Description

An overview of relevant training datasets for RAG-style prompt generation and chaining:

• altinn-studio-docs repo or docs.altinn.studio website
• Altinn Studio Designer schema files (contains descriptive texts for objects and individual properties)
• Github Issues, Pull requests and Releases (contain valuable and up to date descriptions of changes made to Studio)
• Slack conversations (QA style conversations)

In scope

In a multi-query workflow, a single incoming query can be forwarded to multiple search backends and combined using techniques such as Reciprocal rank fusion

See also Ensemble Retriever

Pagesense support similarity and hybrid search within the same index, see Pagesense docs

Description

Identify and setup Azure resources needed to run Assistant-style AI apps for experimentation (not full production requirements)

Although initial costs are expected to be low due to intermittent use and no requirement for dedicated GPU resources, we need to develop a good understanding for how costs accrue for different approaches.

Potential dependency on #8

Description

Central to the definition of an Altinn 3 app are three well defined JSON schemas. JSON files conforming to these schemas are used to define data models, layouts and text translations.

Studio is a user friendly editing interface for these files, which are saved in a Git repository.

Our hypothesis is that Studio Assistant could be added to Studio with minimal integration effort and significant functional augmentation. Specifically, Studio Assistant can deliver functionality that would normally require significant effort to design a usable visual interface for.

In scope

Make a good list of useful prompts. Here are some ideas to get started:

Multiple edits

"Flytt adressefeltene til å være i en egen gruppe som heter 'Postadresse'"

"Endre de merkerte felt til å være påkrevd"

"Dupliser gruppenummer 2"

Queries

"Hvilke felt er påkrevd?"

Navigation

"Gå til neste felt som mangler oversettelse til nynorsk"

Out of scope

No response

Additional Information

No response

Tasks

No response

Description

Tried hosting blog articles on the Github wiki space included in our subscription, but it doesn't provide basic functionality such as ordering by blog post date or displaying posts in a navigation component.

Easiest option is to use a default blog theme for a static site generator such as Astro.

Additional Information

No response

Tasks

Description

Verify that our repositories are correctly configured to meet our unique file naming conventions.

https://docs.github.com/en/copilot/managing-copilot-business/configuring-content-exclusions-for-github-copilot

Additional Information

No response

Tasks

No response

Acceptance Criterias

No response

Description

Before attempting to fix specific quality issues related to the documentation training dataset, we should document them and perform a cost-benefit analysis together with the relevant teams.

Walk-through:
https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/create-resource?pivots=web-portal

Description

Ref:
Query relaxation and scoping
https://www.algolia.com/blog/ux/query-relaxation-and-scoping-as-part-of-semantic-search/

Small to big retrieval
https://www.youtube.com/watch?v=ihSiRrOUwmg

Include a reference to this nice introduction video, explaining RAG concepts:
https://www.youtube.com/watch?v=T-D1OfcDW1M

Name is just a suggestion, sure if "ai" is already used to indicate "application insights".

"assistant" could also be used to group several AI apps, without the "ai" designation.

Description

We have demands for delivering complete documentation in both norsk bokmål/nynorsk and english (DPG). Translating is time consuming for all teams.
Generate translated pages on commit and just mark them "AI translated" and/or let teams review the translations before published.

Additional Information

In my opinion this should be prioritized, and i could probablly be based on work alerady done with the assistant? Please advice? @altinnadmin @bdb-dd

Description

There are many examples of existing PDF and HTML forms across the Norwegian public service.

We should experiment and evaluate existing tools combined with new LLM-based techniques for interpreting existing form definitions and generating equivalent Altinn 3 apps.

In scope

Out of scope

Not ready for a full scale conversion effort until initial evaluation has been reviewed.

Additional Information

No response

Tasks

No response

Description

In order to facilitate safe and secure experimentation with machine learning practices, we need to prioritize defining initial guidelines and restrictions for training datasets, agent functionality scope, deployment and testing.

In scope

No response

Out of scope

No response

Additional Information

No response

Analysis

No response

Conclusion

No response

Description

There are several hundred Altinn II services (infopath forms) that need to be converted to Altinn 3 apps, prior to the phase-out of Altinn II.

A certain proportion of these require few or no changes (unchanged XSD data model), while others will need some "refurbishing". The hypothesis is that a lot of time can be saved if one can import the existing form as a starting point for further work.

The tool https://github.com/Altinn/altinn2-convert converts XSN files to Altinn 3 apps and handles data model, GUI (pages and elements), texts, bindings between data model and GUI, etc. For example, the Financial Supervisory Authority has tried converting all its approximately 120 services.

Additional Information

Expected challenges with importing from Infopath files (.CAB, zipped XSN files):

• Infopath files lack context between input fields and field description
• Fields appear in a different order than how they're defined in the code and the reason is unknown

Expected challenges with importing from PDF:

• "Conditional logic" can influence which field gets included in the PDF
• It's not certain that we have PDF files for all services (produced by download or completion?)

Description

In order to gain interoperability between different platforms and solutions, we need good metadata about the data used in a service. This job with data classification and populating the data catalogues on data.norge.no has been lagging behind for years.

Could a simple AI application feed on raw data an achieve a >80% coverage on a dataset in the data-catalogue that could raise coverage and data quality in order to stimulate to data-driven services in A3, and with a more runtime approach to the data-registries at data.norge.

As a starter this could be done with data managerd/owned by digdir that is not yet described in FDK. If the case is valid, this approach could be used in mapping and compiling other metadata-classes that we dont have general overview on like for instance processing of personal data (could be scraped from the "personvernærklæring"), in order to create cool personal data management applications.

Additional Information

https://data.norge.no/

Reports that may be relevant in the regard of this case:
https://www.regjeringen.no/contentassets/0e36c85fcfe143a5b626c53cf292cb3b/altinns-innspill-vedlegg-1---konseptet-digitale-meg-2019.07.05.pdf
https://www.digdir.no/datadeling/innsynslosning-tekniske-og-juridiske-muligheter/3465
https://www.digdir.no/digital-samhandling/konseptskisse-realisering-av-en-innbyggerorientert-digital-assistent/2949

Description

Propose a practical approach to improving the current documentation

Criteria:

• Assist developers in identifying the topics that are in most urgent need of improvement
• Assist developers in generating English documentation by creating LLM prompt templates for reference-style articles, how-to guides
• Add feedback channel for users to provide free text feedback on any documentation topic, anonymously.
• Identify need for "conditional content", content that applies to some subset of users. F.eks front-end or backend version specific, target audience specific (technical vs non-technical), language specific, etc.

Suggestions:

• Extract relevant information from related issues in Github

Additional Information

No response

Tasks

No response

Acceptance Criterias

No response