DataBrain - RAG AI Solutions

Overview

DataBrain provides a RESTful API that allows developers to harness the power of Retrieval-Augmented Generation (RAG) technology. With our API, you can upload documents, create knowledge bases, and generate highly accurate, contextually relevant responses based on your data.

Our API is organized around REST principles. All requests should be made to the base URL https://api.databrain.ai/rag, using HTTPS, and will return JSON-encoded responses with standard HTTP response codes.

Document Management

Upload and manage your documents that will serve as sources for the RAG system.

Query Capabilities

Retrieve information from your documents using natural language queries.

Secure & Scalable

Enterprise-grade security with token-based authentication and scalable infrastructure.

Authentication

DataBrain API uses token-based authentication. You'll need to include your API token in the Authorization header for all requests.

Authorization Header

Authorization: Bearer YOUR_API_TOKEN

You can obtain your API token from the DataBrain Dashboard under API Settings. Keep your token secure and don't share it in publicly accessible areas such as GitHub or client-side code.

All API requests must be made over HTTPS. Calls made over plain HTTP will fail.

Document Management

DataBrain supports various document types including PDF, TXT, DOCX, MP3, and CSV files. Documents are processed and chunked automatically for optimal retrieval.

Upload Document

POST

Upload and process a document to be used as a knowledge source for RAG queries.

Endpoint

https://ai.goodbits.tech/api/rag/documents/upload

Parameters

Parameter	Type	Required	Description
document	File	Yes	The document file to upload (PDF, TXT, CSV, DOCX, MP3)

Response (201 Created)

{
    "message": "Document processed successfully",
    "document_id": "123e4567-e89b-12d3-a456-426614174000",
    "name": "example.pdf",
    "type": "pdf",
    "chunks": 15
}

List Documents

GET

Retrieve a list of all documents uploaded by the current user.

Endpoint

https://ai.goodbits.tech/api/rag/documents

Parameters

No parameters required.

Response (200 OK)

{
    "documents": [
        {
            "id": "123e4567-e89b-12d3-a456-426614174000",
            "name": "example1.pdf",
            "type": "pdf",
            "created_at": "2023-06-01T15:30:45Z"
        },
        {
            "id": "123e4567-e89b-12d3-a456-426614174001",
            "name": "example2.txt",
            "type": "txt",
            "created_at": "2023-06-02T10:15:30Z"
        }
    ]
}

Documents List API

Retrieve detailed information about your documents with advanced filtering, pagination, and statistics. This API provides comprehensive management capabilities for all documents in your account.

List All Documents

GET

Retrieve a paginated list of all documents with optional filtering and sorting capabilities.

Endpoint

https://ai.goodbits.tech/api/documents

Query Parameters

Parameter	Type	Required	Description
per_page	Integer	No	Number of items per page (default: 15, max: 100)
search	String	No	Search by document name
type	String	No	Filter by document type (pdf, txt, docx, csv, etc)
batch_id	UUID	No	Filter by batch ID
status	String	No	Filter by processing status (queued, processing, completed, failed)
sort_by	String	No	Field to sort by (created_at, name, type) - default: created_at
sort_order	String	No	Sort order (asc, desc) - default: desc

Example Request

				GET https://ai.goodbits.tech/api/documents?per_page=20&search=contract&type=pdf&sort_by=name&sort_order=asc
			

Response (200 OK)

{
    "success": true,
    "data": [
        {
            "id": "9c8e7f6d-5a4b-3c2d-1e0f-123456789abc",
            "name": "Contract 2024.pdf",
            "type": "pdf",
            "file_path": "documents/abc123.pdf",
            "batch_id": "9c8e7f6d-5a4b-3c2d-1e0f-987654321xyz",
            "batch_name": "Upload Batch 1",
            "batch_status": "completed",
            "processing_order": 1,
            "processing_status": "completed",
            "chunks_count": 25,
            "vector_ids_count": 25,
            "size": 2048576,
            "mime_type": "application/pdf",
            "created_at": "2025-10-09 10:30:00",
            "updated_at": "2025-10-09 10:35:00",
            "deleted_at": null
        },
        {
            "id": "9c8e7f6d-5a4b-3c2d-1e0f-123456789def",
            "name": "Contract Amendment.pdf",
            "type": "pdf",
            "file_path": "documents/def456.pdf",
            "batch_id": "9c8e7f6d-5a4b-3c2d-1e0f-987654321xyz",
            "batch_name": "Upload Batch 1",
            "batch_status": "completed",
            "processing_order": 2,
            "processing_status": "completed",
            "chunks_count": 12,
            "vector_ids_count": 12,
            "size": 1024000,
            "mime_type": "application/pdf",
            "created_at": "2025-10-09 10:32:00",
            "updated_at": "2025-10-09 10:37:00",
            "deleted_at": null
        }
    ],
    "pagination": {
        "total": 150,
        "per_page": 20,
        "current_page": 1,
        "last_page": 8,
        "from": 1,
        "to": 20
    }
}

Get Document Details

GET

Retrieve complete details about a specific document including content, metadata, batch information, and vector IDs.

Endpoint

https://ai.goodbits.tech/api/documents/{document_id}

Path Parameters

Parameter	Type	Required	Description
document_id	UUID	Yes	The unique identifier of the document

Response (200 OK)

{
    "success": true,
    "data": {
        "id": "9c8e7f6d-5a4b-3c2d-1e0f-123456789abc",
        "name": "Contract 2024.pdf",
        "type": "pdf",
        "file_path": "documents/abc123.pdf",
        "content": "Full extracted text content from the document...",
        "batch_id": "9c8e7f6d-5a4b-3c2d-1e0f-987654321xyz",
        "batch": {
            "id": "9c8e7f6d-5a4b-3c2d-1e0f-987654321xyz",
            "name": "Upload Batch 1",
            "status": "completed",
            "total_documents": 10,
            "processed_documents": 10,
            "progress": 100
        },
        "processing_order": 1,
        "vector_ids": [
            "vec_9c8e7f6d5a4b3c2d1e0f123456789001",
            "vec_9c8e7f6d5a4b3c2d1e0f123456789002",
            "vec_9c8e7f6d5a4b3c2d1e0f123456789003"
        ],
        "vector_ids_count": 25,
        "metadata": {
            "size": 2048576,
            "mime_type": "application/pdf",
            "processing_status": "completed",
            "chunks_count": 25,
            "processing_started": "2025-10-09 10:30:00",
            "processing_completed": "2025-10-09 10:35:00",
            "original_name": "Contract 2024.pdf"
        },
        "created_at": "2025-10-09 10:30:00",
        "updated_at": "2025-10-09 10:35:00",
        "deleted_at": null
    }
}

Error Response (404 Not Found)

{
    "success": false,
    "message": "Document not found or access denied",
    "error": "No query results for model [App\\Models\\Document]."
}

Documents Statistics

GET

Get comprehensive statistics about your documents including totals, distribution by type and status, and recent activity.

Endpoint

https://ai.goodbits.tech/api/documents/statistics/overview

Response (200 OK)

{
    "success": true,
    "data": {
        "total_documents": 150,
        "total_chunks": 3750,
        "documents_by_type": {
            "pdf": 80,
            "txt": 30,
            "docx": 25,
            "csv": 10,
            "xlsx": 5
        },
        "documents_by_status": {
            "completed": 140,
            "processing": 5,
            "failed": 3,
            "queued": 2
        },
        "total_batches": 15,
        "recent_uploads": 8
    }
}

Statistics Fields

Field	Type	Description
total_documents	Integer	Total number of documents in your account
total_chunks	Integer	Total number of vector chunks across all documents
documents_by_type	Object	Document count grouped by file type
documents_by_status	Object	Document count grouped by processing status
total_batches	Integer	Total number of upload batches
recent_uploads	Integer	Number of documents uploaded in the last 7 days

List Batches

GET

Retrieve a paginated list of all document batches with their processing status and progress information.

Endpoint

https://ai.goodbits.tech/api/documents/batches/list

Query Parameters

Parameter	Type	Required	Description
per_page	Integer	No	Number of items per page (default: 15, max: 100)

Response (200 OK)

{
    "success": true,
    "data": [
        {
            "id": "9c8e7f6d-5a4b-3c2d-1e0f-987654321xyz",
            "name": "Upload Batch 1",
            "status": "completed",
            "total_documents": 10,
            "processed_documents": 10,
            "failed_documents": 0,
            "progress_percentage": 100,
            "documents_count": 10,
            "metadata": {
                "uploaded_by": "user@email.com",
                "source": "web_interface",
                "description": "Monthly reports upload"
            },
            "created_at": "2025-10-09 10:00:00",
            "updated_at": "2025-10-09 10:45:00"
        },
        {
            "id": "9c8e7f6d-5a4b-3c2d-1e0f-987654321abc",
            "name": "API Upload - 2025-10-08",
            "status": "processing",
            "total_documents": 25,
            "processed_documents": 18,
            "failed_documents": 1,
            "progress_percentage": 72,
            "documents_count": 25,
            "metadata": {
                "uploaded_by": "api_user",
                "source": "api",
                "description": "Automated daily sync"
            },
            "created_at": "2025-10-08 15:30:00",
            "updated_at": "2025-10-08 16:15:00"
        }
    ],
    "pagination": {
        "total": 15,
        "per_page": 15,
        "current_page": 1,
        "last_page": 1
    }
}

Batch Status Values

Status	Description
pending	Batch created but processing has not started
processing	Batch is currently being processed
completed	All documents in batch have been processed successfully
failed	Batch processing failed
partial	Some documents processed successfully, some failed

List Batch Documents

GET

Retrieve all documents that belong to a specific batch, ordered by their processing sequence.

Endpoint

https://ai.goodbits.tech/api/documents/batches/{batch_id}/documents

Path Parameters

Parameter	Type	Required	Description
batch_id	UUID	Yes	The unique identifier of the batch

Query Parameters

Parameter	Type	Required	Description
per_page	Integer	No	Number of items per page (default: 15, max: 100)

Response (200 OK)

{
    "success": true,
    "batch": {
        "id": "9c8e7f6d-5a4b-3c2d-1e0f-987654321xyz",
        "name": "Upload Batch 1",
        "status": "completed",
        "progress_percentage": 100
    },
    "documents": [
        {
            "id": "9c8e7f6d-5a4b-3c2d-1e0f-123456789abc",
            "name": "Contract 2024.pdf",
            "type": "pdf",
            "processing_order": 1,
            "processing_status": "completed",
            "chunks_count": 25,
            "vector_ids_count": 25,
            "created_at": "2025-10-09 10:30:00"
        },
        {
            "id": "9c8e7f6d-5a4b-3c2d-1e0f-123456789def",
            "name": "Invoice Q3.pdf",
            "type": "pdf",
            "processing_order": 2,
            "processing_status": "completed",
            "chunks_count": 18,
            "vector_ids_count": 18,
            "created_at": "2025-10-09 10:32:00"
        },
        {
            "id": "9c8e7f6d-5a4b-3c2d-1e0f-123456789ghi",
            "name": "Meeting Notes.txt",
            "type": "txt",
            "processing_order": 3,
            "processing_status": "completed",
            "chunks_count": 8,
            "vector_ids_count": 8,
            "created_at": "2025-10-09 10:33:00"
        }
    ],
    "pagination": {
        "total": 10,
        "per_page": 15,
        "current_page": 1,
        "last_page": 1
    }
}

Error Response (404 Not Found)

{
    "success": false,
    "message": "Batch not found or access denied",
    "error": "No query results for model [App\\Models\\DocumentBatch]."
}

Queries

The heart of DataBrain's RAG system is the ability to query your documents using natural language and receive accurate, context-aware responses.

Query RAG

POST

Perform a RAG query against all documents in your knowledge base.

Endpoint

https://ai.goodbits.tech/api/rag/query

Request Body

Parameter	Type	Required	Description
query	String	Yes	The natural language query to process

Example Request

{
    "query": "What are the main points of the privacy policy document?"
}

Response (200 OK)

{
    "answer": "The main points of the privacy policy include: 1) Collection of personal data only with consent; 2) Use of data to improve services; 3) No sharing of data with third parties without authorization; 4) User's right to access and rectify data; 5) Secure storage with encryption.",
    "sources": [
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Privacy Policy.pdf",
            "relevance": 0.92,
            "content": "The privacy policy establishes that we collect personal data only with explicit user consent. We use this data exclusively to improve our services and user experience."
        },
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Privacy Policy.pdf",
            "relevance": 0.87,
            "content": "We are committed not to share personal data with third parties without express authorization. All users have the right to access, rectify and delete their data at any time."
        },
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Privacy Policy.pdf",
            "relevance": 0.81,
            "content": "All data is stored on secure servers with end-to-end encryption, ensuring maximum protection against leaks and unauthorized access."
        }
    ]
}

Filtered Query

POST

Perform a RAG query against specific documents in your knowledge base.

Endpoint

https://ai.goodbits.tech/api/rag/filtered-query

Request Body

Parameter	Type	Required	Description
query	String	Yes	The natural language query to process
document_ids	Array	Yes	Array of document IDs to query against

Example Request

{
    "query": "What are the main points of the privacy policy document?",
    "document_ids": ["123e4567-e89b-12d3-a456-426614174000", "123e4567-e89b-12d3-a456-426614174001"]
}

Response (200 OK)

{
    "answer": "The main points of the privacy policy include: 1) Collection of personal data only with consent; 2) Use of data to improve services; 3) No sharing of data with third parties without authorization; 4) User's right to access and rectify data; 5) Secure storage with encryption.",
    "sources": [
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Privacy Policy.pdf",
            "relevance": 0.92,
            "content": "The privacy policy establishes that we collect personal data only with explicit user consent. We use this data exclusively to improve our services and user experience."
        },
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Privacy Policy.pdf",
            "relevance": 0.87,
            "content": "We are committed not to share personal data with third parties without express authorization. All users have the right to access, rectify and delete their data at any time."
        },
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Privacy Policy.pdf",
            "relevance": 0.81,
            "content": "All data is stored on secure servers with end-to-end encryption, ensuring maximum protection against leaks and unauthorized access."
        }
    ]
}

Training

Train your RAG model with custom data to improve response accuracy and domain-specific knowledge.

Train Model

POST

Initiate a training session with your documents to enhance the RAG model's understanding of your specific domain.

Endpoint

https://ai.goodbits.tech/api/training

Request Body

Parameter	Type	Required	Description
document_ids	Array	Yes	Array of document IDs to use for training
training_mode	String	No	Training mode: "standard" or "intensive" (default: "standard")
epochs	Integer	No	Number of training epochs (default: 3, max: 10)

Example Request

{
    "document_ids": ["123e4567-e89b-12d3-a456-426614174000", "123e4567-e89b-12d3-a456-426614174001"],
    "training_mode": "intensive",
    "epochs": 5
}

Response (202 Accepted)

{
    "message": "Training session initiated successfully",
    "training_id": "train_789e4567-e89b-12d3-a456-426614174000",
    "status": "processing",
    "estimated_completion_time": "2023-06-15T16:45:30Z",
    "documents_count": 2,
    "mode": "intensive",
    "epochs": 5
}

Training Status

You can check the training status with a GET request:

GET https://ai.goodbits.tech/api/training/{training_id}/status

Status Response (200 OK)

{
    "training_id": "train_789e4567-e89b-12d3-a456-426614174000",
    "status": "completed",
    "progress": 100,
    "started_at": "2023-06-15T14:30:00Z",
    "completed_at": "2023-06-15T16:40:25Z",
    "accuracy_improvement": 15.3,
    "credits_used": 50
}

Credits

Monitor your API usage and available credits. Each API operation consumes credits based on complexity and resource usage.

Check Credits

GET

Retrieve your current credit balance and usage statistics.

Endpoint

https://ai.goodbits.tech/api/credits

Parameters

No parameters required.

Response (200 OK)

{
    "user_id": "user_123e4567-e89b-12d3-a456-426614174000",
    "credits": {
        "available": 8750,
        "total": 10000,
        "used": 1250
    },
    "usage_statistics": {
        "current_month": {
            "queries": 450,
            "documents_uploaded": 23,
            "training_sessions": 2,
            "credits_used": 625
        },
        "last_month": {
            "queries": 380,
            "documents_uploaded": 19,
            "training_sessions": 1,
            "credits_used": 475
        }
    },
    "subscription": {
        "plan": "Professional",
        "renewal_date": "2023-07-15T00:00:00Z",
        "monthly_credit_allowance": 10000
    },
    "credit_pricing": {
        "query": 1,
        "document_upload": 5,
        "training_standard": 25,
        "training_intensive": 50
    }
}

Credit Usage

Operation	Credits Cost	Notes
RAG Query	1 credit	Per query request
Document Upload	5 credits	Per document, regardless of size
Training (Standard)	25 credits	Per training session
Training (Intensive)	50 credits	Per training session

Code Examples

Here are some examples of how to use the DataBrain API in different programming languages.

Upload a Document

curl -X POST \
  https://ai.goodbits.tech/api/rag/documents/upload \
  -H 'Authorization: Bearer YOUR_API_TOKEN' \
  -H 'Accept: application/json' \
  -F 'document=@/path/to/your/document.pdf'

Query RAG

curl -X POST \
  https://ai.goodbits.tech/api/rag/query \
  -H 'Authorization: Bearer YOUR_API_TOKEN' \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json' \
  -d '{
    "query": "What are the main points of the privacy policy?"
}'

Train Model

curl -X POST \
  https://ai.goodbits.tech/api/training \
  -H 'Authorization: Bearer YOUR_API_TOKEN' \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json' \
  -d '{
    "document_ids": ["123e4567-e89b-12d3-a456-426614174000"],
    "training_mode": "standard",
    "epochs": 3
}'

Check Credits

curl -X GET \
  https://ai.goodbits.tech/api/credits \
  -H 'Authorization: Bearer YOUR_API_TOKEN' \
  -H 'Accept: application/json'

Upload a Document

<?php
$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://ai.goodbits.tech/api/rag/documents/upload",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => [
    'document' => new CURLFILE('/path/to/your/document.pdf')
  ],
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer YOUR_API_TOKEN",
    "Accept: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

Query RAG

<?php
$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://ai.goodbits.tech/api/rag/query",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'query' => 'What are the main points of the privacy policy?'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer YOUR_API_TOKEN",
    "Content-Type: application/json",
    "Accept: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

Train Model

<?php
$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://ai.goodbits.tech/api/training",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'document_ids' => ['123e4567-e89b-12d3-a456-426614174000'],
    'training_mode' => 'standard',
    'epochs' => 3
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer YOUR_API_TOKEN",
    "Content-Type: application/json",
    "Accept: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

Check Credits

<?php
$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://ai.goodbits.tech/api/credits",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer YOUR_API_TOKEN",
    "Accept: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

Upload a Document

import requests

url = "https://ai.goodbits.tech/api/rag/documents/upload"

headers = {
    'Authorization': 'Bearer YOUR_API_TOKEN',
    'Accept': 'application/json'
}

files = {
    'document': open('/path/to/your/document.pdf', 'rb')
}

response = requests.post(url, headers=headers, files=files)

print(response.json())

Query RAG

import requests
import json

url = "https://ai.goodbits.tech/api/rag/query"

headers = {
    'Authorization': 'Bearer YOUR_API_TOKEN',
    'Content-Type': 'application/json',
    'Accept': 'application/json'
}

payload = {
    'query': 'What are the main points of the privacy policy?'
}

response = requests.post(url, headers=headers, data=json.dumps(payload))

print(response.json())

Train Model

import requests
import json

url = "https://ai.goodbits.tech/api/training"

headers = {
    'Authorization': 'Bearer YOUR_API_TOKEN',
    'Content-Type': 'application/json',
    'Accept': 'application/json'
}

payload = {
    'document_ids': ['123e4567-e89b-12d3-a456-426614174000'],
    'training_mode': 'standard',
    'epochs': 3
}

response = requests.post(url, headers=headers, data=json.dumps(payload))

print(response.json())

Check Credits

import requests

url = "https://ai.goodbits.tech/api/credits"

headers = {
    'Authorization': 'Bearer YOUR_API_TOKEN',
    'Accept': 'application/json'
}

response = requests.get(url, headers=headers)

print(response.json())

Upload a Document

const fs = require('fs');
const axios = require('axios');
const FormData = require('form-data');

async function uploadDocument() {
  const formData = new FormData();
  formData.append('document', fs.createReadStream('/path/to/your/document.pdf'));

  try {
    const response = await axios.post('https://ai.goodbits.tech/api/rag/documents/upload', formData, {
      headers: {
        ...formData.getHeaders(),
        'Authorization': 'Bearer YOUR_API_TOKEN',
        'Accept': 'application/json'
      }
    });
    
    console.log(response.data);
  } catch (error) {
    console.error(error);
  }
}

uploadDocument();

Query RAG

const axios = require('axios');

async function queryRag() {
  try {
    const response = await axios.post('https://ai.goodbits.tech/api/rag/query', {
      query: 'What are the main points of the privacy policy?'
    }, {
      headers: {
        'Authorization': 'Bearer YOUR_API_TOKEN',
        'Content-Type': 'application/json',
        'Accept': 'application/json'
      }
    });
    
    console.log(response.data);
  } catch (error) {
    console.error(error);
  }
}

queryRag();

Train Model

const axios = require('axios');

async function trainModel() {
  try {
    const response = await axios.post('https://ai.goodbits.tech/api/training', {
      document_ids: ['123e4567-e89b-12d3-a456-426614174000'],
      training_mode: 'standard',
      epochs: 3
    }, {
      headers: {
        'Authorization': 'Bearer YOUR_API_TOKEN',
        'Content-Type': 'application/json',
        'Accept': 'application/json'
      }
    });
    
    console.log(response.data);
  } catch (error) {
    console.error(error);
  }
}

trainModel();

Check Credits

const axios = require('axios');

async function checkCredits() {
  try {
    const response = await axios.get('https://ai.goodbits.tech/api/credits', {
      headers: {
        'Authorization': 'Bearer YOUR_API_TOKEN',
        'Accept': 'application/json'
      }
    });
    
    console.log(response.data);
  } catch (error) {
    console.error(error);
  }
}

checkCredits();

API Documentation

Overview

Document Management

Query Capabilities

Secure & Scalable

Authentication

Authorization Header

Document Management

Upload Document

Endpoint

Parameters

Response (201 Created)

List Documents

Endpoint

Parameters

Response (200 OK)

Documents List API

List All Documents

Endpoint

Query Parameters

Example Request

Response (200 OK)

Get Document Details

Endpoint

Path Parameters

Response (200 OK)

Error Response (404 Not Found)

Documents Statistics

Endpoint

Response (200 OK)

Statistics Fields

List Batches

Endpoint

Query Parameters

Response (200 OK)

Batch Status Values

List Batch Documents

Endpoint

Path Parameters

Query Parameters

Response (200 OK)

Error Response (404 Not Found)

Queries

Query RAG

Endpoint

Request Body

Example Request

Response (200 OK)

Filtered Query

Endpoint

Request Body

Example Request

Response (200 OK)

Training

Train Model

Endpoint

Request Body

Example Request

Response (202 Accepted)

Training Status

Status Response (200 OK)

Credits

Check Credits

Endpoint

Parameters

Response (200 OK)

Credit Usage

Code Examples

Upload a Document

Query RAG

Train Model

Check Credits

Upload a Document

Query RAG

Train Model

Check Credits

Upload a Document

Query RAG

Train Model

Check Credits