A simple tool to extract data from PDFs and images using Google's gemini-2.0-flash-001 model.
Project description
Gemini Data Extractor
This tool is a prof-of-concept for extracting data from PDFs and images, using the gemini-2.0-flash-001 LLM from Google. This model attracted a lot of attention lately due to its good performances ad affordable API prices.
It uses Google's GenAI library to interact with the model and extract data from a given document using your prompt. The extracted date is returned in JSON format.
Installation
You can install the tool using pip:
pip install gemini-data-extractor
Usage
You can use the tool by running the following command (see also "Authentication" below):
gemini-data-extractor --path path/to/your/file.pdf --prompt-text "Your prompt here"
The tool will return the extracted data in JSON format to the standard output. In case of a long prompt, you can save it to a file and pass the path to the file using the --prompt-file argument:
gemini-data-extractor --path path/to/your/file.png --prompt-file path/to/your/prompt.txt
Authentication
In order to use the gemini API you need to authenticate either using a gemini studio API key or via the Google Cloud SDK. You can obtain a key from Google AI Studio. You can then authenticate using the --api-key argument or setting the GEMINI_API_KEY environment variable:
gemini-data-extractor --path path/to/your/file.pdf --prompt "Your prompt here" --api-key your-api-key
or
export GEMINI_API_KEY=your-api-key
gemini-data-extractor --path path/to/your/file.pdf --prompt "Your prompt here"
Alternatively, if you have a working Google Cloud Account and the Google Cloud SDK installed, you can authenticate using the gcloud command:
gcloud auth application-default login
Then you can use the tool with the options --project-id and --location (or by setting the GCP_PROJECT_ID and GCP_LOCATION environment variables):
gemini-data-extractor --path path/to/your/file.pdf --prompt "Your prompt here" --project-id your-project-id --location your-location
or
export GCP_PROJECT_ID=your-project-id
export GCP_LOCATION=your-location
gemini-data-extractor --path path/to/your/file.pdf --prompt "Your prompt here"
License
This tool is licensed under the MIT license. You can find more information in the LICENSE file.
Disclaimer
Gemini is a trademark of Google LLC. This project is not affiliated with Google LLC. The tool uses the GenAI library to interact with the gemini-2.0-flash-001 LLM from Google.
The tool is provided as-is and is not officially supported by Google LLC. Use it at your own risk.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file gemini_data_extractor-0.1.2.tar.gz.
File metadata
- Download URL: gemini_data_extractor-0.1.2.tar.gz
- Upload date:
- Size: 36.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.6.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
75a4f8e6ef24e71a3fcd14475f6d5f069f48635e1c2e1373c028f263c2690b23
|
|
| MD5 |
91f5758ae35b97d5331c58f65ab0a174
|
|
| BLAKE2b-256 |
2d72ee23a597d302c3f207f200e41fb5f1ca06d452d686d87e9699927fee179d
|
File details
Details for the file gemini_data_extractor-0.1.2-py3-none-any.whl.
File metadata
- Download URL: gemini_data_extractor-0.1.2-py3-none-any.whl
- Upload date:
- Size: 5.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.6.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
351a68fa8f8b253281f7841781464985097a9a7aa0ffecae486fa761c0f55481
|
|
| MD5 |
c655c4048034b3c66f81c09f62df2f81
|
|
| BLAKE2b-256 |
7b0f554f823029831a413c55fcd050bb5c600e0662dc6a2e1b42b0d86389627d
|