Notion
What is a Notion data loader node?
Node in Stack AI
Notion is a cloud-based productivity and collaboration all in-one workspace tool, where users write, add external content (e.g., URLs, images, videos, code, etc.) and organize their content in pages. Notion is a great tool to organize your knowledge base, and it is also a great tool to extract information from.
In Stack AI, you can connect your Notion knowledge base by using this node and linking it to an existing account.
How to use it?
How to connect with other nodes
This node outputs all the information from the connected page, as opposed to the Notion node as knowledge base, where only the most relevant chunks of information were returned. You would use this node when requiring the full information from a specific Notion page as context for the LLM. Typically, you would connect the output to an LLM, to an Output node, or to a vector data base (to generate and store the embeddings).
Notion node settings
By clicking on the settings icon, you can access the settings modal. Here you can do the following:
- Select the model for embeddings: as default, the
text-embedding-ada-002 model
from OpenAI is selected. However, you will have the option to select the following ones:azure-text-embedding-ada-002
,bert-base-cased
,all-mpnset-base
,palm2
- Chunking algorithm: by default, the system uses
sentence
. You can also choosenaive
. - Chunk overlap: by default, the system uses
500
. You can also choose as many as you want by clicking the number and editing it. - Chunk length: by default, the system uses
1500
. You can also choose as many as you want by clicking the number and editing it. - Unstructured.io: by default, this option is deselected. Enable it to extract unstructured data from documents.
- Text in images (OCR): by default, this option is deselected. Enable it if you want to extract text from images that are present in your documents.