OpenAI’s text-embedding-ada-002)
Pro tip: If you’re new to Azure AI Search, check out Microsoft’s Vector Search documentation to set up your first index with vector search support.

​
Setup

1

Navigate to Integrations

In Langdock, go to Integrations and find Azure AI Search in the integrations list.
2

Enter Your Credentials

Fill in the required configuration fields (see table below).
3

Test the Connection

Save the integration - Langdock will validate that your index exists and is accessible.
4

Start Searching

Tag the integration with @ in any chat or add the Search documents action to your assistant to search your indexed documents.

​
Configuration Parameters

​
Required Fields

FieldDescriptionExample
NameA name for this connectionCompany Knowledge Base
API KeyAdmin key from Azure Portal -> KeysYour admin key
Index NameThe exact name of your Azure AI Search indexlangdock-prod-company
URLYour Azure AI Search service endpointhttps://my-service.search.windows.net
Search FieldThe vector field name in your index schemacontentVector
Top KNumber of search results to retrieve5

​
Optional Fields

FieldDescriptionDefault
Embedding DimensionDimension of your vector embeddings1536
Embedding ModelModel used for embeddings (display only)Ada v2
SelectComma-separated fields to returnAll fields
FilterOData filter expression to narrow resultsNone
Where to find your credentials:
  • Service URL: Azure Portal -> Your Search service -> Overview -> copy the Url field
  • API Key: Azure Portal -> Your Search service -> Keys -> copy an admin key

​
Available Actions

​
Search Documents

azureaisearch.searchDocuments
Performs semantic vector search across your indexed documents. Requires Confirmation: No Parameters:
  • query (VECTOR, Required): Vector query for semantic search
Output: Returns search results with the following structure:
  • value: Array of search result objects containing:
    • @search.score: Relevance score
    • @search.highlights: Highlighted text snippets
    • Field values from the indexed documents
  • @odata.count: Total number of results
  • @odata.nextLink: Link to next page of results (if available)
Generating embeddings: You can use the Langdock Embedding API to generate the vector embeddings needed for your Azure AI Search index.

​
Common Use Cases

Enterprise Knowledge Search

Search across internal documentation, policies, and knowledge bases using natural language

Research & Analysis

Find relevant research papers, reports, and data from large document collections

Customer Support

Quickly retrieve product information, FAQs, and support articles to answer customer queries

Content Discovery

Surface relevant content from archives, wikis, or document repositories

​
Troubleshooting

IssueCauseSolution
Index not foundIndex name mismatch or doesn’t existVerify the exact index name in Azure Portal matches your configuration (case-sensitive)
No search resultsNo documents or invalid embeddingsConfirm documents are uploaded with valid 1536-dimension embeddings in your vector field
Low search scoresEmbedding model mismatchEnsure all documents use the same embedding model (e.g., text-embedding-ada-002)
Authentication failedInvalid or expired API keyCopy a fresh Admin Key from Azure Portal -> Keys
Validation checklist
  • Service URL format: https://[service-name].search.windows.net
  • Index name matches exactly (case-sensitive)
  • Search field matches your vector field name (e.g., contentVector)
  • Documents contain valid vector embeddings

​
Support

For additional help with the Azure AI Search integration, contact [email protected].