Ever wondered how Notion Ask AI works?

Notion is hot right now. So many companies are using it.

Here's a glimpse into the architecture of a real-world RAG system:

1. Notion receives a question from a user.

2. The question is passed to an LLM provider (OpenAI / Anthropic)

• If the request does not require searching the Notion workspace, the LLM generates a response at this point, skipping the rest of the process.
• If the user's request requires searching their workspace, the LLM generates the most relevant search query for the user's request.

3. The query is passed to a vector database (Pinecone), which identifies a list of pages based on their relevance to the query.

• For each page in the Notion workspace, an embedding is generated using the OpenAI embeddings API.

4. Notion sends the query — along with the pages identified by the vector database — to a self-hosted LLM, where the pages are refined and ranked by relevance to the query.

5. The query, refined list of pages, and page rankings are processed by the LLM provider to generate a response that fulfills the user's request.

6. Notion processes the output to ensure it adheres to the right format and language, then displays it to the user.

Author

AiUTOMATING PEOPLE, ABN ASIA was founded by people with deep roots in academia, with work experience in the US, Holland, Hungary, Japan, South Korea, Singapore, and Vietnam. ABN Asia is where academia and technology meet opportunity. With our cutting-edge solutions and competent software development services, we're helping businesses level up and take on the global scene. Our commitment: Faster. Better. More reliable. In most cases: Cheaper as well.

Feel free to reach out to us whenever you require IT services, digital consulting, off-the-shelf software solutions, or if you'd like to send us requests for proposals (RFPs). You can contact us at [email protected]. We're ready to assist you with all your technology needs.

© ABN ASIA