Gooey.AI (Dara.network Inc)

EU DSA Bot

This bot helps people understand the EU DSA and how to best conduct audits.
https://www.eu-digital-services-act.com/
https://ec.europa.eu/info/law/better-regulation/have-your-say/initiatives/13626-Digital-Services-Act-conducting-independent-audits_en

Tweak this workflow to create customized chatbots from your own docs/PDF/webpages.

📝 Instructions

🧠 Language Model

GPT-4 Turbo (openai)

📄 Knowledge

Add documents or links to give your copilot a knowledge base. When asked a question, we'll search them to generate an answer with citations.

Submit Links in Bulk

💪 Capabilities

🦻 Speech Recognition & Translation

🗣️ Text to Speech & Lipsync

🩻 Photo & Document Intelligence

🧩 Developer Tools and Functions

⚙️ Settings

📄 Knowledge Base

👩‍🏫 Search Instructions

How should the LLM interpret the results from your knowledge base?

Citation Style

Plain Text / WhatsApp Symbols + Footnotes

🔗 Shorten Citation URLs

Create Synthetic Data

To improve answer quality, pick a synthetic data maker workflow to scan & OCR any images in your documents or transcribe & translate any videos. It also can synthesize a helpful FAQ. Adds ~2 minutes of one-time processing per file.

———

Advanced Settings

In general, you should not need to adjust these.

👁‍🗨 Conversation Summarization

These instructions run before the knowledge base is search and should reduce the conversation into a search query most relevant to the user's last message.

🔑 Keyword Extraction

Instructions to create a query for keyword/hybrid BM25 search. Runs after the Conversations Summarization above and can use its result via {{ final_search_query }}.

✏ Embeddings Model

Text Embedding 3 Large (OpenAI)

Dense Embeddings Weightage

Weightage for dense vs sparse embeddings. 0 for sparse, 1 for dense, 0.5 for equal weight.
Generally speaking, dense embeddings excel at understanding the context of the query, whereas sparse vectors excel at keyword matches.

Max Citations

The maximum number of document search citations.

Max Snippet Words

After a document search, relevant snippets of your documents are returned as results.
This setting adjusts the maximum number of words in each snippet (tokens = words * 2).
A high snippet size allows the LLM to access more information from your document results, at the cost of being verbose and potentially exhausting input tokens (which can cause a failure of the copilot to respond).

Snippet Overlap Ratio

Your knowledge base documents are split into overlapping snippets.
This settings adjusts how much those snippets overlap (overlap tokens = snippet tokens / overlap ratio).
In general you shouldn't need to adjust this.

🔠 Language Model Settings

Avoid Repetition

Response Format

———

Max Output Tokens

The maximum number of tokens to generate in the completion. Increase to generate longer responses.

Creativity (aka Sampling Temperature)

Higher values allow the LLM to take more risks. Try values larger than 1 for more creative applications or 0 to ensure that LLM gives the same answer when given the same user input.

Answer Outputs

How many answers should the copilot generate? Additional answer outputs increase the cost of each run.

Run cost = 4 credits

Breakdown: 1 (GPT-4 Turbo (openai)) + 3/run

By submitting, you agree to Gooey.AI's terms & privacy policy.

Show Raw Output

Assistant

According to the provided search result snippet, a dark pattern is described as a misleading interface. These are design practices aimed at deceiving or manipulating users into making choices they might not otherwise make, such as signing up for recurring subscriptions or sharing more personal information than necessary. The Digital Services Act bans such practices to protect users from being misled online [*] .

*. www.eu-digital-services-act.com https://www.eu-digital-services-act.com/

User
what's a dark pattern, according to these docs?

Assistant
The auditor plays a crucial role in the supervision of compliance for very large online platforms and search engines with their obligations under the DSA. Independent audits are an important tool in assessing providers' adherence to the DSA, and their findings can meaningfully inform regulatory supervision. Auditors are responsible for carrying out audits in an effective, efficient, timely, and comparable manner. They assess the compliance of these providers with the DSA and any commitments they have made under codes of conduct and crisis protocols. The auditors provide an independent assessment that enhances accountability by offering both the public and regulators insight into the providers' compliance with their obligations.

User
What roles does the auditor play?

Assistant
The Digital Services Act (DSA) is a regulation aimed at protecting the digital space from the spread of illegal content and safeguarding users' fundamental rights. It sets out obligations for online platforms and services, particularly focusing on large entities known as very large online platforms (VLOPs) and very large online search engines (VLOSEs), which are subject to stricter rules. The DSA requires platforms to be more transparent, holds them accountable for disseminating illegal and harmful content, combats the sale of illegal products online, and introduces measures against illegal content. It also protects minors from targeted advertising based on their personal data, imposes limits on advertising, bans dark patterns, and requires VLOPs and VLOSEs to offer non-profiling-based content recommendation systems and analyze systemic risks they may create.

User
What's the DSA about?

💁‍♀️ Sources

Generated in 6.9s on

...

ℹ️ Details

How to Use This Recipe

🙋🏽‍♀️ Need more help? Join our Discord