Message Threads | The Odoo Community Association

Re: Guidelines for LLM generated contributions

I agree with Daniel.

Blog posts (the second is linked in the first) inspiring me recently on this topic: https://www.bitecode.dev/p/the-kids-are-alright

Regards,

Pierre

Le mar. 23 sept. 2025 à 10:41, Stuart J Mackintosh <notifications@odoo-community.org> a écrit :

+1

On 23/09/2025 10:28, Daniel Reis wrote:
Hello all,

It begs the question of what is "AI generated code".
AI can assist code writing from code completion suggestions, to full design and code writing.
Or just assist with code reviews or issue resolution, without writing code.

In the end AI is just a tool.
Irresponsible use can happen with AI or any other automation tool.

What really matters is the behavior of people using these tools.
I feel that we might need a guideline regarding responsible use of automated tools, including AI, rather than specifically for AI use.
This could be fitted into a code of conduct for the community.

Thanks
Daniel

On 18/09/2025 08:41, Stefan Rijnhart wrote:
Dear all,

at least one contributor is planning again to flood the OCA projects 
with PRs for module migrations: https://github.com/OCA/web/issues/3285. 
This volume is likely made possible through automation, with an LLM 
generating the actual migration code (on top of, hopefully, a more 
deterministic tool like OCA's odoo-module-migrator).

Regardless of the volume and the submitter, if the submitter has 
reviewed, refined and tested the code generated by an LLM, this should 
not be a problem but as a reviewer I'd like to know what I can expect. 
Holger Brunn pointed out to me that in other projects, this may be 
covered by a demand in the guidelines to disclose LLM usage and its 
extend. For an example, see 
https://github.com/ghostty-org/ghostty/pull/8289/files.

I would very much like to see such an addition to the OCA guidelines. 
Additionally, I would like to suggest that the basic premise (the 
generated code is indeed first self-reviewed, refined and tested) is 
also made explicit, and that it is unacceptable to pass on reviewer 
comments to the LLM only to copy back the LLM's response (which has 
happened to me on one or two occassions).

Can I have a temperature check for your support for such an addition to 
the guidelines? Or do you have other ideas or perspectives on the matter?

Cheers,
Stefan



-- 
Opener B.V. - Business solutions driven by open source collaboration

Stefan Rijnhart - Consultant/developer

mail:stefan@opener.amsterdam
tel: +31 (0) 6 1447 8606
web:https://opener.amsterdam
_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe
--

DANIEL REIS
MANAGING PARTNER
>> Schedule time on my calendar.
M: +351 919 991 307
E: dreis@OpenSourceIntegrators.com
A: Avenida da República 3000, Estoril Office Center, 2649-517 Cascais
_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe
--

Stuart J Mackintosh

Business & digital technology consultant

Open Digital Consulting Co

UK: +44 20 36 27 90 40

FR: +33 1 89 48 00 40

Email: sjm@opendigital.cc

Web: https://opendigital.cc

IM: xmpp:sjm@opendigital.cc
_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

by Pierre Verkest - 09:51 - 23 Sep 2025

Re: Guidelines for LLM generated contributions

+1

On 23/09/2025 10:28, Daniel Reis wrote:

Hello all,

It begs the question of what is "AI generated code".
AI can assist code writing from code completion suggestions, to full design and code writing.
Or just assist with code reviews or issue resolution, without writing code.

In the end AI is just a tool.
Irresponsible use can happen with AI or any other automation tool.

What really matters is the behavior of people using these tools.
I feel that we might need a guideline regarding responsible use of automated tools, including AI, rather than specifically for AI use.
This could be fitted into a code of conduct for the community.

Thanks
Daniel

On 18/09/2025 08:41, Stefan Rijnhart wrote:
Dear all,

at least one contributor is planning again to flood the OCA projects 
with PRs for module migrations: https://github.com/OCA/web/issues/3285. 
This volume is likely made possible through automation, with an LLM 
generating the actual migration code (on top of, hopefully, a more 
deterministic tool like OCA's odoo-module-migrator).

Regardless of the volume and the submitter, if the submitter has 
reviewed, refined and tested the code generated by an LLM, this should 
not be a problem but as a reviewer I'd like to know what I can expect. 
Holger Brunn pointed out to me that in other projects, this may be 
covered by a demand in the guidelines to disclose LLM usage and its 
extend. For an example, see 
https://github.com/ghostty-org/ghostty/pull/8289/files.

I would very much like to see such an addition to the OCA guidelines. 
Additionally, I would like to suggest that the basic premise (the 
generated code is indeed first self-reviewed, refined and tested) is 
also made explicit, and that it is unacceptable to pass on reviewer 
comments to the LLM only to copy back the LLM's response (which has 
happened to me on one or two occassions).

Can I have a temperature check for your support for such an addition to 
the guidelines? Or do you have other ideas or perspectives on the matter?

Cheers,
Stefan


-- 
Opener B.V. - Business solutions driven by open source collaboration

Stefan Rijnhart - Consultant/developer

mail:stefan@opener.amsterdam
tel: +31 (0) 6 1447 8606
web:https://opener.amsterdam
_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe
--

DANIEL REIS
MANAGING PARTNER
>> Schedule time on my calendar.
M: +351 919 991 307
E: dreis@OpenSourceIntegrators.com
A: Avenida da República 3000, Estoril Office Center, 2649-517 Cascais
_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

--

Stuart J Mackintosh

Business & digital technology consultant

Open Digital Consulting Co

Open Digital Consulting Co Logo

UK: +44 20 36 27 90 40

FR: +33 1 89 48 00 40

Email: sjm@opendigital.cc

Web: https://opendigital.cc

IM: xmpp:sjm@opendigital.cc

by Stuart J Mackintosh - 10:40 - 23 Sep 2025

1 attachments 1 attachments

Re: Guidelines for LLM generated contributions

Hello all,

It begs the question of what is "AI generated code".
AI can assist code writing from code completion suggestions, to full design and code writing.
Or just assist with code reviews or issue resolution, without writing code.

In the end AI is just a tool.
Irresponsible use can happen with AI or any other automation tool.

What really matters is the behavior of people using these tools.
I feel that we might need a guideline regarding responsible use of automated tools, including AI, rather than specifically for AI use.
This could be fitted into a code of conduct for the community.

Thanks
Daniel

On 18/09/2025 08:41, Stefan Rijnhart wrote:

Dear all,

at least one contributor is planning again to flood the OCA projects 
with PRs for module migrations: https://github.com/OCA/web/issues/3285. 
This volume is likely made possible through automation, with an LLM 
generating the actual migration code (on top of, hopefully, a more 
deterministic tool like OCA's odoo-module-migrator).

Regardless of the volume and the submitter, if the submitter has 
reviewed, refined and tested the code generated by an LLM, this should 
not be a problem but as a reviewer I'd like to know what I can expect. 
Holger Brunn pointed out to me that in other projects, this may be 
covered by a demand in the guidelines to disclose LLM usage and its 
extend. For an example, see 
https://github.com/ghostty-org/ghostty/pull/8289/files.

I would very much like to see such an addition to the OCA guidelines. 
Additionally, I would like to suggest that the basic premise (the 
generated code is indeed first self-reviewed, refined and tested) is 
also made explicit, and that it is unacceptable to pass on reviewer 
comments to the LLM only to copy back the LLM's response (which has 
happened to me on one or two occassions).

Can I have a temperature check for your support for such an addition to 
the guidelines? Or do you have other ideas or perspectives on the matter?

Cheers,
Stefan


-- 
Opener B.V. - Business solutions driven by open source collaboration

Stefan Rijnhart - Consultant/developer

mail:stefan@opener.amsterdam
tel: +31 (0) 6 1447 8606
web:https://opener.amsterdam

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

--

DANIEL REIS
MANAGING PARTNER

>> Schedule time on my calendar.
M: +351 919 991 307
E: dreis@OpenSourceIntegrators.com
A: Avenida da República 3000, Estoril Office Center, 2649-517 Cascais

by Daniel Reis - 10:26 - 23 Sep 2025

Re: OCA Days 2025 Streaming

Hi Rebecca,

Thank you for the information regarding the OCA Days Streaming. I have a few questions:

Why is it being uploaded to Twitch? As far as I remember, it will be deleted within 1-2 months.
Why are there multiple accounts like odoocommunity1, 2, and 3?
Are there any plans to upload these to YouTube?

On Tue, Sep 16, 2025 at 4:22 PM Rebecca Gellatly <rebecca@odoo-community.org> wrote:

Hi all,

Here are the links to the OCA Days Streaming:

odoocommunity1 => Mosane 5+6
odoocommunity2 => Mosane 2+3
odoocommunity3 => Mosane 7+8+9

Here is the agenda:
https://odoo-community.org/event/oca-days-2025-liege-2025-09-15-2025-09-18-174/agenda

Have a great day,
Rebecca
--
Rebecca Gellatly
General Secretary
Odoo Community Association

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

--

Thank and Regards

IB Teguh TM

about.me/teguhteja

by IB Teguh TM - 04:00 - 20 Sep 2025

Re: Guidelines for LLM generated contributions

On Fri, Sep 19, 2025, 5:22 AM Matthieu Mequignon <notifications@odoo-community.org> wrote:

Hi!

While I understand the concern and the need for compromise here (because I know this is going to happen, no matter what is decided), I'm gonna be «this guy»: I am totally against LLM generated contributions.

Regarding migrations, we already have great tools to facilitate developments, such as oca-port doing migrations in seconds.
I would be ok with community scripts doing the boring/automated changes, such as `tree` -> `list`, `_` -> `self.env._` etc…
From there, the remaining work is the hardest, and LLM can (at best) only assist.

The point is LLMs such as Claude

-Code or Gemini-CLI now use tools like bash tools. So you can instruct them to run oca-port as the start and do the remaing code adjustments to run the tests and even get the pre-commit green. So it'not anyone about using an LLMs alone.

You can also feed the AI context with OpenUpgrade analysis and scripts, the migration diffs of the dependency modules migrations and diffs such as

https://github.com/akretion/odoo-module-diff-analysis/tree/main

So at the end the LLM will have plenty of migration context and can do A LOT extremely fast.

I would say more and more that's you that will assist the AI and not the reverse...

About basic functional knowledge: well may be it's hard to admit but they have more functional ERP knowledge out of the box than most of Odoo developpers have...

And when you feed the LLM with the OCA code before aksing in the prompt, it can quickly "understand" what the code does. I would say the module authors still beat it, but if you are not the author/main contributor, chances are the LLM will "understand" the modules details quicker than you (disclaimer: you really need to pass the module code and its dependencies to the LLM for this go happen though otherwise yes you get mostly hallucinations).

About installing, screenshots etc: AI such as Gemini-CLI can run inside a Github action were Odoo is installed exactly like the OCA CI is. At the moment I run it in a virtualenv were I have my Odoo installed and it can run pytest-odoo untill it makes tests passes. I woukd say it's a matter of just a few months/weeks before we can have the screenshots of the changes from the LLM+tools directly (people using popular stacks like react have it already).

But meanwhile full human control and responsability is what I advocated for.

Also Gemini-CLI tends to work better than Claude Code because the Odoo codebase is huge so if you don't want the LLM to hallucinate you need to feed its context window with all the relevant Odoo/OCA code required. And with 1 millions tokens Gemini beats Claude and most other AI by a faire margin for Odoo. (Claude is only 256k tokens and just account/models from odoo/odoo will consume 350k tokens and max it out). I'll talk more about that in another thread.

At the end yes I think we should forbid lazy AI made PRs by people who just ask anything to chatGPT or similar tools without any testing/critical thinking.

But my point is: an OCA specialist with an LLM will do 10x more than what he does today with AI help and the same quality or better (yes it already really writes better code than you for the 50% of the easy code).

So when the entire industry is making the shift, when our customers will not expect you quote them 5 days for something that could now be done in 1 day, when they will not want to use an Odoo version lagging 2 or 3 versions behind and getting exponentially better, we will have to use AI or die. Like mechanical engineering now use computer simulation instead of only human calculus on sheets of paper.

In this context, it's easy to claim AI will not do it as good and boycott it entirely. But sadly that's simply not true.

Finally, about all the ethical and energy issues raised in other answers, yes I agree this is absolutely a major concern. I think we should act politically regarding this if it is even possible to avoid people would do the bad things and submit you from other countries/juridictions.

by Raphaël Akretion - 02:41 - 19 Sep 2025

Beyond LLM guidelines and generated contributions

Hi everybody,

First, thank you for the great time at the OCA Days and I hope you are enjoying the OXP.

The ongoing discussion on LLM guidelines ~~had me triggered~~ got me thinking.

I would like to give a different perspective on LLMs and what we as a community should care about.

Let's talk about digital sovereignty and power-consumption. Most LLMs used by developers made by big tech companies [0]. These companies have built huge data centers that use an incredible amount of power to run LLMs. They have plans to build nuclear reactors to support the power demand. Anyone who is seriously concerned with digital sovereignty and cares about the environment knows that we need to become independent of big tech and use less energy.

> Supporting AI tools by big tech is a step into the wrong direction.

Moreover, the AI hype is igniting the next level of data collecting and user tracking. The data we generate when interacting with an AI chat and the like is incredibly valuable. As of now the tech bros still have no viable business model and burn money at an incredible amount [1].

Every week a new model is released and we feel pressured to use AI. Let us take a break and take it slow moving forward. We are not forced to do anything (at least for now).

I ask the OCA members to do better than creating an OpenAI account, installing Claude desktop or click the Copilot icon. Use tools and create workflows that respect your privacy and the privacy of others. Make sure your stack uses less energy over time, works independent and is controllable.

> Let us create guides on how to do better.

Here is an example, not show off, but simply to share:
The LLMs I am using are hosted by Infomaniak in Switzerland [2]. They are using "green" energy. I pay per token and I know where the data is stored. On the command line, I am using the LLM cli [3] by Simon Willison (LLM reseacher). Every LLM tool that supports the OpenAI API standard can be connected to an Infomaniak LLM. There are great scripts that help your write better code [4]. I don't have any kind of IDE integration [5]. I like to write code and not press tab tab tab ...

Is somebody interested to create guides on how to work (better) with LLMs and create contributions that help the ecosystem?

Kind regards,

Janik

[0]: https://en.wikipedia.org/wiki/Big_Tech
[1]: https://www.wheresyoured.at/the-haters-gui/
[2]: https://www.infomaniak.com/en/hosting/ai-tools
[3]: https://llm.datasette.io/
[4]: https://notes.billmill.org/blog/2025/07/An_AI_tool_I_find_useful.html
[5]: https://janikvonrotz.ch/2025/01/27/work-with-llms-on-the-command-line/

by Janik von Rotz - 11:05 - 19 Sep 2025

Re: Guidelines for LLM generated contributions

Hi!

While I understand the concern and the need for compromise here (because I know this is going to happen, no matter what is decided), I'm gonna be «this guy»: I am totally against LLM generated contributions.

Regarding migrations, we already have great tools to facilitate developments, such as oca-port doing migrations in seconds.
I would be ok with community scripts doing the boring/automated changes, such as `tree` -> `list`, `_` -> `self.env._` etc…
From there, the remaining work is the hardest, and LLM can (at best) only assist.

Now regarding contribution, in my opinion LLM lacks what I believe is the bare minimum to be able to contribute.
For any change at all, I would expect thorough testing, screenshots or whatever.
It requires to install, configure, set up an odoo instance, which requires basic knowledge of functional processes...
And if this doesn't work, we need to adapt the code until it works, and ensure we do not introduce a regression somewhere else.
Again, this is the long and complicated part to any contribution, and LLM only can assist.

I'm in favor of this flag, so I can filter out the ones to not review.

Regards,

(sorry for the bluntiness, but I really believe AI has its uses, and that this shouldn't be one)

Le 18/09/2025 à 09:42, Stefan Rijnhart a écrit :

Dear all,

at least one contributor is planning again to flood the OCA projects 
with PRs for module migrations: https://github.com/OCA/web/issues/3285. 
This volume is likely made possible through automation, with an LLM 
generating the actual migration code (on top of, hopefully, a more 
deterministic tool like OCA's odoo-module-migrator).

Regardless of the volume and the submitter, if the submitter has 
reviewed, refined and tested the code generated by an LLM, this should 
not be a problem but as a reviewer I'd like to know what I can expect. 
Holger Brunn pointed out to me that in other projects, this may be 
covered by a demand in the guidelines to disclose LLM usage and its 
extend. For an example, see 
https://github.com/ghostty-org/ghostty/pull/8289/files.

I would very much like to see such an addition to the OCA guidelines. 
Additionally, I would like to suggest that the basic premise (the 
generated code is indeed first self-reviewed, refined and tested) is 
also made explicit, and that it is unacceptable to pass on reviewer 
comments to the LLM only to copy back the LLM's response (which has 
happened to me on one or two occassions).

Can I have a temperature check for your support for such an addition to 
the guidelines? Or do you have other ideas or perspectives on the matter?

Cheers,
Stefan


-- 
Opener B.V. - Business solutions driven by open source collaboration

Stefan Rijnhart - Consultant/developer

mail:stefan@opener.amsterdam
tel: +31 (0) 6 1447 8606
web:https://opener.amsterdam

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

-- 
Matthieu Méquignon

+33 6 19 22 76 99

by Matthieu Méquignon - 10:21 - 19 Sep 2025

Re: Integration of knowledge or dms with onlyoffice ?

Hi Cyril, Hi Bruno,

we have integrated onlyoffice since a long time in our dms - which is based on alfrsco and use it also in odoo. We are also aware of onlyoffics odoo ee integration.

We can have a talk tomorow, if you like to on the OCA booth (Hall 11 / Stand 5) if youre intrested.

Best

Chris

Von: Cyril <notifications@odoo-community.org>
An: Contributors <contributors@odoo-community.org>
Datum: Donnerstag, 18. September 2025 17:27 CEST
Betreff: Re: Integration of knowledge or dms with onlyoffice ?

Hi Bruno

What I saw on their demo is a direct integration of what you could find in a drive (spreadsheet, slides, docs...) in enterprise documents module. It looks like you can edit it in odoo UI.

(I can go back tomorrow check it again)

Then I had the idea of integrating the same functionality in OCA's document_page or dms...

--------------------------------
Cyril VINH-TUNG
INVITU
Computer & Network Engineering
BP 32 - 98713 Papeete - French Polynesia
Tél: +689 40 46 11 99
contact@invitu.com
www.invitu.com

Le jeu. 18 sept. 2025, 16:32, Bruno Joliveau <notifications@odoo-community.org> a écrit :

Hi Cyril,

Could you elaborate "I was wondering if we could have the same with knowledge and/or dms." please ?

DMS and Knowledge from Odoo Apps or others ?

Bruno Joliveau

Architecte solutions - Président

+1 514-317-7944

Nouveau
Votre avis est important pour nous ⭐ Découvrir

Le jeu. 18 sept. 2025 à 10:22, Cyril VINH-TUNG <notifications@odoo-community.org> a écrit :

Hello

At oxp, I met https://www.onlyoffice.com/ who developped a connector with odoo's document app...

https://github.com/ONLYOFFICE/onlyoffice_odoo

AFAIK it's LGPL and they run infomaniak Kdrive

I was wondering if we could have the same with knowledge and/or dms.

WDYT ?

Best regards

--------------------------------
Cyril VINH-TUNG
INVITU
Computer & Network Engineering
BP 32 - 98713 Papeete - French Polynesia
Tél: +689 40 46 11 99
contact@invitu.com
www.invitu.com

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

by Chris Lorenz - 08:36 - 18 Sep 2025

Re: Integration of knowledge or dms with onlyoffice ?

You need a running OnlyOffice Document Server to provide the online editor — not a big deal, but worth mentioning.
The integration works quite well. One of my customers is using it on a daily basis. Unfortunately, there is no built-in document revisioning, as far as I know. I submitted a feature request for this a while ago.

I might be wrong, but integration with a DMS shouldn’t be a problem, since OnlyOffice works on a temporary copy of the original file.

I'll give it a try...

Von: Cyril VINH-TUNG <notifications@odoo-community.org>
Gesendet: Thursday, September 18, 2025 4:22:32 PM
An: Contributors <contributors@odoo-community.org>
Betreff: Integration of knowledge or dms with onlyoffice ?

ACHTUNG! Diese E-Mail stammt von außerhalb der Organisation. Klicken Sie nicht auf Links und öffnen Sie keine Anhänge, es sei denn, Sie kennen den Absender und wissen, dass der Inhalt sicher ist.

Hello

At oxp, I met https://www.onlyoffice.com/ who developped a connector with odoo's document app...

https://github.com/ONLYOFFICE/onlyoffice_odoo

AFAIK it's LGPL and they run infomaniak Kdrive

I was wondering if we could have the same with knowledge and/or dms.

WDYT ?

Best regards

--------------------------------
Cyril VINH-TUNG
INVITU
Computer & Network Engineering
BP 32 - 98713 Papeete - French Polynesia
Tél: +689 40 46 11 99
contact@invitu.com
www.invitu.com

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

by Nils Coenen - 06:46 - 18 Sep 2025

Re: Integration of knowledge or dms with onlyoffice ?

Hi Bruno

What I saw on their demo is a direct integration of what you could find in a drive (spreadsheet, slides, docs...) in enterprise documents module. It looks like you can edit it in odoo UI.

(I can go back tomorrow check it again)

Then I had the idea of integrating the same functionality in OCA's document_page or dms...

--------------------------------
Cyril VINH-TUNG
INVITU
Computer & Network Engineering
BP 32 - 98713 Papeete - French Polynesia
Tél: +689 40 46 11 99
contact@invitu.com
www.invitu.com

Le jeu. 18 sept. 2025, 16:32, Bruno Joliveau <notifications@odoo-community.org> a écrit :

Hi Cyril,

Could you elaborate "I was wondering if we could have the same with knowledge and/or dms." please ?

DMS and Knowledge from Odoo Apps or others ?

Bruno Joliveau

Architecte solutions - Président

+1 514-317-7944

Nouveau
Votre avis est important pour nous ⭐ Découvrir

Le jeu. 18 sept. 2025 à 10:22, Cyril VINH-TUNG <notifications@odoo-community.org> a écrit :
Hello

At oxp, I met https://www.onlyoffice.com/ who developped a connector with odoo's document app...
https://github.com/ONLYOFFICE/onlyoffice_odoo

AFAIK it's LGPL and they run infomaniak Kdrive

I was wondering if we could have the same with knowledge and/or dms.

WDYT ?

Best regards

--------------------------------
Cyril VINH-TUNG
INVITU
Computer & Network Engineering
BP 32 - 98713 Papeete - French Polynesia
Tél: +689 40 46 11 99
contact@invitu.com
www.invitu.com

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

by Cyril VINH-TUNG - 05:26 - 18 Sep 2025

Re: Integration of knowledge or dms with onlyoffice ?

Hi Cyril,

Could you elaborate "I was wondering if we could have the same with knowledge and/or dms." please ?

DMS and Knowledge from Odoo Apps or others ?

Bruno Joliveau

Architecte solutions - Président

+1 514-317-7944

Nouveau
Votre avis est important pour nous ⭐

Découvrir

Le jeu. 18 sept. 2025 à 10:22, Cyril VINH-TUNG <notifications@odoo-community.org> a écrit :

Hello

At oxp, I met https://www.onlyoffice.com/ who developped a connector with odoo's document app...
https://github.com/ONLYOFFICE/onlyoffice_odoo

AFAIK it's LGPL and they run infomaniak Kdrive

I was wondering if we could have the same with knowledge and/or dms.

WDYT ?

Best regards

--------------------------------
Cyril VINH-TUNG
INVITU
Computer & Network Engineering
BP 32 - 98713 Papeete - French Polynesia
Tél: +689 40 46 11 99
contact@invitu.com
www.invitu.com

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

by Bruno Joliveau - 04:30 - 18 Sep 2025

Integration of knowledge or dms with onlyoffice ?

Hello

At oxp, I met https://www.onlyoffice.com/ who developped a connector with odoo's document app...

https://github.com/ONLYOFFICE/onlyoffice_odoo

AFAIK it's LGPL and they run infomaniak Kdrive

I was wondering if we could have the same with knowledge and/or dms.

WDYT ?

Best regards

--------------------------------
Cyril VINH-TUNG
INVITU
Computer & Network Engineering
BP 32 - 98713 Papeete - French Polynesia
Tél: +689 40 46 11 99
contact@invitu.com
www.invitu.com

by Cyril VINH-TUNG - 04:20 - 18 Sep 2025

Re: Guidelines for LLM generated contributions

+1000 with Raphael

Bruno Joliveau

Architecte solutions - Président

+1 514-317-7944

Nouveau
Votre avis est important pour nous ⭐

Découvrir

Le jeu. 18 sept. 2025 à 09:22, Maxime Chambreuil <notifications@odoo-community.org> a écrit :

Totally agree with Raphael here.

MAXIME CHAMBREUIL
DIRECTOR INTERNACIONAL

T: +52 (800) 953-2012 #5200
M: +52 (442) 114-9164 | WhatsApp
C: MChambreuil@OpenSourceIntegrators.com

Av. Antea 1032, Piso 4 Local 8, Colonia Jurica
Santiago de Querétaro, Querétaro, 76100, México

Analizar. Optimizar. Automatizar. Transicionar.

Reservar un momento para reunirse conmigo

De: Raphaël Valyi <notifications@odoo-community.org>
Enviado: jueves, 18 de septiembre de 2025 5:36 a. m.
Para: Contributors <contributors@odoo-community.org>
Asunto: Re: Guidelines for LLM generated contributions

This an extremely important topic as AI is completely changing software development in a matter of weeks.

Of course we should require human contributors to do their correction job before submitting the PR. They can run the CI in their organization 1st, it's easy. May be we should explain how in the migration wiki or contributing.md ?

I woukd say yes it's also important to tell AI has been used and at the same time I'm sure in just a few months the vast majority of us will be using some AI in their PR or will be left behind. So soon enough then telling your PR is using AI will be the noise and not the signal...

There is a positive side: in less than 1 year (may be just 6 months) I think 50% of the modules will be able to be migrated automatically with AI and meet all checks. The same will also be probably true for OpenUpgrade.

This will allow us to use the bleeding edge Odoo with all the ecosystem and free us for more interesting work than migration. At some point this is our chance for not getting distanced by Odoo Enterprise.

This raises other concerns: what will be a valid contributors.md or authors.md entry? How will the OCA keep being organized as a meritocracy when the contributions made will soon enough mostly translate to the amount of compute used? How long before AI will claim PSCs?

May be we should also have repo to build these AI migration or review bots? I did some tools already and will tell about them soon... Reach me personally meanwhile if you are interested.

I see many people in the OCA in the denial phase who think AI is just a hype and or just for toy code. There is definitely a hype bubble and It is not able to do the hardest code today but it already beats you at the 50% of the easiest code you write and it is not going to stop any time soon...

This is really such an important topic...

And BTW I believe this will bring dystopia and not abundance. But can we even avoid it?

On Thu, Sep 18, 2025, 6:22 AM Graeme Gellatly <notifications@odoo-community.org> wrote:

I actually just completed a course in ai governance and ethics. It was finance focused as requirement for being an accountant, but declaring usage of llm in generating any professional services output is the very bare minimum. Human review was a mandatory part of governance, but honestly there was like 50 things there.

E.g This PR was generated using x llm and reviewed by a human for correctness prior to submission.

Le jeu. 18 sept. 2025, 21:12, Tom Blauwendraat <notifications@odoo-community.org> a écrit :

Thinking a bit out of the box here, but what might perhaps work is if:

- We set up a separate organisation OCA-ai
- This mirrors the full OCA organization as a fork, similar to odoo vs OCB
- If something looks like AI we close and tell contributors to reopen it there (could possibly be automated with the OCA bot if we can recognize something as AI)
- In that organisation we require 100% test coverage and passing tests, as well as the standard migration process having been followed (could be automated)
- If the bot decides there that it is OK, it automatically reopens the PR to the real OCA organization (where we thus only get "prefiltered" PRs)

In the absence of such automation I +1 Stefan's suggestion of adding a guideline

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

by Bruno Joliveau - 03:45 - 18 Sep 2025

Re: Guidelines for LLM generated contributions

Totally agree with Raphael here.

MAXIME CHAMBREUIL
DIRECTOR INTERNACIONAL

T: +52 (800) 953-2012 #5200
M: +52 (442) 114-9164 | WhatsApp
C: MChambreuil@OpenSourceIntegrators.com

Av. Antea 1032, Piso 4 Local 8, Colonia Jurica
Santiago de Querétaro, Querétaro, 76100, México

Analizar. Optimizar. Automatizar. Transicionar.

Reservar un momento para reunirse conmigo

De: Raphaël Valyi <notifications@odoo-community.org>
Enviado: jueves, 18 de septiembre de 2025 5:36 a. m.
Para: Contributors <contributors@odoo-community.org>
Asunto: Re: Guidelines for LLM generated contributions

This an extremely important topic as AI is completely changing software development in a matter of weeks.

Of course we should require human contributors to do their correction job before submitting the PR. They can run the CI in their organization 1st, it's easy. May be we should explain how in the migration wiki or contributing.md ?

I woukd say yes it's also important to tell AI has been used and at the same time I'm sure in just a few months the vast majority of us will be using some AI in their PR or will be left behind. So soon enough then telling your PR is using AI will be the noise and not the signal...

There is a positive side: in less than 1 year (may be just 6 months) I think 50% of the modules will be able to be migrated automatically with AI and meet all checks. The same will also be probably true for OpenUpgrade.

This will allow us to use the bleeding edge Odoo with all the ecosystem and free us for more interesting work than migration. At some point this is our chance for not getting distanced by Odoo Enterprise.

This raises other concerns: what will be a valid contributors.md or authors.md entry? How will the OCA keep being organized as a meritocracy when the contributions made will soon enough mostly translate to the amount of compute used? How long before AI will claim PSCs?

May be we should also have repo to build these AI migration or review bots? I did some tools already and will tell about them soon... Reach me personally meanwhile if you are interested.

I see many people in the OCA in the denial phase who think AI is just a hype and or just for toy code. There is definitely a hype bubble and It is not able to do the hardest code today but it already beats you at the 50% of the easiest code you write and it is not going to stop any time soon...

This is really such an important topic...

And BTW I believe this will bring dystopia and not abundance. But can we even avoid it?

On Thu, Sep 18, 2025, 6:22 AM Graeme Gellatly <notifications@odoo-community.org> wrote:

I actually just completed a course in ai governance and ethics. It was finance focused as requirement for being an accountant, but declaring usage of llm in generating any professional services output is the very bare minimum. Human review was a mandatory part of governance, but honestly there was like 50 things there.

E.g This PR was generated using x llm and reviewed by a human for correctness prior to submission.

Le jeu. 18 sept. 2025, 21:12, Tom Blauwendraat <notifications@odoo-community.org> a écrit :

Thinking a bit out of the box here, but what might perhaps work is if:

- We set up a separate organisation OCA-ai
- This mirrors the full OCA organization as a fork, similar to odoo vs OCB
- If something looks like AI we close and tell contributors to reopen it there (could possibly be automated with the OCA bot if we can recognize something as AI)
- In that organisation we require 100% test coverage and passing tests, as well as the standard migration process having been followed (could be automated)
- If the bot decides there that it is OK, it automatically reopens the PR to the real OCA organization (where we thus only get "prefiltered" PRs)

In the absence of such automation I +1 Stefan's suggestion of adding a guideline

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

by Maxime Chambreuil - 03:21 - 18 Sep 2025

1 attachments 1 attachments

Re: Guidelines for LLM generated contributions

Hello

I'm afraid to agree with Raphael...

About what I've learned from my very small experience with AI, it's that we will have to learn how to work with it instead of trying to fight against it

My 1 cent

--------------------------------
Cyril VINH-TUNG
INVITU
Computer & Network Engineering
BP 32 - 98713 Papeete - French Polynesia
Tél: +689 40 46 11 99
contact@invitu.com
www.invitu.com

Le jeu. 18 sept. 2025, 13:36, Raphaël Valyi <notifications@odoo-community.org> a écrit :

This an extremely important topic as AI is completely changing software development in a matter of weeks.

Of course we should require human contributors to do their correction job before submitting the PR. They can run the CI in their organization 1st, it's easy. May be we should explain how in the migration wiki or contributing.md ?

I woukd say yes it's also important to tell AI has been used and at the same time I'm sure in just a few months the vast majority of us will be using some AI in their PR or will be left behind. So soon enough then telling your PR is using AI will be the noise and not the signal...

There is a positive side: in less than 1 year (may be just 6 months) I think 50% of the modules will be able to be migrated automatically with AI and meet all checks. The same will also be probably true for OpenUpgrade.

This will allow us to use the bleeding edge Odoo with all the ecosystem and free us for more interesting work than migration. At some point this is our chance for not getting distanced by Odoo Enterprise.

This raises other concerns: what will be a valid contributors.md or authors.md entry? How will the OCA keep being organized as a meritocracy when the contributions made will soon enough mostly translate to the amount of compute used? How long before AI will claim PSCs?

May be we should also have repo to build these AI migration or review bots? I did some tools already and will tell about them soon... Reach me personally meanwhile if you are interested.

I see many people in the OCA in the denial phase who think AI is just a hype and or just for toy code. There is definitely a hype bubble and It is not able to do the hardest code today but it already beats you at the 50% of the easiest code you write and it is not going to stop any time soon...

This is really such an important topic...
And BTW I believe this will bring dystopia and not abundance. But can we even avoid it?

On Thu, Sep 18, 2025, 6:22 AM Graeme Gellatly <notifications@odoo-community.org> wrote:
I actually just completed a course in ai governance and ethics. It was finance focused as requirement for being an accountant, but declaring usage of llm in generating any professional services output is the very bare minimum. Human review was a mandatory part of governance, but honestly there was like 50 things there.

E.g This PR was generated using x llm and reviewed by a human for correctness prior to submission.

Le jeu. 18 sept. 2025, 21:12, Tom Blauwendraat <notifications@odoo-community.org> a écrit :
Thinking a bit out of the box here, but what might perhaps work is if:

- We set up a separate organisation OCA-ai
- This mirrors the full OCA organization as a fork, similar to odoo vs OCB
- If something looks like AI we close and tell contributors to reopen it there (could possibly be automated with the OCA bot if we can recognize something as AI)
- In that organisation we require 100% test coverage and passing tests, as well as the standard migration process having been followed (could be automated)
- If the bot decides there that it is OK, it automatically reopens the PR to the real OCA organization (where we thus only get "prefiltered" PRs)

In the absence of such automation I +1 Stefan's suggestion of adding a guideline

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

_______________________________________________
Mailing-List: https://odoo-community.org/groups/contributors-15
Post to: mailto:contributors@odoo-community.org
Unsubscribe: https://odoo-community.org/groups?unsubscribe

by Cyril VINH-TUNG - 03:11 - 18 Sep 2025