> ## Documentation Index
> Fetch the complete documentation index at: https://docs.hiperai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Zugverzeichnis mit Dokumenten

> Train an index by uploading documents (files) or providing text inputs.
Supports multiple file formats: TXT, PDF, DOCX, DOC, JSON, CSV, XLS, XLSX.
Files can be uploaded as multipart/form-data or text can be provided as JSON.


# Index mit Dokumenten trainieren

Trainieren Sie einen Index, indem Sie Dokumente (Dateien) hochladen oder Texteingaben bereitstellen.

## Endpunkt

```
POST /indexes/{indexName}/train
```

## Beschreibung

Trainieren Sie einen Index, indem Sie Dokumente (Dateien) hochladen oder Texteingaben bereitstellen. Dieser Endpunkt unterstützt mehrere Dateiformate und kann bis zu 20 Dateien gleichzeitig verarbeiten.

### Unterstützte Dateiformate

* TXT
* PDF
* DOCX
* DOC
* JSON
* CSV
* XLS
* XLSX

## Authentifizierung

Erforderlich: API-Schlüssel

```bash theme={null}
Authorization: Bearer sk-your-api-key-here
```

## Pfadparameter

| Parameter   | Geben Sie    | ein Erforderlich | Beschreibung                    |
| ----------- | ------------ | ---------------- | ------------------------------- |
| `indexName` | Zeichenfolge | Ja               | Name des zu trainierenden Index |

## Anforderungstext

Dieser Endpunkt akzeptiert das Format `multipart/form-data`.

### Parameter

| Parameter     | Geben Sie         | ein Erforderlich | Beschreibung                                                                                       |
| ------------- | ----------------- | ---------------- | -------------------------------------------------------------------------------------------------- |
| `files`       | Array von binären | Nein             | Dokumentdateien zum Hochladen (bis zu 20 Dateien, jeweils 50 MB)                                   |
| `text_inputs` | Zeichenfolge      | Nein             | JSON-String-Array mit Texteingaben. Jedes Element sollte Folgendes haben: Name, Typ, Inhalt, Größe |

### Texteingabeformat

Stellen Sie bei Verwendung von `text_inputs` ein JSON-String-Array mit Objekten bereit, die Folgendes enthalten:

```json theme={null}
[
  {
    "name": "doc1.txt",
    "type": "text/plain",
    "content": "Document content here",
    "size": 20
  }
]
```

## Beispiele anfordern

### Dateien hochladen (mehrteilige Formulardaten)

```bash theme={null}
curl -X POST "https://{customer.name}.hiperai.ai/api/external/indexes/my-knowledge-base/train" \
  -H "Authorization: Bearer sk-your-api-key-here" \
  -F "files=@document1.pdf" \
  -F "files=@document2.docx" \
  -F "files=@document3.txt"
```

### JavaScript/Node.js

```javascript theme={null}
const formData = new FormData();
formData.append('files', fileInput1.files[0]);
formData.append('files', fileInput2.files[0]);
formData.append('files', fileInput3.files[0]);

const response = await fetch('https://{customer.name}.hiperai.ai/api/external/indexes/my-knowledge-base/train', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-your-api-key-here'
  },
  body: formData
});

const data = await response.json();
console.log('Files processed:', data.results.files_processed);
console.log('Documents indexed:', data.results.documents_indexed);
```

### Python

```python theme={null}
import requests

url = "https://{customer.name}.hiperai.ai/api/external/indexes/my-knowledge-base/train"
headers = {
    "Authorization": "Bearer sk-your-api-key-here"
}

files = [
    ('files', open('document1.pdf', 'rb')),
    ('files', open('document2.docx', 'rb')),
    ('files', open('document3.txt', 'rb'))
]

response = requests.post(url, headers=headers, files=files)
result = response.json()
print('Files processed:', result['results']['files_processed'])
print('Documents indexed:', result['results']['documents_indexed'])
```

### Verwenden von Texteingaben

```bash theme={null}
curl -X POST "https://{customer.name}.hiperai.ai/api/external/indexes/my-knowledge-base/train" \
  -H "Authorization: Bearer sk-your-api-key-here" \
  -F 'text_inputs=[{"name":"doc1.txt","type":"text/plain","content":"Document content here","size":20}]'
```

## Antwort

### Erfolgsantwort (200)

```json theme={null}
{
  "success": true,
  "message": "Index trained successfully",
  "request_id": "550e8400-e29b-41d4-a716-446655440000",
  "results": {
    "files_processed": 3,
    "documents_extracted": 3,
    "documents_indexed": 3,
    "total_vectors": 11,
    "total_chunks": 3,
    "index_name": "my-knowledge-base",
    "namespace": "user-60a7c8f5e8b4f5001f7a8c24-index-my-knowledge-base"
  }
}
```

### Antwortfelder

| Feld         | Geben Sie       | ein Beschreibung                      |
| ------------ | --------------- | ------------------------------------- |
| `success`    | boolescher Wert | Bei erfolgreichen Anfragen immer wahr |
| `message`    | Zeichenfolge    | Erfolgsmeldung                        |
| `request_id` | Zeichenfolge    | ID zur Nachverfolgung anfordern       |
| `results`    | Objekt          | Trainingsergebnisse                   |

### Ergebnisobjekt

| Feld                  | Geben Sie    | ein Beschreibung                              |                        |
| --------------------- | ------------ | --------------------------------------------- | ---------------------- |
| `files_processed`     | Ganzzahl     | Anzahl der verarbeiteten Dateien              |                        |
| `documents_extracted` | Ganzzahl     | Anzahl der aus Dateien extrahierten Dokumente |                        |
| `documents_indexed`   | Ganzzahl     | Anzahl der erfolgreich indexierten Dokumente  |                        |
| `total_vectors`       | Ganzzahl     | Gesamtzahl der in Pinecone                    | gespeicherten Vektoren |
| `total_chunks`        | Ganzzahl     | Gesamtzahl der erstellten Textblöcke          |                        |
| `index_name`          | Zeichenfolge | Name des trainierten Index                    |                        |
| `namespace`           | Zeichenfolge | Namensraum des Index                          |                        |

## Fehlerantworten

### 400 Ungültige Anfrage

```json theme={null}
{
  "success": false,
  "error": "Invalid request",
  "message": "Missing files or text_inputs"
}
```

### 401 Nicht autorisiert

```json theme={null}
{
  "success": false,
  "error": "Invalid API key",
  "message": "The provided API key is invalid or has been revoked"
}
```

### 403 Verboten

```json theme={null}
{
  "success": false,
  "error": "Access denied",
  "message": "User doesn't have access to this index"
}
```

### 404 Nicht gefunden

```json theme={null}
{
  "success": false,
  "error": "Index not found",
  "message": "The specified index does not exist"
}
```

### 413 Nutzlast zu groß

```json theme={null}
{
  "success": false,
  "error": "File too large",
  "message": "Maximum file size is 50MB per file"
}
```

### 500 Interner Serverfehler

```json theme={null}
{
  "success": false,
  "error": "Index training failed",
  "message": "Vector database unavailable or training failed"
}
```

## Notizen

* Maximal 20 Dateien pro Anfrage
* Maximal 50 MB pro Datei
* Dateien können als Multipart-/Formulardaten hochgeladen werden
  – Texteingaben können als JSON-String-Array bereitgestellt werden
* Dokumente werden für die semantische Suche automatisch in Chunks aufgeteilt und vektorisiert
* Der Index muss vor dem Training vorhanden sein
* Trainingsergebnisse zeigen, wie viele Dokumente erfolgreich indiziert wurden


## OpenAPI

````yaml POST /indexes/{indexName}/train
openapi: 3.0.3
info:
  title: SecureAI External API
  description: >
    SecureAI External API provides AI chat completion and image generation
    capabilities with knowledge base retrieval, 

    security policies, and comprehensive usage tracking. This API is designed
    for external developers 

    and integrations using API key authentication.


    ## Key Features

    - **RAG (Retrieval-Augmented Generation)**: Automatically search knowledge
    bases for relevant context

    - **Multi-Model Support**: OpenAI, Anthropic, Google, Meta, and other AI
    models

    - **Model Redundancy & Failover**: Caller-defined failover chains (primary +
    fallbacks) with per-attempt timeouts

    - **OpenAI-Compatible Endpoint**: Point any OpenAI SDK at `/api/external/v1`
    — no code changes

    - **Image Generation**: Generate and edit images using Google Gemini 2.5
    Flash Image

    - **Speech-to-Speech (S2S)**: Real-time voice conversations using OpenAI
    Realtime API with WebRTC

    - **Security Policies**: SMLTP policy enforcement, per-call Prompt Shield,
    and signed compliance receipts

    - **Usage Tracking**: Comprehensive usage monitoring, self-service quota,
    and rate limiting

    - **Knowledge Base Integration**: Access to personal and shared knowledge
    bases

    - **User Management**: Complete user, group, and role management
    capabilities

    - **Audit Logging**: Comprehensive activity and security audit logs


    ## Authentication

    All endpoints (except health check) require API key authentication using
    Bearer token:

    ```

    Authorization: Bearer sk-your-api-key-here

    ```


    ## Billing and Usage

    By default, API requests are billed to the user account that owns the API
    key. You can specify 

    a different user to bill by including the `user_id` parameter in your
    request. This allows for:

    - Multi-tenant applications with per-user billing

    - Flexible completion limit management

    - Per-user "Usage by Model" settings


    ## Rate Limits

    - Default: 60 requests per minute, 1000 requests per hour

    - Daily limits: 100 requests (configurable)

    - Monthly limits: 10,000 requests (configurable)


    ## Base URL

    ```

    https://secureai.hiperai.ai/api/external

    ```
  version: 1.1.0
  contact:
    name: SecureAI Support
    email: support@secureai.hiperai.ai
  license:
    name: Proprietary
    url: https://secureai.hiperai.ai/terms
servers:
  - url: https://secureai.hiperai.ai/api/external
    description: Production server
  - url: http://localhost:3010/api/external
    description: Development server
security:
  - ApiKeyAuth: []
tags:
  - name: System
    description: System health and status endpoints
  - name: Discovery
    description: Endpoints to discover available models, indexes, and policies
  - name: Chat
    description: AI chat completion endpoints
  - name: User Management
    description: Endpoints for managing user accounts and roles
  - name: Index Management
    description: Endpoints for managing knowledge base indexes
  - name: Group Management
    description: Endpoints for managing user groups
  - name: SMLTP Security
    description: Endpoints for managing SMLTP security policies and audit logs
  - name: Role Management
    description: Endpoints for managing user roles
  - name: Activity Logs
    description: Endpoints for retrieving activity logs
externalDocs:
  description: SecureAI Documentation
  url: https://secureai.hiperai.ai/docs
paths:
  /indexes/{indexName}/train:
    post:
      tags:
        - Index Management
      summary: Train Index with Documents
      description: >
        Train an index by uploading documents (files) or providing text inputs.

        Supports multiple file formats: TXT, PDF, DOCX, DOC, JSON, CSV, XLS,
        XLSX.

        Files can be uploaded as multipart/form-data or text can be provided as
        JSON.
      parameters:
        - name: indexName
          in: path
          required: true
          description: Name of the index to train
          schema:
            type: string
            example: my-knowledge-base
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                files:
                  type: array
                  items:
                    type: string
                    format: binary
                  description: |
                    Document files to upload (up to 20 files, 50MB each).
                    Supported formats: TXT, PDF, DOCX, DOC, JSON, CSV, XLS, XLSX
                  maxItems: 20
                text_inputs:
                  type: string
                  description: |
                    JSON string array of text inputs. Each item should have:
                    - name: string (filename)
                    - type: string (MIME type, e.g., "text/plain")
                    - content: string (text content)
                    - size: number (content length in bytes)
                  example: >-
                    [{"name":"doc1.txt","type":"text/plain","content":"Document
                    content here","size":20}]
      responses:
        '200':
          description: Index trained successfully
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                    example: true
                  message:
                    type: string
                    example: Index trained successfully
                  request_id:
                    type: string
                    format: uuid
                    example: 550e8400-e29b-41d4-a716-446655440000
                  results:
                    type: object
                    properties:
                      files_processed:
                        type: integer
                        description: Number of files processed
                        example: 3
                      documents_extracted:
                        type: integer
                        description: Number of documents extracted from files
                        example: 3
                      documents_indexed:
                        type: integer
                        description: Number of documents successfully indexed
                        example: 3
                      total_vectors:
                        type: integer
                        description: Total number of vectors stored in Pinecone
                        example: 11
                      total_chunks:
                        type: integer
                        description: Total number of text chunks created
                        example: 3
                      index_name:
                        type: string
                        example: my-knowledge-base
                      namespace:
                        type: string
                        example: user-60a7c8f5e8b4f5001f7a8c24-index-my-knowledge-base
        '400':
          description: Invalid request (missing files/text_inputs or invalid format)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Invalid API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Access denied - user doesn't have access to this index
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Index not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '413':
          description: File too large (max 50MB per file)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Index training failed or vector database unavailable
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      security:
        - ApiKeyAuth: []
components:
  schemas:
    ErrorResponse:
      type: object
      properties:
        success:
          type: boolean
          example: false
        error:
          type: string
          example: Invalid API key
        message:
          type: string
          example: The provided API key is invalid or has been revoked
        request_id:
          type: string
          example: req-abc123
          description: Request ID for tracking (if available)
  securitySchemes:
    ApiKeyAuth:
      type: http
      scheme: bearer
      description: |
        API key authentication using Bearer token format.
        Example: `Authorization: Bearer sk-your-api-key-here`

````