Level Up Your Odoo : A Head-to-Head Comparison of LLMs for Odoo Code Generation

Streamlining inventory management is a cornerstone of Odoo’s power. But manually tracking stock levels can be a time-consuming headache.  

This blog dives into the exciting world of Large Language Models (LLMs) – AI-powered tools revolutionizing Odoo development.

We compare five leading LLMs – GPT-4, Gemini, Perplexity, Microsoft Copilot, Cohere and Claude 3 opus – to discover which one reigns supreme in generating code for automated low-stock notification systems within Odoo 17.  

Get ready to witness the future of Odoo development!

THE CONTENDERS

1. GPT-4: This powerhouse focuses on thorough testing and deployment considerations, ensuring a robust solution.
2. Gemini : Known for its clean and adaptable code, Gemini offers a foundation for customization.
3. Perplexity : Simplicity reigns with Perplexity’s approach, introducing a new field for low-stock identification.
4. Microsoft Copilot : This practical solution extends the StockQuant model, offering email notifications.
5. Claude 3 opus : Taking a user-centric approach, Claude offers in-depth code explanations and notification customization.
6. Cohere : Cohere provides a comprehensive approach with a dedicated notification model and email functionality.

LET THE CODE CLASH BEGIN!

TOOL # 1 – GPT4

Prompt – What is the most efficient or elegant way to generate code In inventory management, there are data for many numbers of stocks,So if a stock level goes down from a particular level, the application should notify the user about it in  Odoo 17?

Code-

After implementing these features, test the module thoroughly in a development environment to ensure that it works as expected. This involves simulating low stock conditions and verifying that notifications are generated correctly.

Deploying this system requires careful planning, especially in a production environment where inventory data is critical. Make sure to handle all edge cases and ensure that the notification system doesn’t introduce any performance bottlenecks.

TOOL # 2 – GEMINI

Prompt- Can you generate code In inventory management, there are data for many numbers of stocks, so if a stock level goes down from a particular level, the application should notify the user about it in Odoo 17?

Code-

SUMMARY

Replace ‘your.module’ with your actual module name and define the send_notification_func to handle sending the notification based on your needs.

This is a basic example. You might need to modify it based on your specific notification requirements and data structure.

This approach allows you to programmatically check stock levels and trigger notifications when they fall below a certain threshold. Remember to adapt the code to your specific Odoo environment and notification preferences.

TOOL # 3 – PERPLEXITY

Prompt- Can you generate code In inventory management, there are data for many numbers of stocks, so if a stock level goes down from a particular level, the application should notify the user about it in Odoo 17?

Code-

SUMMARY

This module will create a new field low_stock in the product.product model that is set to True when the qty_available field is less than the min_qty field. It also overrides the create method of the stock.move model to send a notification email when a new stock move is created for a product with low stock.

Note that this is just an example and you may need to customize it to fit your specific needs. Also, make sure to test it thoroughly before using it in a production environment.

TOOL # 4 – MICROSOFT COPILOT

Prompt – Can you generate code In inventory management, there are data for many numbers of stocks, so if a stock level goes down from a particular level, the application should notify the user about it in Odoo 17?

Code –

SUMMARY

This code snippet includes a new field in the product.template model to set a low stock threshold for each product. The StockQuant model is extended with a method to check stock levels against these thresholds and send an email notification if the stock is low. You would need to replace ‘your_module.your_email_template_id’ with the actual XML ID of your email template.

Remember to add this method to a scheduled action (cron job) in Odoo to run it periodically.

Please ensure to test this code in a development environment before deploying it to production, as it may need adjustments to fit your specific Odoo setup. 

TOOL # 5 – CLAUDE 3 OPUS

Prompt- Can you generate code In inventory management, there are data for many numbers of stocks, so if a stock level goes down from a particular level, the application should notify the user about it in Odoo 17?

Code –

SUMMARY

In this code,  We inherit the stock.move model to extend its functionality.

We override the create and write methods to trigger the stock level check whenever a stock move is created or updated.

In the _check_stock_level method, we iterate over the stock moves and check if the move is in the ‘done’ state, indicating that the stock has been moved.

For each moved product, we retrieve the current stock level using product.qty_available.

We define a minimum stock level (in this example, it’s set to 10, but you can adjust it according to your needs).

If the current stock level is below the minimum level, we create a notification using the mail.message model.

The notification includes a title and a message indicating the low stock level for the specific product.

We set the partner_ids to the current user’s partner ID to send the notification to the current user.

Finally, we associate the notification with the stock.move model and the specific move record using the model and res_id fields.

With this code, whenever a stock move is created or updated, and the resulting stock level goes below the specified minimum level, a notification will be sent to the user in Odoo 17.

Note : Make sure to replace the minimum stock level (minimum_level) with the appropriate value based on your business requirements.

TOOL # 6 – COHERE

Prompt – Can you generate code In inventory management, there are data for many numbers of stocks, so if a stock level goes down from a particular level, the application should notify the user about it in Odoo 17?

Code –

SUMMARY

First, we define a new model StockNotification to represent the stock level notification settings. It has the following fields :

product_id : A reference to the product for which we want to monitor the stock level.

location_id : The location where we want to track the stock level.

threshold_quantity : The minimum quantity below which a notification should be sent.

notify_email : The email address to which the notification should be sent.

We use an on change method _onchange_product_id to automatically set the location_id based on the selected product, assuming that each product has a default stock location.

The check_stock_level method is responsible for checking the stock levels and sending notifications if needed. It iterates over each record in the StockNotification model, retrieves the real quantity available (taking reservations into account) and compares it with the threshold quantity. If the real quantity is below the threshold, it calls the send_notification method to send an email notification.

The send_notification method constructs the email subject and body, and then uses the mail.compose.message model to send the email notification.

To use this code, you need to create records in the StockNotification model specifying the products, locations, threshold quantities and notification email addresses. Then, you can call the check_stock_level method to trigger the stock level checks and notifications.

This is just an example, and you can customize it further based on your specific requirements and Odoo version. Make sure to adapt the code to your needs and consider adding error handling, translations and other enhancements as necessary.

Each LLM tackles the task differently, offering a unique blend of features and complexity. 

While all achieve the core functionality, their approaches vary in :

1. Code Structure : Some (Gemini, Copilot) present easily modifiable code, while others (Perplexity) introduce new models.
2. Notification Methods : Email remains the primary choice (Copilot, Cohere), with Claude offering more flexibility.
3. User Focus : Claude stands out with detailed explanations, while others prioritize core functionality.

PICKING YOUR LLM CHAMPION

The ideal LLM depends on your specific needs. Here’s a quick guide :

• Need a solid foundation for customization? Choose Gemini.
• Prioritize a simple, new-field approach? Perplexity is your pick.
• Value clear explanations and user-friendliness? Claude’s your champion.
• Want email notifications and a practical solution? Copilot or Cohere fit the bill.

THE FINAL VERDICT

Our team’s in-depth testing across these LLMs has identified two frontrunners for building automated low-stock notification systems in Odoo 17 : Claude Opus 3 and GPT-4.

Claude Opus 3 shines with its user-friendly approach, providing clear explanations alongside well-structured code (great syntax!). This makes it ideal for developers seeking a documented and adaptable solution.

GPT-4, on the other hand, excels in robustness. Its focus on thorough testing and deployment considerations ensures a highly reliable solution – perfect for mission-critical functionalities.

Remember, though, each LLM has its strengths. Experiment and see which one aligns best with your Odoo development style!

Ready to Supercharge Your Odoo?

Pragmatic Techsoft offers a complete Odoo experience – from customization and migration to development, deployment, support and training.

Contact us today and let our Odoo experts help you unlock the full potential of your LLM-powered inventory management system!