# Smart PDF Loader
```bash
pip install llama-index-readers-smart-pdf-loader
```
SmartPDFLoader is a super fast PDF reader that understands the layout structure of PDFs such as nested sections, nested lists, paragraphs and tables.
It uses layout information to smartly chunk PDFs into optimal short contexts for LLMs.
## Requirements
Install the llmsherpa library if it is not already present:
```
pip install llmsherpa
```
## Usage
Here's an example usage of the SmartPDFLoader:
```python
from llama_index.readers.smart_pdf_loader import SmartPDFLoader
llmsherpa_api_url = "https://readers.llmsherpa.com/api/document/developer/parseDocument?renderFormat=all"
pdf_url = "https://arxiv.org/pdf/1910.13461.pdf" # also allowed is a file path e.g. /home/downloads/xyz.pdf
pdf_loader = SmartPDFLoader(llmsherpa_api_url=llmsherpa_api_url)
documents = pdf_loader.load_data(pdf_url)
```
Now you can use the documents with other LlamaIndex components. For example, for retrieval augmented generation, try this:
```python
from llama_index.core import VectorStoreIndex
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
response = query_engine.query("list all the tasks that work with bart")
print(response)
response = query_engine.query("what is the bart performance score on squad")
print(response)
```
## More Examples
SmartPDFLoader is based on LayoutPDFReader from [llmsherpa](https://github.com/nlmatics/llmsherpa) library. See the [documentation](<(https://github.com/nlmatics/llmsherpa)>) there to explore other ways to use the library for connecting data from your PDFs with LLMs.
- [Summarize a section using prompts](https://github.com/nlmatics/llmsherpa#summarize-a-section-using-prompts)
- [Analyze a table using prompts](https://github.com/nlmatics/llmsherpa#analyze-a-table-using-prompts)
- [Vector search and RAG](https://github.com/nlmatics/llmsherpa#vector-search-and-retrieval-augmented-generation-with-smart-chunking)
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-readers-smart-pdf-loader",
"maintainer": "ansukla",
"docs_url": null,
"requires_python": "<4.0,>=3.8.1",
"maintainer_email": null,
"keywords": "pdf layout, pdf table, pdf",
"author": "Your Name",
"author_email": "you@example.com",
"download_url": "https://files.pythonhosted.org/packages/cf/b0/05008a9c052b3cec0d12f53659b53489f773b3431647ae5da2ffa5118f33/llama_index_readers_smart_pdf_loader-0.1.4.tar.gz",
"platform": null,
"description": "# Smart PDF Loader\n\n```bash\npip install llama-index-readers-smart-pdf-loader\n```\n\nSmartPDFLoader is a super fast PDF reader that understands the layout structure of PDFs such as nested sections, nested lists, paragraphs and tables.\nIt uses layout information to smartly chunk PDFs into optimal short contexts for LLMs.\n\n## Requirements\n\nInstall the llmsherpa library if it is not already present:\n\n```\npip install llmsherpa\n```\n\n## Usage\n\nHere's an example usage of the SmartPDFLoader:\n\n```python\nfrom llama_index.readers.smart_pdf_loader import SmartPDFLoader\n\nllmsherpa_api_url = \"https://readers.llmsherpa.com/api/document/developer/parseDocument?renderFormat=all\"\npdf_url = \"https://arxiv.org/pdf/1910.13461.pdf\" # also allowed is a file path e.g. /home/downloads/xyz.pdf\npdf_loader = SmartPDFLoader(llmsherpa_api_url=llmsherpa_api_url)\ndocuments = pdf_loader.load_data(pdf_url)\n```\n\nNow you can use the documents with other LlamaIndex components. For example, for retrieval augmented generation, try this:\n\n```python\nfrom llama_index.core import VectorStoreIndex\n\nindex = VectorStoreIndex.from_documents(documents)\nquery_engine = index.as_query_engine()\n\nresponse = query_engine.query(\"list all the tasks that work with bart\")\nprint(response)\n\nresponse = query_engine.query(\"what is the bart performance score on squad\")\nprint(response)\n```\n\n## More Examples\n\nSmartPDFLoader is based on LayoutPDFReader from [llmsherpa](https://github.com/nlmatics/llmsherpa) library. See the [documentation](<(https://github.com/nlmatics/llmsherpa)>) there to explore other ways to use the library for connecting data from your PDFs with LLMs.\n\n- [Summarize a section using prompts](https://github.com/nlmatics/llmsherpa#summarize-a-section-using-prompts)\n- [Analyze a table using prompts](https://github.com/nlmatics/llmsherpa#analyze-a-table-using-prompts)\n- [Vector search and RAG](https://github.com/nlmatics/llmsherpa#vector-search-and-retrieval-augmented-generation-with-smart-chunking)\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index readers smart_pdf_loader integration",
"version": "0.1.4",
"project_urls": null,
"split_keywords": [
"pdf layout",
" pdf table",
" pdf"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "eee91d25bb73b9b03c1d753f16b4b6d4a82cbeeff2fbe72ea7e337c971f1e648",
"md5": "a9d58ed1c90f7bfe76fef7f0005e62ec",
"sha256": "ba21a0ba8b46cd5a5f1205b4601147e469dccccac57de2902cab44794047f57a"
},
"downloads": -1,
"filename": "llama_index_readers_smart_pdf_loader-0.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a9d58ed1c90f7bfe76fef7f0005e62ec",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.8.1",
"size": 3165,
"upload_time": "2024-04-15T18:31:37",
"upload_time_iso_8601": "2024-04-15T18:31:37.781919Z",
"url": "https://files.pythonhosted.org/packages/ee/e9/1d25bb73b9b03c1d753f16b4b6d4a82cbeeff2fbe72ea7e337c971f1e648/llama_index_readers_smart_pdf_loader-0.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "cfb005008a9c052b3cec0d12f53659b53489f773b3431647ae5da2ffa5118f33",
"md5": "58304b509ab85d34199096d8604459c6",
"sha256": "40b135750612b175eea16297749946a82238776b398683fc6b1a605e7208300d"
},
"downloads": -1,
"filename": "llama_index_readers_smart_pdf_loader-0.1.4.tar.gz",
"has_sig": false,
"md5_digest": "58304b509ab85d34199096d8604459c6",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.8.1",
"size": 2787,
"upload_time": "2024-04-15T18:31:40",
"upload_time_iso_8601": "2024-04-15T18:31:40.055272Z",
"url": "https://files.pythonhosted.org/packages/cf/b0/05008a9c052b3cec0d12f53659b53489f773b3431647ae5da2ffa5118f33/llama_index_readers_smart_pdf_loader-0.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-15 18:31:40",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-readers-smart-pdf-loader"
}
JSON