Seamless Document Processing with Google Gemini API
🌍 gemini-parser is your all-in-one Python library for document parsing using the Google Gemini API.
⚡ It enables developers to transcribe PDFs, extract structured data, and summarize large documents with ease.
🚀 Whether you're transcribing PDFs, extracting structured data, or summarizing large documents, gemini-parser delivers fast, reliable, and efficient results.
🔥 Why choose gemini-parser?
- 🚀 AI-powered document parsing with Google Gemini API.
- 📦 Handles large files effortlessly (up to 20GB).
- ⚡ Smart caching for faster processing and reduced costs.
- 📑 Supports multiple formats: PDF, CSV, HTML, DOC, XML, TXT.
- 🌐 Flexible inputs from local files, folders, or URLs.
- 📊 Structured data extraction for easy analysis.
- 📜 Handle Large output context unlike gemini output context of ~8000 tokens, gemini-parser doesn't have a limit.
📦 Installation
pip install gemini-parser
Usage
⚠️ The library works perfectly fine for PDFs now. For other files type I will be adding support soon.
Quickstart Example
from gemini_parser import DocumentProcessor
from pathlib import Path
import os
from dotenv import load_dotenv
load_dotenv()
# Initialize processor with API key
processor = DocumentProcessor(api_key=os.getenv("GEMINI_API_KEY"))
# Process a single PDF file
result = processor.process_file(Path("path/to/document.pdf"))
print(result)
# Process from a URL
url_result = processor.process_from_url("https://example.com/document.pdf")
print(url_result)
# Process all files in a folder
processor.process_folder(Path("path/to/folder"))
# List all caches
caches = processor.list_caches()
print(caches)
# Delete a cache
processor.delete_cache("cachedContentID")
Configuration
You can customize key parameters when initializing the DocumentProcessor:
api_key: Your Gemini API key.model_name: The Gemini model (e.g.,gemini-1.5-flash-002).prompt: The default processing prompt.log_level: Logging level (INFO,DEBUG, etc.).
API Reference
DocumentProcessor
process_file(file_path, use_cache=False, cache_ttl=None): Processes a local file.process_from_url(url, use_cache=False, cache_ttl=None): Processes a document from a URL.process_multiple_files(file_paths, use_cache=False, cache_ttl=None): Processes multiple files.process_folder(folder_path, output_dir=None, out_ext="md", use_cache=False, cache_ttl=None): Processes all files in a folder.list_caches(): Lists all available caches.delete_cache(cache_name): Deletes a cache by name.
FileManager
upload_file(file_or_path, mime_type): Uploads files to Gemini.list_files(): Lists all uploaded files.get_file(file_name): Gets metadata of a file.delete_file(file_name): Deletes an uploaded file.
CachingManager
create_cache(model_name, contents, system_instruction): Creates a new cache.generate_with_cache(model_name, cached_content_name, prompt): Generates content using a cache.list_caches(): Lists all cached content.update_cache_ttl(cache_name, hours): Updates the cache TTL.delete_cache(cache_name): Deletes a cache.
Testing
Your library includes pytest-based tests in the tests/ folder. Run them with:
pytest tests/
Requirements
- Python 3.8+
tqdmPyPDF2google-genaipython-dotenvhttpx
Project Structure
gemini-parser/
│
├── gemini_parser/
│ ├── document_processor.py
│ ├── file_manager.py
│ ├── caching.py
│ ├── utils.py
│
├── tests/
│ ├── test_gemini_parser.py
│
├── setup.py
├── pyproject.toml
├── README.md
└── LICENSE
License
This project is licensed under the MIT License.
Contributing
Contributions are welcome! Please fork this repository, create a new branch, and submit a pull request.
Author
Developed by Thimira Nirmal
📧 timnirmal@gmail.com
🌐 GitHub | Website
Metadata
Release files for gemini-parser 0.1.0.post2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| gemini-parser-0.1.0.post2.tar.gz | 12.3 kB | Without provenance | Details for gemini-parser-0.1.0.post2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| gemini_parser-0.1.0.post2-py3-none-any.whl | Python 3 | none | any | Details for gemini_parser-0.1.0.post2-py3-none-any.whl |
Total release size: 22.7 kB
Release files / gemini-parser-0.1.0.post2.tar.gz
| Download URL | gemini-parser-0.1.0.post2.tar.gz |
|---|---|
| Size | 12.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
82145a4e9b40ebe55f2e7c7148c437c36fa5b6c6d4ed625a2bd55cb2323302dd
|
|
BLAKE2b-256 checksum How to use checksums |
cb0ef9824bfa9e40c64e108a2e6e46063da34b80b26b40b05525a904251a2510
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.10.0
|
Release files / gemini_parser-0.1.0.post2-py3-none-any.whl
| Download URL | gemini_parser-0.1.0.post2-py3-none-any.whl |
|---|---|
| Size | 10.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
507bb0a70bb43aaa34cfcd900ae5c072c3b351a74d5aa2bea11d964606880690
|
|
BLAKE2b-256 checksum How to use checksums |
c31c2493f3bd0531adb0be62ef0209b2f450fbaf5909bdd31af98b5bc1ae41a6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.10.0
|
Security for gemini-parser 0.1.0.post2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.