Keyword Full-Text Search with Azure AI Search REST API | RAG Retrieval

RAG PIPELINE — KEYWORD SEARCH

Text Search (Keyword Search)

Run a BM25 full-text keyword search against your Azure AI Search index. The engine tokenizes the query and matches it against indexed document chunks, returning the top results ranked by keyword relevance. This is the simplest retrieval method and a good starting point in a RAG pipeline before adding semantic or vector search.

POST · Azure AI Search BM25 Full-Text Search Variables: azureAiSearch_ResourceName, azureAISearch_IndexName, azureAISearch_Key

Endpoint

POST https://{{azureAiSearch_ResourceName}}.search.windows.net/indexes/{{azureAISearch_IndexName}}/docs/search?api-version=2025-05-01-preview

Property	Value
Method	POST
Content-Type	application/json
Service	Azure AI Search (direct API call)
API Version	2025-05-01-preview

Postman Collection Variables Required

Set these variables in the Postman collection before calling this API azureAiSearch_ResourceName — Your Azure AI Search resource name
azureAISearch_IndexName — The name of your Azure AI Search index
azureAISearch_Key — Your Azure AI Search API key

Authentication

Azure AI Search API Key

Header: api-key{{azureAISearch_Key}}

Request Body

Field	Type	Required	Description
search	String	Required	The query text to search for. Keywords are matched against all indexed text fields.
select	String	Optional	Comma-separated list of fields to return. Example: `"section,content"`. Omit to return all fields.
top	Integer	Optional	Number of results to return. Default is 50. Use `3`–`5` for RAG context chunks.

Request Body (from Postman collection)

{
  "search" : "How do I configure Azure AI Search with OutSystems?",
  "select" : "section,content",
  "top"    : 3
}

Sample Request

cURL

curl -X POST \
  -H "api-key: <your-azure-search-key>" \
  -H "Content-Type: application/json" \
  -d '{"search":"How do I configure Azure AI Search?","select":"section,content","top":3}' \
  "https://<resource>.search.windows.net/indexes/<index>/docs/search?api-version=2025-05-01-preview"

Response — 200 OK

Sample Response

{
  "@odata.context" : "...",
  "value": [
    {
      "@search.score" : 4.2831,
      "section"       : "Configuring the Search Service",
      "content"       : "To configure Azure AI Search, navigate to your resource in the Azure portal..."
    },
    // more results...
  ]
}

Error Responses

200

OK — Search results returned. Empty value[] means no matches found.

401

Unauthorized — api-key header missing or invalid.

403

Forbidden — Key does not have read access to this index.

404

Not Found — Index does not exist in the specified Azure AI Search resource.

400

Bad Request — Malformed JSON or invalid field name in select.