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

# Create Knowledge Base

Create a new knowledge base from collections and data sources with customizable chunking and embedding configurations.

## Request Body

<ParamField body="name" type="string" required>
  Knowledge base name
</ParamField>

<ParamField body="description" type="string">
  Optional description
</ParamField>

<ParamField body="processing_engine" type="string" required>
  Processing engine: `milvus`

  Currently only Milvus is supported as the processing engine.
</ParamField>

<ParamField body="selected_collections" type="array">
  Array of collection IDs to include. Data sources from these collections will be extracted automatically.

  Either `selected_collections` or `selected_datasources` (or both) must be provided.
</ParamField>

<ParamField body="selected_datasources" type="array">
  Array of individual data source IDs to include.

  Either `selected_collections` or `selected_datasources` (or both) must be provided.
</ParamField>

<ParamField body="chunking_strategy" type="object">
  Chunking configuration for text processing. See [Chunking Strategies](#chunking-strategies) for details.

  **Default:** Recursive strategy with 500 word chunks and 50 word overlap
</ParamField>

<ParamField body="embedding_config" type="object">
  Embedding model configuration. See [Embedding Configuration](#embedding-configuration) for details.

  **Required fields:**

  * `provider`: `"azure_openai"` | `"mistral"` | `"telekom_otc"`
  * `model`: Model name (e.g., `"text-embedding-ada-002"`, `"mistral-embed"`)
  * `dimensions`: Vector dimensions (e.g., `1536`, `1024`)
</ParamField>

<ParamField body="save_as_collection" type="boolean" default="false">
  Whether to save the selected data sources as a new collection
</ParamField>

<ParamField body="new_collection_name" type="string">
  Name for the new collection (required if `save_as_collection` is `true`)
</ParamField>

<ParamField body="new_collection_description" type="string">
  Description for the new collection (optional)
</ParamField>

## Chunking Strategies

Control how documents are split into searchable chunks:

<Frame>
  <img src="https://mintlify.s3.us-west-1.amazonaws.com/arttacsolutions/images/chunking_config.png" alt="Chunking Strategy Configuration" />
</Frame>

### Recursive (Default)

Splits text using multiple separators in order (paragraphs → sentences → words).

```json theme={null}
"chunking_strategy": {
  "strategy": "recursive",
  "chunk_size": 500,
  "chunk_overlap": 50,
  "split_by": "word",  // "word" or "char" only
  "recursive_separators": ["\n\n", "\n", ". ", " "]
}
```

### Hierarchical

Creates multi-level chunks preserving document structure.

```json theme={null}
"chunking_strategy": {
  "strategy": "hierarchical",
  "chunk_overlap": 50,
  "split_by": "word",  // "word" only
  "hierarchical_block_sizes": [700, 350, 150]
}
```

### Fixed

Simple fixed-size chunks with specified overlap.

```json theme={null}
"chunking_strategy": {
  "strategy": "fixed",
  "chunk_size": 500,
  "chunk_overlap": 50,
  "split_by": "word"  // "word" only
}
```

### Structured Data (CSV/Excel)

For `.csv`, `.xlsx`, `.xls` files, use separate configuration:

```json theme={null}
"chunking_strategy": {
  "document_config": {
    "strategy": "recursive",
    "chunk_size": 500,
    "chunk_overlap": 50,
    "split_by": "word"
  },
  "structured_config": {
    "rows_per_batch": 10,
    "table_format": "csv",
    "csv_content_column": "text",
    "csv_conversion_mode": "row"
  }
}
```

**Structured Config Fields:**

* `rows_per_batch`: Rows to combine per chunk (1-20)
* `table_format`: Output format (`"csv"` or `"markdown"`)
* `csv_content_column`: Column name for text content (CSV only)
* `csv_conversion_mode`: `"row"` (one doc per row) or `"file"` (one doc per file)

## Embedding Configuration

**Supported Providers:**

* **Azure OpenAI**: `text-embedding-ada-002` (1536 dimensions)
* **Mistral AI**: `mistral-embed` (1024 dimensions)
* **Telekom OTC**:
  * `text-embedding-bge-m3` (1024 dimensions)
  * `jina-embeddings-v2-base-de` (768 dimensions)
  * `jina-embeddings-v2-base-code` (768 dimensions)
  * `tsi-embedding-colqwen2-2b-v1` (1024 dimensions)

```json theme={null}
"embedding_config": {
  "provider": "mistral",
  "model": "mistral-embed",
  "dimensions": 1024
}
```

## Examples

### Basic Example

<CodeGroup>
  ```bash cURL theme={null}
  curl -X POST https://api.artaios.ai/api/v1/knowledge-bases/ \
    -H "x-api-key: YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "name": "Product Knowledge Base",
      "description": "Product documentation and guides",
      "processing_engine": "milvus",
      "selected_collections": ["coll_123", "coll_456"]
    }'
  ```

  ```python Python theme={null}
  import requests

  data = {
      "name": "Product Knowledge Base",
      "description": "Product documentation and guides",
      "processing_engine": "milvus",
      "selected_collections": ["coll_123", "coll_456"]
  }

  response = requests.post(
      "https://api.artaios.ai/api/v1/knowledge-bases/",
      headers={"x-api-key": "YOUR_API_KEY"},
      json=data
  )
  kb = response.json()
  ```

  ```javascript JavaScript theme={null}
  const data = {
    name: "Product Knowledge Base",
    description: "Product documentation and guides",
    processing_engine: "milvus",
    selected_collections: ["coll_123", "coll_456"]
  };

  const response = await fetch('https://api.artaios.ai/api/v1/knowledge-bases/', {
    method: 'POST',
    headers: {
      'x-api-key': 'YOUR_API_KEY',
      'Content-Type': 'application/json'
    },
    body: JSON.stringify(data)
  });

  const kb = await response.json();
  ```
</CodeGroup>

### Advanced Example with Custom Chunking

<CodeGroup>
  ```bash cURL theme={null}
  curl -X POST https://api.artaios.ai/api/v1/knowledge-bases/ \
    -H "x-api-key: YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "name": "Research Papers KB",
      "description": "Academic research with hierarchical chunking",
      "processing_engine": "milvus",
      "selected_datasources": ["ds_789", "ds_012"],
      "chunking_strategy": {
        "strategy": "hierarchical",
        "chunk_overlap": 70,
        "split_by": "word",
        "hierarchical_block_sizes": [700, 350, 150]
      },
      "embedding_config": {
        "provider": "azure_openai",
        "model": "text-embedding-3-small",
        "dimensions": 1536
      },
      "save_as_collection": true,
      "new_collection_name": "Research Collection"
    }'
  ```

  ```python Python theme={null}
  import requests

  data = {
      "name": "Research Papers KB",
      "description": "Academic research with hierarchical chunking",
      "processing_engine": "milvus",
      "selected_datasources": ["ds_789", "ds_012"],
      "chunking_strategy": {
          "strategy": "hierarchical",
          "chunk_overlap": 70,
          "split_by": "word",
          "hierarchical_block_sizes": [700, 350, 150]
      },
      "embedding_config": {
          "provider": "azure_openai",
          "model": "text-embedding-3-small",
          "dimensions": 1536
      },
      "save_as_collection": True,
      "new_collection_name": "Research Collection"
  }

  response = requests.post(
      "https://api.artaios.ai/api/v1/knowledge-bases/",
      headers={"x-api-key": "YOUR_API_KEY"},
      json=data
  )
  kb = response.json()
  ```
</CodeGroup>

## Response

```json theme={null}
{
  "success": true,
  "message": "Knowledge base 'Product Knowledge Base' created successfully",
  "knowledge_base": {
    "id": "kb_789",
    "name": "Product Knowledge Base",
    "description": "Product documentation and guides",
    "processing_engine": "milvus",
    "dataset_name": "",
    "normalized_dataset_name": "product_knowledge_base",
    "status": "pending",
    "progress": 0,
    "datasources": [],
    "datasource_count": 2,
    "total_datasources": 2,
    "ingested_datasources": [],
    "failed_datasources": [],
    "datasource_errors": {},
    "datasource_snapshots": {},
    "success_rate": 0,
    "chunking_strategy": {
      "strategy": "recursive",
      "chunk_size": 500,
      "chunk_overlap": 50,
      "split_by": "word",
      "recursive_separators": ["\n\n", "\n", ". ", " "]
    },
    "embedding_config": {
      "provider": "mistral",
      "model": "mistral-embed",
      "dimensions": 1024
    },
    "llm_config": {},
    "processing_metadata": {},
    "created_by_name": "John Doe",
    "company_name": "Acme Corp",
    "created_at": "2025-01-15T10:30:00Z",
    "updated_at": "2025-01-15T10:30:00Z"
  }
}
```