Azure AI Search

Overview

AI-powered information retrieval platform by Microsoft Azure. Through Langdock’s integration, you can access and manage Azure AI Search directly from your conversations.

Authentication: API Key Category: AI & Search Availability: All workspace plans

---

Available Actions

Search Documents

azureaisearch.searchDocuments

Searches the database for the most relevant information based on the query provided

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)

---

List Datasets

azureaisearch.listDatasets

Lists all datasets in a BigQuery project

Requires Confirmation: No

Parameters:

• projectId (TEXT, Required): The Google Cloud project ID containing the datasets

Output:

• Returns an array of datasets with their IDs, names, and metadata

---

List Tables

azureaisearch.listTables

Lists all tables in a BigQuery dataset

Requires Confirmation: No

Parameters:

• projectId (TEXT, Required): The Google Cloud project ID

• datasetId (TEXT, Required): The dataset ID containing the tables

Output:

• Returns an array of tables with their IDs, names, and metadata

---

Get Table Schema

azureaisearch.getTableSchema

Gets the schema information for a specific BigQuery table

Requires Confirmation: No

Parameters:

• projectId (TEXT, Required): The Google Cloud project ID

• datasetId (TEXT, Required): The dataset ID containing the table

• tableId (TEXT, Required): The table ID to get schema information for

Output:

• Returns the table schema including field names, types, and constraints

---

Execute Query

azureaisearch.executeQuery

Executes a SQL query in BigQuery and returns the results

Requires Confirmation: No

Parameters:

• projectId (TEXT, Required): The Google Cloud project ID to execute the query in

• query (MULTI_LINE_TEXT, Required): The SQL query to execute in BigQuery

• useLegacySql (BOOLEAN, Optional): Whether to use legacy SQL syntax (default: false for Standard SQL)

Output:

• jobReference: Job reference information

• totalRows: Total number of rows in the result

• rows: Array of result rows containing field values

• schema: Schema of the result fields

• jobComplete: Whether the job completed successfully

---

Get Table Data

azureaisearch.getTableData

Retrieves actual data rows from a BigQuery table

Requires Confirmation: No

Parameters:

• projectId (TEXT, Required): The Google Cloud project ID

• datasetId (TEXT, Required): The dataset ID containing the table

• tableId (TEXT, Required): The table ID to retrieve data from

• maxResults (NUMBER, Optional): Maximum number of rows to return (optional)

Output:

• Returns table data with rows and schema information

---

Create Dataset

azureaisearch.createDataset

Creates a new dataset in BigQuery

Requires Confirmation: No

Parameters:

• projectId (TEXT, Required): The Google Cloud project ID

• datasetId (TEXT, Required): The ID for the new dataset

• description (TEXT, Optional): Optional description for the dataset

• location (TEXT, Optional): Geographic location for the dataset (e.g., US, EU)

Output:

• Returns the created dataset with its ID and metadata

---

Create Table

azureaisearch.createTable

Creates a new table in a BigQuery dataset

Requires Confirmation: No

Parameters:

• projectId (TEXT, Required): The Google Cloud project ID

• datasetId (TEXT, Required): The dataset ID to create the table in

• tableId (TEXT, Required): The ID for the new table

• description (TEXT, Optional): Optional description for the table

• schema (MULTI_LINE_TEXT, Optional): Table schema as JSON array of field objects (optional)

Output:

• Returns the created table with its ID and schema information

---

Insert Table Data

azureaisearch.insertTableData

Inserts data rows into a BigQuery table

Requires Confirmation: No

Parameters:

• projectId (TEXT, Required): The Google Cloud project ID

• datasetId (TEXT, Required): The dataset ID containing the table

• tableId (TEXT, Required): The table ID to insert data into

• rows (MULTI_LINE_TEXT, Required): JSON array of row objects to insert

• ignoreUnknownValues (BOOLEAN, Optional): Whether to ignore unknown values in the data

• skipInvalidRows (BOOLEAN, Optional): Whether to skip rows that contain invalid data

Output:

• Returns insertion results with success/failure information

---

Get Dataset Info

azureaisearch.getDatasetInfo

Gets detailed information about a BigQuery dataset

Requires Confirmation: No

Parameters:

• projectId (TEXT, Required): The Google Cloud project ID

• datasetId (TEXT, Required): The dataset ID to get information for

Output:

• Returns dataset information including creation time, location, and access controls

---

Common Use Cases

• Data Management — Manage and organize your Azure AI Search data

• Automation — Automate workflows with Azure AI Search

• Reporting — Generate insights and reports

• Integration — Connect Azure AI Search with other tools

---

Best Practices

1

Getting Started

• Enable the Azure AI Search integration in your workspace settings

• Authenticate using API Key

• 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 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 Azure AI Search integration, contact [email protected]

---