Submit a question — retrieve relevant documents only

Time	Status	User Agent
Retrieving recent requests…

Time

Status

User Agent

Retrieving recent requests…

Title
Submit a question — retrieve relevant documents only

Description
Send a natural-language search to the specified dataset.
The service retrieves and ranks the most relevant document snippets but does not generate an AI answer.
Typical uses:

Build your own answer logic while relying on AutoDriveDDF for retrieval.
Feed the snippets into a separate LLM or analytics pipeline.
Batch offline processing where you first collect context, then post-process.

The call returns quickly with a question_id.
Use GET /dataset/{dataset_id}/question/{question_id} to fetch the snippets.

HTTP Request

POST /dataset/{dataset_id}/question

Authentication

In your REST client (Postman/Insomnia), select Basic Auth and enter your Username and Password.

The client will automatically generate the Authorization: Basic … header for you. Do not add that header manually.

Request Headers

Header	Example	Required	Notes
Content-Type	application/json	✓	JSON payload
Accept	application/json	—	Ensures JSON response

Path Parameters

Location	Name	Type	Required	Description
Path	`dataset_id`	string	✓	UUID of the dataset you want to search, e.g. `c8004e22-87f7-441f-8302-80c934841196`

Request Body

Field	Type	Required	Description
question	string	✓	Natural-language query (max 1000 chars).
k	integer	—	Optional. Number of top snippets to keep (default server value, e.g. `5`).

Example JSON

{
  "question": "How do I configure the data pipeline?",
  "k": 5
}

Example Request (cURL)

curl -u admin:mypassword \
     -H "Content-Type: application/json" \
     -d '{"question":"How do I configure the data pipeline?"}' \
     https://api.autodriveddf.example/dataset/c8004e22-87f7-441f-8302-80c934841196/question

Success Response `200 OK`

{
  "dataset_id": "c8004e22-87f7-441f-8302-80c934841196",
  "question_id": "73a1f41a-0754-48cb-8b6d-4d9c25a6fc0b"
}

Field	Description
dataset_id	UUID of the dataset queried.
question_id	UUID for this question. Use it with GET /dataset/{dataset_id}/question/{question_id} to retrieve the snippets.

Error Responses

Code	Reason	When it happens	Example Body
400	Bad Request	`question` missing / empty, or malformed JSON	`{ "detail": "Field 'question' is required." }`
401	Unauthorized	Missing / wrong Basic Auth	—
404	Not Found	Dataset UUID does not exist	`{ "detail": "Dataset not found." }`
422	Unprocessable Entity	Dataset is still processing or failed (`status ≠ success`)	`{ "detail": "Dataset is not available for querying yet." }`
500	Server Error	Unexpected failure while registering the question	`{ "detail": "Unexpected error." }`

Next Steps

Wait briefly, then call GET /dataset/{dataset_id}/question/{question_id}.
The response will include question_text and an array relevant_documents.
Use those snippets however you like—display to users, feed into another model, etc.

This field can be used to filter documents using the metadata of the documents. Example: metadata_filter={"source": "file.txt"} In this scenario, before selecting the documents, the following filter would be routerlied to the dataset.

Distance Metric in Embedding Distances In the realm of embeddings, where data points are represented as vectors in a continuous space, a distance metric quantifies the similarity or dissimilarity between these vectors. It allows us to gauge how close or far apart two embeddings are, helping capture semantic or contextual relationships. Available metrics: - "L2": "Euclidean Distance" - "L1": "Nuclear distance" - "max": "L-infinity" - "cos": "Cosine" - "dot": "dot product"

Whether to use MMR (Maximal Marginal Relevance) in the selection of documents to retrieve. MMR is an algorithm commonly used in information retrieval and text summarization. Its primary goal is to balance relevance and diversity. When retrieving or summarizing documents, MMR ensures that the selected items are not only relevant to the query or topic but also diverse enough to provide comprehensive information. This prevents redundancy and offers a broader perspective on the topic.