RAG Search with Answer

RAG Search with Answer is the service that leverages the power of Retrieval-Augmented Generation (RAG) technology to enable intelligent searches within your documents. The service combines semantic search and natural language output generation, returning in real time a single relevant response based on a query. All of this is done reliably and securely, without any data leaks.

As mentioned, at the core is the RAG-as-a-Service by Openapi technology, which allows companies to query their proprietary data and obtain reliable, contextualized answers. The system reduces the risk of “hallucinations” typical of Large Language Models (LLMs), providing responses that are consistent and relevant to the organization’s specific knowledge.

Thanks to RAG-as-a-Service, you can easily integrate advanced RAG functionalities into your applications, without the complexity of dedicated infrastructures or data pipelines. Your data is automatically indexed, allowing the model to access up-to-date information in real time. In this way, Openapi combines the power of LLMs with contextual search on corporate data, providing precise answers based exclusively on your proprietary knowledge.

In addition to Search with Answer, Openapi also offers two other RAG services for document search: Search, which returns one or more relevant text excerpts, and Conversation, which allows contextualized conversations based on previous interactions. All three are valid globally.

To obtain coherent and relevant results with RAG Search with Answer, three main steps must be followed:

Indexing makes it possible to quickly retrieve the most relevant information in response to a query. Each time the RAG is modified (by uploading or removing documents), it is essential to restart the indexing to ensure updated and accurate answers.

Create a new RAG

The first step is to create an empty RAG through the endpoint POST /rag, where documents will later be added.

REQUEST EXAMPLE

The request must include:

{
  "name": "RAGTest",
  "options": {
    "ocr": false,
    "autoIndexingIntervalHours": 0
  },
  "callback": {
    "method": "POST",
    "field": "string",
    "url": "https://www.mysite.it/callback.php",
    "data": {}
  }
}

RESPONSE EXAMPLE

The response contains details of the RAG (e.g. ID and name, status, options, settings such as OCR, total and indexed documents, creation, update, and last indexing dates).

{
  "data": {
    "id": "68947e1e0dab7e743108abfb",
    "name": "RAGTest",
    "state": "ready",
    "options": {
      "ocr": false,
      "autoIndexingIntervalHours": 0
    },
    "totalDocuments": 0,
    "totalIndexedDocuments": 0,
    "sizeMegaByte": 0,
    "createdAt": "2025-09-04T10:45:42.036Z",
    "updatedAt": "2025-09-04T10:45:42.036Z",
    "indexedAt": "2025-09-04T10:45:42.036Z",
    "indexingRunAt": "2025-09-04T10:45:42.036Z",
    "callback": {
      "method": "POST",
      "field": "string",
      "url": "https://www.mysite.it/callback.php",
      "data": {}
    }
  },
  "success": true,
  "message": "",
  "error": null
}

At any time, you can retrieve the list of all RAGs or the details of a single RAG using the endpoints GET /rag and GET /rag/{id}.

Upload a document

Once the RAG has been created, you can proceed with adding a document through the endpoint POST /rag/{id}/documents.

REQUEST EXAMPLE

In the request, the ID of the RAG in which the document will be uploaded must be specified as a parameter.

The payload must include:

{
  "fileName": "documentTest",
  "fileContent": "string",
  "metadata": {
    "custom_key_str": "string",
    "custom_key_date": "2025-09-04T10:51:06.259Z",
    "custom_key_int": 0,
    "custom_key_geo_latitude": 0,
    "custom_key_geo_longitude": 0,
    "custom_key_bool": true
  }
}

RESPONSE EXAMPLE

The response provides details about the document, including ID, name, status, metadata, size, file type, and creation and update dates.

{
  "data": [
    {
      "id": "string",
      "name": "string",
      "state": "string",
      "metadata": {
        "custom_key_str": "string",
        "custom_key_date": "2025-09-04T10:51:06.260Z",
        "custom_key_int": 0,
        "custom_key_geo_latitude": 0,
        "custom_key_geo_longitude": 0,
        "custom_key_bool": true
      },
      "sizeMegaByte": 0,
      "mimeType": "string",
      "createdAt": "2025-09-04T10:51:06.260Z",
      "updatedAt": "2025-09-04T10:51:06.260Z",
      "paymentDueDate": "2025-09-04T10:51:06.260Z"
    }
  ],
  "success": true,
  "message": "",
  "error": null
}

At any time, you can retrieve the list of documents within a RAG through the endpoint GET /rag/{id}/documents.

Start indexing process

As mentioned above, to obtain contextual and accurate answers, it is essential to start indexing every time a modification is made to the RAG (when a document is uploaded or deleted). If this step is not performed, the system will continue to rely only on previous data and not on the updated ones.

Indexing can be started manually through PATCH/rag/{id}; alternatively, automatic indexing can be set to start every X hours (as defined by the user). The latter must be configured when creating the RAG, via the endpoint POST /rag. There are no additional costs for indexing, whether automatic or manual.

REQUEST EXAMPLE

In the request, the ID of the RAG for which the manual indexing process is started must be specified as a parameter.

The request payload must include the parameter startIndexing set to true to start the indexing process:

"startIndexing": true

RESPONSE EXAMPLE

The response returns details about the RAG name, status (e.g. ready, indexing), settings (e.g. OCR yes/no, automatic indexing yes/no), number of documents present and indexed, current RAG size in MB, and creation and update dates.

{
  "data": {
    "id": "68947e1e0dab7e743108abfb",
    "name": "RAGTest",
    "state": "indexing",
    "options": {
      "ocr": false,
      "autoIndexingIntervalHours": 0
    },
    "totalDocuments": 0,
    "totalIndexedDocuments": 0,
    "sizeMegaByte": 0,
    "createdAt": "2025-09-04T10:55:37.306Z",
    "updatedAt": "2025-09-04T10:55:37.306Z",
    "callback": {
      "method": "POST",
      "field": "string",
      "url": "https://www.mysite.it/callback.php",
      "data": {}
    }
  },
  "success": true,
  "message": "",
  "error": null
}

RAG SEARCH WITH ANSWER

After completing the three steps mentioned above, you can proceed to the actual search through the endpoint POST /rag/search-with-answer.

As specified at the beginning, RAG Search with Answer allows you — via API and in real time — to find the document or information you need within all your files, starting from a query, and to obtain contextual answers in natural language. All this in total security and with no risk of sensitive data leakage.

REQUEST EXAMPLE

The request must include:

{
  "ragId": "688b2ab3bccc6a603202f87c",
  "query": "che servizi ci sono?",
  "max_len": 5,
  "metadata_filter": "(custom_key_int<175 AND custom_key_bool = \"true\") OR (custom_key_int<125 AND custom_key_bool = \"false\")",
  "settings": {
    "prompt_style": "basic"
  }
}

RESPONSE EXAMPLE

RAG Search with Answer returns information on the documents most relevant to your query, including text excerpts that can help you quickly find the data you are looking for.

Specifically, the response payload provides:

{
  "data": [
    {
      "answer": "string",
      "search_result": [
        {
          "index": 0,
          "snippets": [
            "string"
          ],
          "id": "689c70313f292734010a7dda",
          "ragId": "689c6ed7b283ac0aa40c1555",
          "name": "documentTest",
          "state": "indexing",
          "metadata": {
            "custom_key_str": "string",
            "custom_key_date": "2025-09-25T10:34:00.005Z",
            "custom_key_int": 0,
            "custom_key_geo_latitude": 0,
            "custom_key_geo_longitude": 0,
            "custom_key_bool": true
          }
        }
      ]
    }
  ],
  "success": true,
  "message": "",
  "error": null
}

With RAG Search with Answer, you can quickly query your documents, obtaining precise and reliable answers while accessing only the data that has been uploaded and indexed. This way, your information remains completely protected.

The service is ideal for companies that manage large volumes of documents (contracts, reports, manuals), such as:

In general, RAG Search with Answer supports all organizations or professionals who need to quickly access reliable information, optimizing time and accuracy in document management.