### GET /v1/clear/results

Source: https://www.jsonkeeper.com/b/S8XBK

API endpoint for GET /v1/clear/results

```markdown
### Parameters

- **older_then** (number, query, optional)

### Responses

#### 200 - Successful Response

**ClearResponse**
- **status** (string)

#### 422 - Validation Error

**HTTPValidationError**
- **detail** (array (string))
  Array items:
    - **loc** (array (string)) (required)
    - **msg** (string) (required)
    - **type** (string) (required)

### Example Usage

```bash
curl -X GET "https://api.example.com/v1/clear/results?older_then=3600"
```

```

--------------------------------

### Schema: KeyValueItem

Source: https://www.jsonkeeper.com/b/S8XBK

KeyValueItem.

```markdown
## Schema: KeyValueItem

KeyValueItem.

**Type:** object

- **self_ref** (string) (required)
- **parent** (object): RefItem.
  - **$ref** (string) (required)
- **children** (array (string))
  Array items:
- **content_layer** (string (body|furniture|background|invisible|notes)): ContentLayer. ("body"|"furniture"|"background"|"invisible"|"notes")
- **label** (string)
- **prov** (array (string))
  Array items:
    - **page_no** (integer) (required)
    - **bbox** (object) (required): BoundingBox.
      - **l** (number) (required)
      - **t** (number) (required)
      - **r** (number) (required)
      - **b** (number) (required)
      - **coord_origin** (string (TOPLEFT|BOTTOMLEFT)): CoordOrigin. ("TOPLEFT"|"BOTTOMLEFT")
    - **charspan** (array (string)) (required)
- **captions** (array (string))
  Array items:
- **references** (array (string))
  Array items:
- **footnotes** (array (string))
  Array items:
- **image** (object): ImageRef.
  - **mimetype** (string) (required)
  - **dpi** (integer) (required)
  - **size** (object) (required): Size.
    - **width** (number)
    - **height** (number)
  - **uri** (string (uri)) (required)
- **graph** (object) (required): GraphData.
  - **cells** (array (string))
    Array items:
      - **label** (string (unspecified|key|value|checkbox)) (required): GraphCellLabel. ("unspecified"|"key"|"value"|"checkbox")
      - **cell_id** (integer) (required)
      - **text** (string) (required)
      - **orig** (string) (required)
      - **prov** (object): ProvenanceItem.
      - **item_ref** (object): RefItem.
  - **links** (array (string))
    Array items:
      - **label** (string (unspecified|to_value|to_key|to_parent|to_child)) (required): GraphLinkLabel. ("unspecified"|"to_value"|"to_key"|"to_parent"|"to_child")
      - **source_cell_id** (integer) (required)
      - **target_cell_id** (integer) (required)

```

--------------------------------

### Schema: BoundingBox

Source: https://www.jsonkeeper.com/b/S8XBK

BoundingBox.

```markdown
## Schema: BoundingBox

BoundingBox.

**Type:** object

- **l** (number) (required)
- **t** (number) (required)
- **r** (number) (required)
- **b** (number) (required)
- **coord_origin** (string (TOPLEFT|BOTTOMLEFT)): CoordOrigin. ("TOPLEFT"|"BOTTOMLEFT")

```

--------------------------------

### GET /v1/clear/converters

Source: https://www.jsonkeeper.com/b/S8XBK

API endpoint for GET /v1/clear/converters

```markdown
### Responses

#### 200 - Successful Response

**ClearResponse**
- **status** (string)

### Example Usage

```bash
curl -X GET "https://api.example.com/v1/clear/converters"
```

```

--------------------------------

### GET /health

Source: https://www.jsonkeeper.com/b/S8XBK

API endpoint for GET /health

```markdown
### Responses

#### 200 - Successful Response

**HealthCheckResponse**
- **status** (string)

### Example Usage

```bash
curl -X GET "https://api.example.com/health"
```

```

--------------------------------

### Schema: Formatting

Source: https://www.jsonkeeper.com/b/S8XBK

Formatting.

```markdown
## Schema: Formatting

Formatting.

**Type:** object

- **bold** (boolean)
- **italic** (boolean)
- **underline** (boolean)
- **strikethrough** (boolean)
- **script** (string (baseline|sub|super)): Text script position. ("baseline"|"sub"|"super")

```

--------------------------------

### Schema: ProvenanceItem

Source: https://www.jsonkeeper.com/b/S8XBK

ProvenanceItem.

```markdown
## Schema: ProvenanceItem

ProvenanceItem.

**Type:** object

- **page_no** (integer) (required)
- **bbox** (object) (required): BoundingBox.
  - **l** (number) (required)
  - **t** (number) (required)
  - **r** (number) (required)
  - **b** (number) (required)
  - **coord_origin** (string (TOPLEFT|BOTTOMLEFT)): CoordOrigin. ("TOPLEFT"|"BOTTOMLEFT")
- **charspan** (array (string)) (required)

```

--------------------------------

### GET /openapi-3.0.json

Source: https://www.jsonkeeper.com/b/S8XBK

API endpoint for GET /openapi-3.0.json

```markdown
### Responses

#### 200 - Successful Response


### Example Usage

```bash
curl -X GET "https://api.example.com/openapi-3.0.json"
```

```

--------------------------------

### Schema: RefItem

Source: https://www.jsonkeeper.com/b/S8XBK

RefItem.

```markdown
## Schema: RefItem

RefItem.

**Type:** object

- **$ref** (string) (required)

```

--------------------------------

### GET /v1/result/{task_id}

Source: https://www.jsonkeeper.com/b/S8XBK

API endpoint for GET /v1/result/{task_id}

```markdown
### Parameters

- **task_id** (string, path, required)

### Responses

#### 200 - Successful Response

- **document** (object) (required)
  - **filename** (string) (required)
  - **md_content** (string)
  - **json_content** (object): DoclingDocument.
    - **schema_name** (string)
    - **version** (string)
    - **name** (string) (required)
    - **origin** (object): FileSource.
      - **mimetype** (string) (required)
      - **binary_hash** (integer) (required)
      - **filename** (string) (required)
      - **uri** (string (uri))
    - **furniture** (object): GroupItem.
      - **self_ref** (string) (required)
      - **parent** (object): RefItem.
        - **$ref** (string) (required)
      - **children** (array (string))
        Array items:
      - **content_layer** (string (body|furniture|background|invisible|notes)): ContentLayer. ("body"|"furniture"|"background"|"invisible"|"notes")
      - **name** (string)
      - **label** (string (unspecified|list|ordered_list|chapter|section|sheet|slide|form_area|key_value_area|comment_section|inline|picture_area)): GroupLabel. ("unspecified"|"list"|"ordered_list"|"chapter"|"section"|"sheet"|"slide"|"form_area"|"key_value_area"|"comment_section"|"inline"|"picture_area")
    - **body** (object): GroupItem.
    - **groups** (array (string))
      Array items:
        - **self_ref** (string) (required)
        - **parent** (object): RefItem.
        - **children** (array (string))
          Array items:
        - **content_layer** (string (body|furniture|background|invisible|notes)): ContentLayer. ("body"|"furniture"|"background"|"invisible"|"notes")
        - **name** (string)
        - **label** (string)
    - **texts** (array (string))
      Array items:
        - **self_ref** (string) (required)
        - **parent** (object): RefItem.
        - **children** (array (string))
          Array items:
        - **content_layer** (string (body|furniture|background|invisible|notes)): ContentLayer. ("body"|"furniture"|"background"|"invisible"|"notes")
        - **label** (string)
        - **prov** (array (string))
          Array items:
            - **page_no** (integer) (required)
            - **bbox** (object) (required): BoundingBox.
              - **l** (number) (required)
              - **t** (number) (required)
              - **r** (number) (required)
              - **b** (number) (required)
              - **coord_origin** (string (TOPLEFT|BOTTOMLEFT)): CoordOrigin. ("TOPLEFT"|"BOTTOMLEFT")
            - **charspan** (array (string)) (required)
        - **orig** (string) (required)
        - **text** (string) (required)
        - **formatting** (object): Formatting.
          - **bold** (boolean)
          - **italic** (boolean)
          - **underline** (boolean)
          - **strikethrough** (boolean)
          - **script** (string (baseline|sub|super)): Text script position. ("baseline"|"sub"|"super")
        - **hyperlink** (string (uri))
    - **pictures** (array (string))
      Array items:
        - **self_ref** (string) (required)
        - **parent** (object): RefItem.
        - **children** (array (string))
          Array items:
        - **content_layer** (string (body|furniture|background|invisible|notes)): ContentLayer. ("body"|"furniture"|"background"|"invisible"|"notes")
        - **label** (string (picture|chart)) ("picture"|"chart")
        - **prov** (array (string))
          Array items:
        - **captions** (array (string))
          Array items:
        - **references** (array (string))
          Array items:
        - **footnotes** (array (string))
          Array items:
        - **image** (object): ImageRef.
          - **mimetype** (string) (required)
          - **dpi** (integer) (required)
          - **size** (object) (required): Size.
            - **width** (number)
            - **height** (number)
          - **uri** (string (uri)) (required)
        - **annotations** (array (string))
          Array items:
            - **kind** (string) (required)
            - **text** (string) (required)
            - **provenance** (string) (required)
    - **tables** (array (string))
      Array items:
        - **self_ref** (string) (required)
        - **parent** (object): RefItem.
        - **children** (array (string))
          Array items:
        - **content_layer** (string (body|furniture|background|invisible|notes)): ContentLayer. ("body"|"furniture"|"background"|"invisible"|"notes")
        - **label** (string (document_index|table)) ("document_index"|"table")
        - **prov** (array (string))
          Array items:
        - **captions** (array (string))
          Array items:
        - **references** (array (string))
          Array items:
        - **footnotes** (array (string))
          Array items:
        - **image** (object): ImageRef.
        - **data** (object) (required): BaseTableData.
          - **table_cells** (array (string))
            Array items:
              - **bbox** (object): BoundingBox.
              - **row_span** (integer)
              - **col_span** (integer)
              - **start_row_offset_idx** (integer) (required)
              - **end_row_offset_idx** (integer) (required)
              - **start_col_offset_idx** (integer) (required)
              - **end_col_offset_idx** (integer) (required)
              - **text** (string) (required)
              - **column_header** (boolean)
              - **row_header** (boolean)
              - **row_section** (boolean)
              - **fillable** (boolean)
              - **ref** (object) (required): RefItem.
          - **num_rows** (integer)
          - **num_cols** (integer)
          - **grid** (array (array (string))) (required): grid.
        - **annotations** (array (string))
          Array items:
    - **key_value_items** (array (string))
      Array items:
        - **self_ref** (string) (required)
        - **parent** (object): RefItem.
        - **children** (array (string))
          Array items:
        - **content_layer** (string (body|furniture|background|invisible|notes)): ContentLayer. ("body"|"furniture"|"background"|"invisible"|"notes")
        - **label** (string)
        - **prov** (array (string))
          Array items:
        - **captions** (array (string))
          Array items:
        - **references** (array (string))
          Array items:
        - **footnotes** (array (string))
          Array items:
        - **image** (object): ImageRef.
        - **graph** (object) (required): GraphData.
          - **cells** (array (string))
            Array items:
              - **label** (string (unspecified|key|value|checkbox)) (required): GraphCellLabel. ("unspecified"|"key"|"value"|"checkbox")
              - **cell_id** (integer) (required)
              - **text** (string) (required)
              - **orig** (string) (required)
              - **prov** (object): ProvenanceItem.
              - **item_ref** (object): RefItem.
          - **links** (array (string))
            Array items:
              - **label** (string (unspecified|to_value|to_key|to_parent|to_child)) (required): GraphLinkLabel. ("unspecified"|"to_value"|"to_key"|"to_parent"|"to_child")
              - **source_cell_id** (integer) (required)
              - **target_cell_id** (integer) (required)
    - **form_items** (array (string))
      Array items:
        - **self_ref** (string) (required)
        - **parent** (object): RefItem.
        - **children** (array (string))
          Array items:
        - **content_layer** (string (body|furniture|background|invisible|notes)): ContentLayer. ("body"|"furniture"|"background"|"invisible"|"notes")
        - **label** (string)
        - **prov** (array (string))
          Array items:
        - **captions** (array (string))
          Array items:
        - **references** (array (string))
          Array items:
        - **footnotes** (array (string))
          Array items:
        - **image** (object): ImageRef.
        - **graph** (object) (required): GraphData.
    - **pages** (object)
  - **html_content** (string)
  - **text_content** (string)
  - **doctags_content** (string)
- **status** (string (pending|started|failure|success|partial_success|skipped)) (required) ("pending"|"started"|"failure"|"success"|"partial_success"|"skipped")
- **errors** (array (string))
  Array items:
    - **component_type** (string (document_backend|model|doc_assembler|user_input)) (required) ("document_backend"|"model"|"doc_assembler"|"user_input")
    - **module_name** (string) (required)
    - **error_message** (string) (required)
- **processing_time** (number) (required)
- **timings** (object)

#### 422 - Validation Error

**HTTPValidationError**
- **detail** (array (string))
  Array items:
    - **loc** (array (string)) (required)
    - **msg** (string) (required)
    - **type** (string) (required)

### Example Usage

```bash
curl -X GET "https://api.example.com/v1/result/{task_id}"
```

```

--------------------------------

### Schema: Size

Source: https://www.jsonkeeper.com/b/S8XBK

Size.

```markdown
## Schema: Size

Size.

**Type:** object

- **width** (number)
- **height** (number)

```

--------------------------------

### GET /v1/status/poll/{task_id}

Source: https://www.jsonkeeper.com/b/S8XBK

API endpoint for GET /v1/status/poll/{task_id}

```markdown
### Parameters

- **task_id** (string, path, required)
- **wait** (number, query, optional): Number of seconds to wait for a completed status.

### Responses

#### 200 - Successful Response

**TaskStatusResponse**
- **task_id** (string) (required)
- **task_type** (string (convert|chunk)) (required) ("convert"|"chunk")
- **task_status** (string) (required)
- **task_position** (integer)
- **task_meta** (object)
  - **num_docs** (integer) (required)
  - **num_processed** (integer)
  - **num_succeeded** (integer)
  - **num_failed** (integer)

#### 422 - Validation Error

**HTTPValidationError**
- **detail** (array (string))
  Array items:
    - **loc** (array (string)) (required)
    - **msg** (string) (required)
    - **type** (string) (required)

### Example Usage

```bash
curl -X GET "https://api.example.com/v1/status/poll/{task_id}?wait=0"
```

```

--------------------------------

### Schema: FormItem

Source: https://www.jsonkeeper.com/b/S8XBK

FormItem.

```markdown
## Schema: FormItem

FormItem.

**Type:** object

- **self_ref** (string) (required)
- **parent** (object): RefItem.
  - **$ref** (string) (required)
- **children** (array (string))
  Array items:
- **content_layer** (string (body|furniture|background|invisible|notes)): ContentLayer. ("body"|"furniture"|"background"|"invisible"|"notes")
- **label** (string)
- **prov** (array (string))
  Array items:
    - **page_no** (integer) (required)
    - **bbox** (object) (required): BoundingBox.
      - **l** (number) (required)
      - **t** (number) (required)
      - **r** (number) (required)
      - **b** (number) (required)
      - **coord_origin** (string (TOPLEFT|BOTTOMLEFT)): CoordOrigin. ("TOPLEFT"|"BOTTOMLEFT")
    - **charspan** (array (string)) (required)
- **captions** (array (string))
  Array items:
- **references** (array (string))
  Array items:
- **footnotes** (array (string))
  Array items:
- **image** (object): ImageRef.
  - **mimetype** (string) (required)
  - **dpi** (integer) (required)
  - **size** (object) (required): Size.
    - **width** (number)
    - **height** (number)
  - **uri** (string (uri)) (required)
- **graph** (object) (required): GraphData.
  - **cells** (array (string))
    Array items:
      - **label** (string (unspecified|key|value|checkbox)) (required): GraphCellLabel. ("unspecified"|"key"|"value"|"checkbox")
      - **cell_id** (integer) (required)
      - **text** (string) (required)
      - **orig** (string) (required)
      - **prov** (object): ProvenanceItem.
      - **item_ref** (object): RefItem.
  - **links** (array (string))
    Array items:
      - **label** (string (unspecified|to_value|to_key|to_parent|to_child)) (required): GraphLinkLabel. ("unspecified"|"to_value"|"to_key"|"to_parent"|"to_child")
      - **source_cell_id** (integer) (required)
      - **target_cell_id** (integer) (required)

```

--------------------------------

### POST /v1/convert/source/async

Source: https://www.jsonkeeper.com/b/S8XBK

API endpoint for POST /v1/convert/source/async

```markdown
### Request Body

**Content-Type:** application/json

- **options** (object)
  - **from_formats** (array (string)): Input format(s) to convert from. String or list of strings. Allowed values: docx, pptx, html, image, pdf, asciidoc, md, csv, xlsx, xml_uspto, xml_jats, mets_gbs, json_docling, audio. Optional, defaults to all formats.
  - **to_formats** (array (string)): Output format(s) to convert to. String or list of strings. Allowed values: md, json, html, html_split_page, text, doctags. Optional, defaults to Markdown.
  - **image_export_mode** (string (placeholder|embedded|referenced)): ImageRefMode. ("placeholder"|"embedded"|"referenced")
  - **do_ocr** (boolean): If enabled, the bitmap content will be processed using OCR. Boolean. Optional, defaults to true
  - **force_ocr** (boolean): If enabled, replace existing text with OCR-generated text over content. Boolean. Optional, defaults to false.
  - **ocr_engine** (string (easyocr|ocrmac|rapidocr|tesserocr|tesseract)) ("easyocr"|"ocrmac"|"rapidocr"|"tesserocr"|"tesseract")
  - **ocr_lang** (array (string))
  - **pdf_backend** (string (pypdfium2|dlparse_v1|dlparse_v2|dlparse_v4)): Enum of valid PDF backends. ("pypdfium2"|"dlparse_v1"|"dlparse_v2"|"dlparse_v4")
  - **table_mode** (string (fast|accurate)): Modes for the TableFormer model. ("fast"|"accurate")
  - **table_cell_matching** (boolean): If true, matches table cells predictions back to PDF cells. Can break table output if PDF cells are merged across table columns. If false, let table structure model define the text cells, ignore PDF cells.
  - **pipeline** (string (standard|vlm|asr)) ("standard"|"vlm"|"asr")
  - **page_range** (unknown): Only convert a range of pages. The page number starts at 1.
  - **document_timeout** (number): The timeout for processing each document, in seconds.
  - **abort_on_error** (boolean): Abort on error if enabled. Boolean. Optional, defaults to false.
  - **do_table_structure** (boolean): If enabled, the table structure will be extracted. Boolean. Optional, defaults to true.
  - **include_images** (boolean): If enabled, images will be extracted from the document. Boolean. Optional, defaults to true.
  - **images_scale** (number): Scale factor for images. Float. Optional, defaults to 2.0.
  - **md_page_break_placeholder** (string): Add this placeholder betweek pages in the markdown output.
  - **do_code_enrichment** (boolean): If enabled, perform OCR code enrichment. Boolean. Optional, defaults to false.
  - **do_formula_enrichment** (boolean): If enabled, perform formula OCR, return LaTeX code. Boolean. Optional, defaults to false.
  - **do_picture_classification** (boolean): If enabled, classify pictures in documents. Boolean. Optional, defaults to false.
  - **do_picture_description** (boolean): If enabled, describe pictures in documents. Boolean. Optional, defaults to false.
  - **picture_description_area_threshold** (number): Minimum percentage of the area for a picture to be processed with the models.
  - **picture_description_local** (object)
    - **repo_id** (string) (required): Repository id from the Hugging Face Hub.
    - **prompt** (string): Prompt used when calling the vision-language model.
    - **generation_config** (object): Config from https://huggingface.co/docs/transformers/en/main_classes/text_generation#transformers.GenerationConfig
  - **picture_description_api** (object)
    - **url** (string (uri)) (required): Endpoint which accepts openai-api compatible requests.
    - **headers** (object): Headers used for calling the API endpoint. For example, it could include authentication headers.
    - **params** (object): Model parameters.
    - **timeout** (number): Timeout for the API request.
    - **concurrency** (integer): Maximum number of concurrent requests to the API.
    - **prompt** (string): Prompt used when calling the vision-language model.
  - **vlm_pipeline_model** (string (smoldocling|smoldocling_vllm|granite_vision|granite_vision_vllm|granite_vision_ollama|got_ocr_2)) ("smoldocling"|"smoldocling_vllm"|"granite_vision"|"granite_vision_vllm"|"granite_vision_ollama"|"got_ocr_2")
  - **vlm_pipeline_model_local** (object)
    - **repo_id** (string) (required): Repository id from the Hugging Face Hub.
    - **prompt** (string): Prompt used when calling the vision-language model.
    - **scale** (number): Scale factor of the images used.
    - **response_format** (string (doctags|markdown|html|otsl|plaintext)) (required) ("doctags"|"markdown"|"html"|"otsl"|"plaintext")
    - **inference_framework** (string (mlx|transformers|vllm)) (required) ("mlx"|"transformers"|"vllm")
    - **transformers_model_type** (string (automodel|automodel-vision2seq|automodel-causallm|automodel-imagetexttotext)) ("automodel"|"automodel-vision2seq"|"automodel-causallm"|"automodel-imagetexttotext")
    - **extra_generation_config** (object): Config from https://huggingface.co/docs/transformers/en/main_classes/text_generation#transformers.GenerationConfig
  - **vlm_pipeline_model_api** (object)
    - **url** (string (uri)) (required): Endpoint which accepts openai-api compatible requests.
    - **headers** (object): Headers used for calling the API endpoint. For example, it could include authentication headers.
    - **params** (object): Model parameters.
    - **timeout** (number): Timeout for the API request.
    - **concurrency** (integer): Maximum number of concurrent requests to the API.
    - **prompt** (string): Prompt used when calling the vision-language model.
    - **scale** (number): Scale factor of the images used.
    - **response_format** (string (doctags|markdown|html|otsl|plaintext)) (required) ("doctags"|"markdown"|"html"|"otsl"|"plaintext")
- **sources** (array (string)) (required)
  Array items:
    - **base64_string** (string) (required): Content of the file serialized in base64. For example it can be obtained via `base64 -w 0 /path/to/file/pdf-to-convert.pdf`.
    - **filename** (string) (required): Filename of the uploaded document
    - **kind** (string) (required)
- **target** (object)
  - **kind** (string) (required)

### Responses

#### 200 - Successful Response

**TaskStatusResponse**
- **task_id** (string) (required)
- **task_type** (string (convert|chunk)) (required) ("convert"|"chunk")
- **task_status** (string) (required)
- **task_position** (integer)
- **task_meta** (object)
  - **num_docs** (integer) (required)
  - **num_processed** (integer)
  - **num_succeeded** (integer)
  - **num_failed** (integer)

#### 422 - Validation Error

**HTTPValidationError**
- **detail** (array (string))
  Array items:
    - **loc** (array (string)) (required)
    - **msg** (string) (required)
    - **type** (string) (required)

### Example Usage

```bash
curl -X POST "https://api.example.com/v1/convert/source/async" \
  -H "Content-Type: application/json" \
  -d '{
  "options": "[object Object]",
  "sources": [
    "string"
  ],
  "target": "[object Object]"
}'
```

```

--------------------------------

### Schema: TitleItem

Source: https://www.jsonkeeper.com/b/S8XBK

TitleItem.

```markdown
## Schema: TitleItem

TitleItem.

**Type:** object

- **self_ref** (string) (required)
- **parent** (object): RefItem.
  - **$ref** (string) (required)
- **children** (array (string))
  Array items:
- **content_layer** (string (body|furniture|background|invisible|notes)): ContentLayer. ("body"|"furniture"|"background"|"invisible"|"notes")
- **label** (string)
- **prov** (array (string))
  Array items:
    - **page_no** (integer) (required)
    - **bbox** (object) (required): BoundingBox.
      - **l** (number) (required)
      - **t** (number) (required)
      - **r** (number) (required)
      - **b** (number) (required)
      - **coord_origin** (string (TOPLEFT|BOTTOMLEFT)): CoordOrigin. ("TOPLEFT"|"BOTTOMLEFT")
    - **charspan** (array (string)) (required)
- **orig** (string) (required)
- **text** (string) (required)
- **formatting** (object): Formatting.
  - **bold** (boolean)
  - **italic** (boolean)
  - **underline** (boolean)
  - **strikethrough** (boolean)
  - **script** (string (baseline|sub|super)): Text script position. ("baseline"|"sub"|"super")
- **hyperlink** (string (uri))

```

--------------------------------

### Schema: CodeItem

Source: https://www.jsonkeeper.com/b/S8XBK

CodeItem.

```markdown
## Schema: CodeItem

CodeItem.

**Type:** object

- **self_ref** (string) (required)
- **parent** (object): RefItem.
  - **$ref** (string) (required)
- **children** (array (string))
  Array items:
- **content_layer** (string (body|furniture|background|invisible|notes)): ContentLayer. ("body"|"furniture"|"background"|"invisible"|"notes")
- **label** (string)
- **prov** (array (string))
  Array items:
    - **page_no** (integer) (required)
    - **bbox** (object) (required): BoundingBox.
      - **l** (number) (required)
      - **t** (number) (required)
      - **r** (number) (required)
      - **b** (number) (required)
      - **coord_origin** (string (TOPLEFT|BOTTOMLEFT)): CoordOrigin. ("TOPLEFT"|"BOTTOMLEFT")
    - **charspan** (array (string)) (required)
- **orig** (string) (required)
- **text** (string) (required)
- **formatting** (object): Formatting.
  - **bold** (boolean)
  - **italic** (boolean)
  - **underline** (boolean)
  - **strikethrough** (boolean)
  - **script** (string (baseline|sub|super)): Text script position. ("baseline"|"sub"|"super")
- **hyperlink** (string (uri))
- **captions** (array (string))
  Array items:
- **references** (array (string))
  Array items:
- **footnotes** (array (string))
  Array items:
- **image** (object): ImageRef.
  - **mimetype** (string) (required)
  - **dpi** (integer) (required)
  - **size** (object) (required): Size.
    - **width** (number)
    - **height** (number)
  - **uri** (string (uri)) (required)
- **code_language** (string (Ada|Awk|Bash|bc|C|C#|C++|CMake|COBOL|CSS|Ceylon|Clojure|Crystal|Cuda|Cython|D|Dart|dc|Dockerfile|Elixir|Erlang|FORTRAN|Forth|Go|HTML|Haskell|Haxe|Java|JavaScript|Julia|Kotlin|Lisp|Lua|Matlab|MoonScript|Nim|OCaml|ObjectiveC|Octave|PHP|Pascal|Perl|Prolog|Python|Racket|Ruby|Rust|SML|SQL|Scala|Scheme|Swift|TypeScript|unknown|VisualBasic|XML|YAML)): CodeLanguageLabel. ("Ada"|"Awk"|"Bash"|"bc"|"C"|"C#"|"C++"|"CMake"|"COBOL"|"CSS"|"Ceylon"|"Clojure"|"Crystal"|"Cuda"|"Cython"|"D"|"Dart"|"dc"|"Dockerfile"|"Elixir"|"Erlang"|"FORTRAN"|"Forth"|"Go"|"HTML"|"Haskell"|"Haxe"|"Java"|"JavaScript"|"Julia"|"Kotlin"|"Lisp"|"Lua"|"Matlab"|"MoonScript"|"Nim"|"OCaml"|"ObjectiveC"|"Octave"|"PHP"|"Pascal"|"Perl"|"Prolog"|"Python"|"Racket"|"Ruby"|"Rust"|"SML"|"SQL"|"Scala"|"Scheme"|"Swift"|"TypeScript"|"unknown"|"VisualBasic"|"XML"|"YAML")

```

--------------------------------

### POST /v1/chunk/hybrid/file/async

Source: https://www.jsonkeeper.com/b/S8XBK

API endpoint for POST /v1/chunk/hybrid/file/async

```markdown
### Request Body

**Content-Type:** multipart/form-data

- **files** (array (string (binary))) (required)
- **include_converted_doc** (boolean): If true, the output will include both the chunks and the converted document.
- **target_type** (string (inbody|zip)) ("inbody"|"zip")
- **convert_from_formats** (array (string)): Input format(s) to convert from. String or list of strings. Allowed values: docx, pptx, html, image, pdf, asciidoc, md, csv, xlsx, xml_uspto, xml_jats, mets_gbs, json_docling, audio. Optional, defaults to all formats.
- **convert_image_export_mode** (string (placeholder|embedded|referenced)): ImageRefMode. ("placeholder"|"embedded"|"referenced")
- **convert_do_ocr** (boolean): If enabled, the bitmap content will be processed using OCR. Boolean. Optional, defaults to true
- **convert_force_ocr** (boolean): If enabled, replace existing text with OCR-generated text over content. Boolean. Optional, defaults to false.
- **convert_ocr_engine** (string (easyocr|ocrmac|rapidocr|tesserocr|tesseract)) ("easyocr"|"ocrmac"|"rapidocr"|"tesserocr"|"tesseract")
- **convert_ocr_lang** (array (string))
- **convert_pdf_backend** (string (pypdfium2|dlparse_v1|dlparse_v2|dlparse_v4)): Enum of valid PDF backends. ("pypdfium2"|"dlparse_v1"|"dlparse_v2"|"dlparse_v4")
- **convert_table_mode** (string (fast|accurate)): Modes for the TableFormer model. ("fast"|"accurate")
- **convert_table_cell_matching** (boolean): If true, matches table cells predictions back to PDF cells. Can break table output if PDF cells are merged across table columns. If false, let table structure model define the text cells, ignore PDF cells.
- **convert_pipeline** (string (standard|vlm|asr)) ("standard"|"vlm"|"asr")
- **convert_page_range** (array (string)): Only convert a range of pages. The page number starts at 1.
- **convert_document_timeout** (number): The timeout for processing each document, in seconds.
- **convert_abort_on_error** (boolean): Abort on error if enabled. Boolean. Optional, defaults to false.
- **convert_do_table_structure** (boolean): If enabled, the table structure will be extracted. Boolean. Optional, defaults to true.
- **convert_include_images** (boolean): If enabled, images will be extracted from the document. Boolean. Optional, defaults to true.
- **convert_images_scale** (number): Scale factor for images. Float. Optional, defaults to 2.0.
- **convert_md_page_break_placeholder** (string): Add this placeholder betweek pages in the markdown output.
- **convert_do_code_enrichment** (boolean): If enabled, perform OCR code enrichment. Boolean. Optional, defaults to false.
- **convert_do_formula_enrichment** (boolean): If enabled, perform formula OCR, return LaTeX code. Boolean. Optional, defaults to false.
- **convert_do_picture_classification** (boolean): If enabled, classify pictures in documents. Boolean. Optional, defaults to false.
- **convert_do_picture_description** (boolean): If enabled, describe pictures in documents. Boolean. Optional, defaults to false.
- **convert_picture_description_area_threshold** (number): Minimum percentage of the area for a picture to be processed with the models.
- **convert_picture_description_local** (string): Options for running a local vision-language model in the picture description. The parameters refer to a model hosted on Hugging Face. This parameter is mutually exclusive with picture_description_api.
- **convert_picture_description_api** (string): API details for using a vision-language model in the picture description. This parameter is mutually exclusive with picture_description_local.
- **convert_vlm_pipeline_model** (string (smoldocling|smoldocling_vllm|granite_vision|granite_vision_vllm|granite_vision_ollama|got_ocr_2)) ("smoldocling"|"smoldocling_vllm"|"granite_vision"|"granite_vision_vllm"|"granite_vision_ollama"|"got_ocr_2")
- **convert_vlm_pipeline_model_local** (string): Options for running a local vision-language model for the vlm pipeline. The parameters refer to a model hosted on Hugging Face. This parameter is mutually exclusive with vlm_pipeline_model_api and vlm_pipeline_model.
- **convert_vlm_pipeline_model_api** (string): API details for using a vision-language model for the vlm pipeline. This parameter is mutually exclusive with vlm_pipeline_model_local and vlm_pipeline_model.
- **chunking_use_markdown_tables** (boolean): Use markdown table format instead of triplets for table serialization.
- **chunking_include_raw_text** (boolean): Include both raw_text and text (contextualized) in response. If False, only text is included.
- **chunking_max_tokens** (integer)
- **chunking_tokenizer** (string): HuggingFace model name for custom tokenization. If not specified, uses 'sentence-transformers/all-MiniLM-L6-v2' as default.
- **chunking_merge_peers** (boolean): Merge undersized successive chunks with same headings.

### Responses

#### 200 - Successful Response

**TaskStatusResponse**
- **task_id** (string) (required)
- **task_type** (string (convert|chunk)) (required) ("convert"|"chunk")
- **task_status** (string) (required)
- **task_position** (integer)
- **task_meta** (object)
  - **num_docs** (integer) (required)
  - **num_processed** (integer)
  - **num_succeeded** (integer)
  - **num_failed** (integer)

#### 422 - Validation Error

**HTTPValidationError**
- **detail** (array (string))
  Array items:
    - **loc** (array (string)) (required)
    - **msg** (string) (required)
    - **type** (string) (required)

### Example Usage

```bash
curl -X POST "https://api.example.com/v1/chunk/hybrid/file/async" \
  -H "Content-Type: application/json" \
  -d '{
  "files": [
    "string"
  ],
  "include_converted_doc": "false",
  "target_type": "inbody",
  "convert_from_formats": [
    "string"
  ],
  "convert_image_export_mode": "embedded",
  "convert_do_ocr": "true",
  "convert_force_ocr": "false",
  "convert_ocr_engine": "easyocr",
  "convert_ocr_lang": "value",
  "convert_pdf_backend": "dlparse_v4",
  "convert_table_mode": "accurate",
  "convert_table_cell_matching": "true",
  "convert_pipeline": "standard",
  "convert_page_range": [
    "string"
  ],
  "convert_document_timeout": "604800",
  "convert_abort_on_error": "false",
  "convert_do_table_structure": "true",
  "convert_include_images": "true",
  "convert_images_scale": "2",
  "convert_md_page_break_placeholder": "",
  "convert_do_code_enrichment": "false",
  "convert_do_formula_enrichment": "false",
  "convert_do_picture_classification": "false",
  "convert_do_picture_description": "false",
  "convert_picture_description_area_threshold": "0.05",
  "convert_picture_description_local": "string",
  "convert_picture_description_api": "string",
  "convert_vlm_pipeline_model": "value",
  "convert_vlm_pipeline_model_local": "string",
  "convert_vlm_pipeline_model_api": "string",
  "chunking_use_markdown_tables": "false",
  "chunking_include_raw_text": "false",
  "chunking_max_tokens": "value",
  "chunking_tokenizer": "sentence-transformers/all-MiniLM-L6-v2",
  "chunking_merge_peers": "true"
}'
```

```