receipt-scanner

🧾✨ AI-Powered Receipt and Invoice Scanner for Laravel, with support for images, documents and text

Stars: 95

Visit

The receipt-scanner repository is an AI-Powered Receipt and Invoice Scanner for Laravel that allows users to easily extract structured receipt data from images, PDFs, and emails within their Laravel application using OpenAI. It provides a light wrapper around OpenAI Chat and Completion endpoints, supports various input formats, and integrates with Textract for OCR functionality. Users can install the package via composer, publish configuration files, and use it to extract data from plain text, PDFs, images, Word documents, and web content. The scanned receipt data is parsed into a DTO structure with main classes like Receipt, Merchant, and LineItem.

README:

Need more flexibility? Try the Extractor package instead, a AI-Powered data extraction library for Laravel

AI-Powered Receipt and Invoice Scanner for Laravel

Easily extract structured receipt data from images, PDFs, and emails within your Laravel application using OpenAI.

Features

Light wrapper around OpenAI Chat and Completion endpoints.
Accepts text as input and returns structured receipt information.
Includes a well-tuned prompt for parsing receipts.
Supports various input formats including Plain Text, PDF, Images, Word documents, and Web content.
Integrates with Textract for OCR functionality.

Installation

Install the package via composer:

composer require helgesverre/receipt-scanner

Publish the config file:

php artisan vendor:publish --tag="receipt-scanner-config"

All the configuration options are documented in the configuration file.

Since this package uses the OpenAI Laravel Package, so you also need to publish their config and add the OPENAI_API_KEY to your .env file:

php artisan vendor:publish --provider="OpenAI\Laravel\ServiceProvider"

OPENAI_API_KEY="your-key-here

Usage

Extracting receipt data from Plain Text

Plain text scanning is useful when you already have the textual representation of a receipt or invoice.

The example is from a Paddle.com receipt email, where I copied all the text in the email, and removed all the empty lines.

$text = <<<RECEIPT
Liseth Solutions AS
via software reseller Paddle.com
Thank you for your purchase!
Your full invoice is attached to this email.
Amount paid
Payment method
NOK 2,498.75
visa
ending in 4242
Test: SaaS Subscription - Pro Plan
September 22, 2023 11:04 am UTC - October 22, 2023 11:04 am UTC
NOK 1,999.00
QTY: 1
Subtotal
NOK 1,999.00
VAT
NOK 499.75
Amount paid*
NOK 2,498.75
*This payment will appear on your statement as: PADDLE.NET* EXAMPLEINC
NEED HELP?
Need help with your purchase? Please contact us on paddle.net.
logo
Paddle.com Market Ltd, Judd House, 18-29 Mora Street, London EC1V 8BT
© 2023 Paddle. All rights reserved.
RECEIPT;


ReceiptScanner::scan($text);

Extracting data from other formats

use HelgeSverre\ReceiptScanner\Facades\Text;

$textPlainText = Text::text(file_get_contents('./receipt.txt'));
$textPdf = Text::pdf(file_get_contents('./receipt.pdf'));
$textImageOcr = Text::textract(file_get_contents('./receipt.jpg'));
$textPdfOcr = Text::textractUsingS3Upload(file_get_contents('./receipt.pdf'));
$textWord = Text::word(file_get_contents('./receipt.doc'));
$textWeb = Text::web('https://example.com');
$textHtml = Text::html(file_get_contents('./receipt.html'));

After loading, you can pass the TextContent or the plain text (which can be retrieved by calling ->toString()) into the ReceiptScanner::scan() method.

use HelgeSverre\ReceiptScanner\Facades\ReceiptScanner;

ReceiptScanner::scan($textPlainText)
ReceiptScanner::scan($textPdf)
ReceiptScanner::scan($textImageOcr)
ReceiptScanner::scan($textPdfOcr)
ReceiptScanner::scan($textWord)
ReceiptScanner::scan($textWeb)
ReceiptScanner::scan($textHtml)

Receipt Data Model

The scanned receipt is parsed into a DTO which consists of a main Receipt class, which contains the receipt metadata, and a Merchant dto, representing the seller on the receipt or invoice, and an array of LineItem DTOs holding each individual line item.

HelgeSverre\ReceiptScanner\Data\Receipt
HelgeSverre\ReceiptScanner\Data\Merchant
HelgeSverre\ReceiptScanner\Data\LineItem

The DTO has a toArray() method, which will result in a structure like this:

For flexibility, all fields are nullable.

[
    "orderRef" => "string",
    "date" => "date",
    "taxAmount" => "number",
    "totalAmount" => "number",
    "currency" => "string",
    "merchant" => [
        "name" => "string",
        "vatId" => "string",
        "address" => "string",
    ],
    "lineItems" => [
        [
            "text" => "string",
            "sku" => "string",
            "qty" => "number",
            "price" => "number",
        ],
    ],
];

Returning an Array instead of a DTO

If you prefer to work with an array instead of the built-in DTO, you can specify asArray: true when calling scan()

use HelgeSverre\ReceiptScanner\Facades\ReceiptScanner;

ReceiptScanner::scan(
    $textPlainText
    asArray: true
)

Specifying the model

To use a different model, you can specify the model name to use with the model named argument when calling the scan() method.

use HelgeSverre\ReceiptScanner\Facades\ReceiptScanner;
use HelgeSverre\ReceiptScanner\ModelNames;

// With the ModelNames class
ReceiptScanner::scan($content, model: ModelNames::GPT4_1106_PREVIEW)

// With a string
ReceiptScanner::scan($content, model: 'gpt-4-1106-preview')

All parameters and what they do

$text (TextContent|string)

The input text from the receipt or invoice that needs to be parsed. It accepts either a TextContent object or a string.

**$model (string)

This parameter specifies the OpenAI model used for the extraction process.

HelgeSverre\ReceiptScanner\ModelNames is a class containing constants for each model, provided for convenience. However, you can also directly use a string to specify the model if you prefer.

Different models have different speed/accuracy characteristics.

If you require high accuracy, use a GPT-4 model, if you need speed, use a GPT-3 model, if you need even more speed, use the gpt-3.5-turbo-instruct model.

The default model is ModelNames::TURBO_INSTRUCT.

`ModelNames` Constant	Value
`ModelNames::TURBO`	`gpt-3.5-turbo`
`ModelNames::TURBO_INSTRUCT`	`gpt-3.5-turbo-instruct`
`ModelNames::TURBO_1106`	`gpt-3.5-turbo-1106`
`ModelNames::TURBO_16K`	`gpt-3.5-turbo-16k`
`ModelNames::TURBO_0613`	`gpt-3.5-turbo-0613`
`ModelNames::TURBO_16K_0613`	`gpt-3.5-turbo-16k-0613`
`ModelNames::TURBO_0301`	`gpt-3.5-turbo-0301`
`ModelNames::GPT4`	`gpt-4`
`ModelNames::GPT4_32K`	`gpt-4-32k`
`ModelNames::GPT4_32K_0613`	`gpt-4-32k-0613`
`ModelNames::GPT4_1106_PREVIEW`	`gpt-4-1106-preview`
`ModelNames::GPT4_0314`	`gpt-4-0314`
`ModelNames::GPT4_32K_0314`	`gpt-4-32k-0314`

$maxTokens (int)

The maximum number of tokens that the model will processes. The default value is 2000, adjusting this value may be necessary for very long text, but 2000 is "usually" fairly good.

$temperature (float)

Controls the randomness/creativity of the model's output.

A higher value (e.g., 0.8) makes the output more random, which is usually not what we want in this scenario, I usually go with 0.1 or 0.2, anything over 0.5 becomes useless. Defaults to 0.1.

$template (string)

This parameter specifies the template used for the prompt.

The default template is 'receipt'. You can create and use additional templates by adding new blade files in the resources/views/vendor/receipt-scanner/ directory and specifying the file name (without extension) as the $template value (eg: "minimal_invoice".

$asArray (bool)

If true, returns the response from the AI model as an array instead of as a DTO, useful if you need to modifythe default DTO to have more/less fields or want to convert the response into your own DTO, defaults to false

Example Usage:

use HelgeSverre\ReceiptScanner\Facades\ReceiptScanner;

$parsedReceipt = ReceiptScanner::scan(
    text: $textInput,
    model: ModelNames::TURBO_INSTRUCT,
    maxTokens: 500,
    temperature: 0.2,
    template: 'minimal_invoice',
    asArray: true,
);

List of supported models

Enum Value	Model name	Endpoint
TURBO_INSTRUCT	gpt-3.5-turbo-instruct	Completion
TURBO_16K	gpt-3.5-turbo-16k	Chat
TURBO	gpt-3.5-turbo	Chat
GPT4	gpt-4	Chat
GPT4_32K	gpt-4-32	Chat

OCR Configuration with AWS Textract

To use AWS Textract for extracting text from large images and multi-page PDFs, the package needs to upload the file to S3 and pass the s3 object location along to the textract service.

So you need to configure your AWS Credentials in the config/receipt-scanner.php file as follows:

TEXTRACT_KEY="your-aws-access-key"
TEXTRACT_SECRET="your-aws-security"
TEXTRACT_REGION="your-textract-region"

# Can be omitted
TEXTRACT_VERSION="2018-06-27"

You also need to configure a seperate Textract disk where the files will be stored, open your config/filesystems.php configuration file and add the following:

'textract' => [
    'driver' => 's3',
    'key' => env('TEXTRACT_KEY'),
    'secret' => env('TEXTRACT_SECRET'),
    'region' => env('TEXTRACT_REGION'),
    'bucket' => env('TEXTRACT_BUCKET'),
],

Ensure the textract_disk setting in config/receipt-scanner.php is the same as your disk name in the filesystems.php config, you can change it with the .env value TEXTRACT_DISK.

return [
    "textract_disk" => env("TEXTRACT_DISK")
];

.env

TEXTRACT_DISK="uploads"

Note

Textract is not available in all regions:

Q: In which AWS regions is Amazon Textract available? Amazon Textract is currently available in the US East (Northern Virginia), US East (Ohio), US West (Oregon), US West ( N. California), AWS GovCloud (US-West), AWS GovCloud (US-East), Canada (Central), EU (Ireland), EU (London), EU ( Frankfurt), EU (Paris), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Seoul), and Asia Pacific ( Mumbai) Regions.

See: https://aws.amazon.com/textract/faqs/

Publishing Prompts

You may publish the prompt file that is used under the hood by running this command:

php artisan vendor:publish --tag="receipt-scanner-prompts"

This package simply uses blade files as prompts, the {{ $context }} variable will be replaced by the text you pass to ReceiptScanner::scan("text here").

Adding prompts/templates

By default, the package uses the receipt.blade.php file as its prompt template, you may add additional templates by simply creating a blade file in resources/views/vendor/receipt-scanner/minimal_invoice.blade.php and changing the $template parameter when calling scan()

Example prompt:

Extract the following fields from the text below, output as JSON

date (as string in the  Y-m-d format)
total_amount (as float, do not include currency symbol) 
vendor_name (company name)

{{ $context }}

OUTPUT IN JSON

use HelgeSverre\ReceiptScanner\Facades\ReceiptScanner;

$receipt = ReceiptScanner::scan(
    text: "Your invoice here",
    model:  ModelNames::TURBO_INSTRUCT,
    template: 'minimal_invoice',
    asArray: true,
);

License

This package is licensed under the MIT License. For more details, refer to the License File.

For Tasks:

Click tags to check more tools for each tasks

extract receipt data parse invoices integrate with textract scan plain text process pdfs

For Jobs:

data analyst accountant financial analyst software developer ai engineer

Alternative AI tools for receipt-scanner

Similar Open Source Tools

receipt-scanner

github

: 95

python-tgpt

Python-tgpt is a Python package that enables seamless interaction with over 45 free LLM providers without requiring an API key. It also provides image generation capabilities. The name _python-tgpt_ draws inspiration from its parent project tgpt, which operates on Golang. Through this Python adaptation, users can effortlessly engage with a number of free LLMs available, fostering a smoother AI interaction experience.

github

: 95

nano-graphrag

nano-GraphRAG is a simple, easy-to-hack implementation of GraphRAG that provides a smaller, faster, and cleaner version of the official implementation. It is about 800 lines of code, small yet scalable, asynchronous, and fully typed. The tool supports incremental insert, async methods, and various parameters for customization. Users can replace storage components and LLM functions as needed. It also allows for embedding function replacement and comes with pre-defined prompts for entity extraction and community reports. However, some features like covariates and global search implementation differ from the original GraphRAG. Future versions aim to address issues related to data source ID, community description truncation, and add new components.

github

: 995

magentic

Easily integrate Large Language Models into your Python code. Simply use the `@prompt` and `@chatprompt` decorators to create functions that return structured output from the LLM. Mix LLM queries and function calling with regular Python code to create complex logic.

github

: 2.0k

mistral-inference

Mistral Inference repository contains minimal code to run 7B, 8x7B, and 8x22B models. It provides model download links, installation instructions, and usage guidelines for running models via CLI or Python. The repository also includes information on guardrailing, model platforms, deployment, and references. Users can interact with models through commands like mistral-demo, mistral-chat, and mistral-common. Mistral AI models support function calling and chat interactions for tasks like testing models, chatting with models, and using Codestral as a coding assistant. The repository offers detailed documentation and links to blogs for further information.

github

: 9.6k

bonito

Bonito is an open-source model for conditional task generation, converting unannotated text into task-specific training datasets for instruction tuning. It is a lightweight library built on top of Hugging Face `transformers` and `vllm` libraries. The tool supports various task types such as question answering, paraphrase generation, sentiment analysis, summarization, and more. Users can easily generate synthetic instruction tuning datasets using Bonito for zero-shot task adaptation.

github

: 636

aicsimageio

AICSImageIO is a Python tool for Image Reading, Metadata Conversion, and Image Writing for Microscopy Images. It supports various file formats like OME-TIFF, TIFF, ND2, DV, CZI, LIF, PNG, GIF, and Bio-Formats. Users can read and write metadata and imaging data, work with different file systems like local paths, HTTP URLs, s3fs, and gcsfs. The tool provides functionalities for full image reading, delayed image reading, mosaic image reading, metadata reading, xarray coordinate plane attachment, cloud IO support, and saving to OME-TIFF. It also offers benchmarking and developer resources.

github

: 198

aiavatarkit

AIAvatarKit is a tool for building AI-based conversational avatars quickly. It supports various platforms like VRChat and cluster, along with real-world devices. The tool is extensible, allowing unlimited capabilities based on user needs. It requires VOICEVOX API, Google or Azure Speech Services API keys, and Python 3.10. Users can start conversations out of the box and enjoy seamless interactions with the avatars.

github

: 154

LeanCopilot

Lean Copilot is a tool that enables the use of large language models (LLMs) in Lean for proof automation. It provides features such as suggesting tactics/premises, searching for proofs, and running inference of LLMs. Users can utilize built-in models from LeanDojo or bring their own models to run locally or on the cloud. The tool supports platforms like Linux, macOS, and Windows WSL, with optional CUDA and cuDNN for GPU acceleration. Advanced users can customize behavior using Tactic APIs and Model APIs. Lean Copilot also allows users to bring their own models through ExternalGenerator or ExternalEncoder. The tool comes with caveats such as occasional crashes and issues with premise selection and proof search. Users can get in touch through GitHub Discussions for questions, bug reports, feature requests, and suggestions. The tool is designed to enhance theorem proving in Lean using LLMs.

github

: 933

auto-playwright

Auto Playwright is a tool that allows users to run Playwright tests using AI. It eliminates the need for selectors by determining actions at runtime based on plain-text instructions. Users can automate complex scenarios, write tests concurrently with or before functionality development, and benefit from rapid test creation. The tool supports various Playwright actions and offers additional options for debugging and customization. It uses HTML sanitization to reduce costs and improve text quality when interacting with the OpenAI API.

github

: 298

datadreamer

DataDreamer is an advanced toolkit designed to facilitate the development of edge AI models by enabling synthetic data generation, knowledge extraction from pre-trained models, and creation of efficient and potent models. It eliminates the need for extensive datasets by generating synthetic datasets, leverages latent knowledge from pre-trained models, and focuses on creating compact models suitable for integration into any device and performance for specialized tasks. The toolkit offers features like prompt generation, image generation, dataset annotation, and tools for training small-scale neural networks for edge deployment. It provides hardware requirements, usage instructions, available models, and limitations to consider while using the library.

github

: 77

openedai-speech

OpenedAI Speech is a free, private text-to-speech server compatible with the OpenAI audio/speech API. It offers custom voice cloning and supports various models like tts-1 and tts-1-hd. Users can map their own piper voices and create custom cloned voices. The server provides multilingual support with XTTS voices and allows fixing incorrect sounds with regex. Recent changes include bug fixes, improved error handling, and updates for multilingual support. Installation can be done via Docker or manual setup, with usage instructions provided. Custom voices can be created using Piper or Coqui XTTS v2, with guidelines for preparing audio files. The tool is suitable for tasks like generating speech from text, creating custom voices, and multilingual text-to-speech applications.

github

: 243

phidata

Phidata is a framework for building AI Assistants with memory, knowledge, and tools. It enables LLMs to have long-term conversations by storing chat history in a database, provides them with business context by storing information in a vector database, and enables them to take actions like pulling data from an API, sending emails, or querying a database. Memory and knowledge make LLMs smarter, while tools make them autonomous.

github

: 11.4k

chatgpt-subtitle-translator

This tool utilizes the OpenAI ChatGPT API to translate text, with a focus on line-based translation, particularly for SRT subtitles. It optimizes token usage by removing SRT overhead and grouping text into batches, allowing for arbitrary length translations without excessive token consumption while maintaining a one-to-one match between line input and output.

github

: 195

olah

Olah is a self-hosted lightweight Huggingface mirror service that implements mirroring feature for Huggingface resources at file block level, enhancing download speeds and saving bandwidth. It offers cache control policies and allows administrators to configure accessible repositories. Users can install Olah with pip or from source, set up the mirror site, and download models and datasets using huggingface-cli. Olah provides additional configurations through a configuration file for basic setup and accessibility restrictions. Future work includes implementing an administrator and user system, OOS backend support, and mirror update schedule task. Olah is released under the MIT License.

github

: 57

detoxify

Detoxify is a library that provides trained models and code to predict toxic comments on 3 Jigsaw challenges: Toxic comment classification, Unintended Bias in Toxic comments, Multilingual toxic comment classification. It includes models like 'original', 'unbiased', and 'multilingual' trained on different datasets to detect toxicity and minimize bias. The library aims to help in stopping harmful content online by interpreting visual content in context. Users can fine-tune the models on carefully constructed datasets for research purposes or to aid content moderators in flagging out harmful content quicker. The library is built to be user-friendly and straightforward to use.

github

: 927

For similar tasks

receipt-scanner

github

: 95

For similar jobs

SheetCopilot

SheetCopilot is an assistant agent that manipulates spreadsheets by following user commands. It leverages Large Language Models (LLMs) to interact with spreadsheets like a human expert, enabling non-expert users to complete tasks on complex software such as Google Sheets and Excel via a language interface. The tool observes spreadsheet states, polishes generated solutions based on external action documents and error feedback, and aims to improve success rate and efficiency. SheetCopilot offers a dataset with diverse task categories and operations, supporting operations like entry & manipulation, management, formatting, charts, and pivot tables. Users can interact with SheetCopilot in Excel or Google Sheets, executing tasks like calculating revenue, creating pivot tables, and plotting charts. The tool's evaluation includes performance comparisons with leading LLMs and VBA-based methods on specific datasets, showcasing its capabilities in controlling various aspects of a spreadsheet.

github

: 82

LangGraph-Expense-Tracker

LangGraph Expense tracker is a small project that explores the possibilities of LangGraph. It allows users to send pictures of invoices, which are then structured and categorized into expenses and stored in a database. The project includes functionalities for invoice extraction, database setup, and API configuration. It consists of various modules for categorizing expenses, creating database tables, and running the API. The database schema includes tables for categories, payment methods, and expenses, each with specific columns to track transaction details. The API documentation is available for reference, and the project utilizes LangChain for processing expense data.

github

: 82

receipt-scanner

github

: 95

actual-ai

Actual AI is a project designed to categorize uncategorized transactions for Actual Budget using OpenAI or OpenAI specification compatible API. It sends requests to the OpenAI API to classify transactions based on their description, amount, and notes. Transactions that cannot be classified are marked as 'not guessed' in notes. The tool allows users to sync accounts before classification and classify transactions on a cron schedule. Guessed transactions are marked in notes for easy review.

github

: 60

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 390

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 572