llama-index-readers-docling


Namellama-index-readers-docling JSON
Version 0.2.1 PyPI version JSON
download
home_pageNone
Summaryllama-index readers docling integration
upload_time2024-10-27 21:25:23
maintainerNone
docs_urlNone
authorPanos Vagenas
requires_python<3.13,>=3.10
licenseMIT
keywords
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            # Docling Reader

## Overview

Docling Reader uses [Docling](https://github.com/DS4SD/docling) to enable fast and easy extraction of PDF, DOCX, HTML, and other document types, into Markdown or JSON-serialized Docling format, for usage in LlamaIndex pipelines for RAG / QA etc.

## Installation

```console
pip install llama-index-readers-docling
```

## Usage

### Markdown export

By default, Docling Reader exports to Markdown. Basic usage looks like this:

```python
from llama_index.readers.docling import DoclingReader

reader = DoclingReader()
docs = reader.load_data(file_path="https://arxiv.org/pdf/2408.09869")
print(f"{docs[0].text[389:442]}...")
# > ## Abstract
# >
# > This technical report introduces Docling...
```

### JSON export

Docling Reader can also export Docling's native format to JSON:

```python
from llama_index.readers.docling import DoclingReader

reader = DoclingReader(export_type=DoclingReader.ExportType.JSON)
docs = reader.load_data(file_path="https://arxiv.org/pdf/2408.09869")
print(f"{docs[0].text[:53]}...")
# > {"schema_name": "DoclingDocument", "version": "1.0.0"...
```

> [!IMPORTANT]
> To appropriately parse Docling's native format, when using JSON export make sure
> to use a Docling Node Parser in your pipeline.

### With Simple Directory Reader

The Docling Reader can also be used directly in combination with Simple Directory Reader, for example:

```python
from llama_index.core import SimpleDirectoryReader

dir_reader = SimpleDirectoryReader(
    input_dir="/path/to/docs",
    file_extractor={".pdf": reader},
)
docs = dir_reader.load_data()
print(docs[0].metadata)
# > {'file_path': '/path/to/docs/2408.09869v3.pdf',
# >  'file_name': '2408.09869v3.pdf',
# >  'file_type': 'application/pdf',
# >  'file_size': 5566574,
# >  'creation_date': '2024-10-06',
# >  'last_modified_date': '2024-10-03'}
```

            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "llama-index-readers-docling",
    "maintainer": null,
    "docs_url": null,
    "requires_python": "<3.13,>=3.10",
    "maintainer_email": null,
    "keywords": null,
    "author": "Panos Vagenas",
    "author_email": "pva@zurich.ibm.com",
    "download_url": "https://files.pythonhosted.org/packages/b8/0c/2b3c6f18afcdb92a41dadb0ef25bd49780240c1c4fee328b67db7293b8e0/llama_index_readers_docling-0.2.1.tar.gz",
    "platform": null,
    "description": "# Docling Reader\n\n## Overview\n\nDocling Reader uses [Docling](https://github.com/DS4SD/docling) to enable fast and easy extraction of PDF, DOCX, HTML, and other document types, into Markdown or JSON-serialized Docling format, for usage in LlamaIndex pipelines for RAG / QA etc.\n\n## Installation\n\n```console\npip install llama-index-readers-docling\n```\n\n## Usage\n\n### Markdown export\n\nBy default, Docling Reader exports to Markdown. Basic usage looks like this:\n\n```python\nfrom llama_index.readers.docling import DoclingReader\n\nreader = DoclingReader()\ndocs = reader.load_data(file_path=\"https://arxiv.org/pdf/2408.09869\")\nprint(f\"{docs[0].text[389:442]}...\")\n# > ## Abstract\n# >\n# > This technical report introduces Docling...\n```\n\n### JSON export\n\nDocling Reader can also export Docling's native format to JSON:\n\n```python\nfrom llama_index.readers.docling import DoclingReader\n\nreader = DoclingReader(export_type=DoclingReader.ExportType.JSON)\ndocs = reader.load_data(file_path=\"https://arxiv.org/pdf/2408.09869\")\nprint(f\"{docs[0].text[:53]}...\")\n# > {\"schema_name\": \"DoclingDocument\", \"version\": \"1.0.0\"...\n```\n\n> [!IMPORTANT]\n> To appropriately parse Docling's native format, when using JSON export make sure\n> to use a Docling Node Parser in your pipeline.\n\n### With Simple Directory Reader\n\nThe Docling Reader can also be used directly in combination with Simple Directory Reader, for example:\n\n```python\nfrom llama_index.core import SimpleDirectoryReader\n\ndir_reader = SimpleDirectoryReader(\n    input_dir=\"/path/to/docs\",\n    file_extractor={\".pdf\": reader},\n)\ndocs = dir_reader.load_data()\nprint(docs[0].metadata)\n# > {'file_path': '/path/to/docs/2408.09869v3.pdf',\n# >  'file_name': '2408.09869v3.pdf',\n# >  'file_type': 'application/pdf',\n# >  'file_size': 5566574,\n# >  'creation_date': '2024-10-06',\n# >  'last_modified_date': '2024-10-03'}\n```\n",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "llama-index readers docling integration",
    "version": "0.2.1",
    "project_urls": null,
    "split_keywords": [],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "df7f6a9df95f2bb17609bf62eecc3ff1d753b3dc417b065024e8401fb1c76e32",
                "md5": "6164bb9c9ee8294e7ad5e47bf2cccd06",
                "sha256": "f64189a83fe7749219b5d75315596df12d9cd3a7e20de5a1c277122f28270f90"
            },
            "downloads": -1,
            "filename": "llama_index_readers_docling-0.2.1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "6164bb9c9ee8294e7ad5e47bf2cccd06",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": "<3.13,>=3.10",
            "size": 3722,
            "upload_time": "2024-10-27T21:25:22",
            "upload_time_iso_8601": "2024-10-27T21:25:22.411645Z",
            "url": "https://files.pythonhosted.org/packages/df/7f/6a9df95f2bb17609bf62eecc3ff1d753b3dc417b065024e8401fb1c76e32/llama_index_readers_docling-0.2.1-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "b80c2b3c6f18afcdb92a41dadb0ef25bd49780240c1c4fee328b67db7293b8e0",
                "md5": "e75fd8bb04ef250f4db4cfd0eb22f28a",
                "sha256": "f30b3af6892fb2192a1fc7df03a96ef5cbac21c8dfd76a99144d46ee59e381ed"
            },
            "downloads": -1,
            "filename": "llama_index_readers_docling-0.2.1.tar.gz",
            "has_sig": false,
            "md5_digest": "e75fd8bb04ef250f4db4cfd0eb22f28a",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": "<3.13,>=3.10",
            "size": 3400,
            "upload_time": "2024-10-27T21:25:23",
            "upload_time_iso_8601": "2024-10-27T21:25:23.864620Z",
            "url": "https://files.pythonhosted.org/packages/b8/0c/2b3c6f18afcdb92a41dadb0ef25bd49780240c1c4fee328b67db7293b8e0/llama_index_readers_docling-0.2.1.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-10-27 21:25:23",
    "github": false,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "lcname": "llama-index-readers-docling"
}
        
Elapsed time: 0.69458s