Possibility of No-Code Creation of Free AI Knowledge Base with basic chat interface using Google NotebookLM but with free tier limits

Using Google’s NotebookLM, which has a free tier, you can create an AI knowledge base. Source material about the knowledge base in formats like Google Docs, pdfs or text should be uploaded to the notebook. Then the AI should be able to perform natural language queries against that specific data, providing source-grounded responses with clickable citations that point directly back to the uploaded documents to ensure accuracy. Unlike generic AI chatbots that "forget" information as a conversation grows long or require files to be re-uploaded for every new session, NotebookLM maintains Global Context Persistence—ensuring that all uploaded sources are immediately and permanently available to every chat session created within that notebook.

Note that this process does not need any software development work and so is a 'no-code creation' process.

The main free tier limits for NotebookLM are as follows:

• Notebooks: 100
• Sources per notebook: 50
• Source file size limit: 500,000 words per source or up to 200MB for local uploads. There’s no page limit.
• Chats: 50/day

For other limits including upgrade options with higher limits, please visit the Google reference page.

The "File size limit for sources in NotebookLM" is given in entry with same name in this Google reference page.

The "50 sources" limit is a restrictive part of the free tier. 

But as each source can hold 500,000 words, when individual source files are significantly lesser than 500,000 words, a workaround approach that may help would be to combine these individual sources such that the combined set of these sources is a smaller number of source files with each source file having not more than 500,000 words. Of course, even after this workaround, if the total set of source files exceeds 50 then the entire set cannot be provided to a notebook in free tier.

Some additional points about NotebookLM

• Public Sharing: As per Gemini, you can set the access to "Anyone with the link," allowing anyone (who is logged in to a Google account) to chat with the AI knowledge base without you needing to manage individual accounts or complex permissions.
• As per Gemini, in the scenario where you share a public link, the 50 chats per day limit is individual to each logged-in Google account user who is on free tier, not shared across the entire notebook.
• Global vs. Session Persistence: In standard AI tools, a "New Chat" usually means a blank slate where sources must be re-attached. In NotebookLM, your sources are a permanent part of the notebook's infrastructure. Every new chat session you (or a public visitor) start begins with a complete "understanding" of the entire source library without any additional setup.
• Source Grounding: Unlike generic AI, this facility provides citations (clickable numbers) that point directly back to the specific sources used to generate the answer, ensuring accuracy and transparency.
• Interface Constraints: The chat happens within the Google NotebookLM website interface. It does not have the custom branding, unique UI/UX, or mobile-app-specific features (like notifications) of a dedicated custom app found on the web or on the Play Store.
• Cloud-Native: It is a powerful, persistent, and intelligent "Knowledge Flywheel" hosted entirely in the Google cloud, making it accessible to anyone with a browser and the link.

I have already validated the above main workflow excluding the public notebook link sharing part, by creating a private NotebookLM notebook for my blog posts on static school website development (17 posts), and in initial testing, it seems to work well. For more on this, you may please visit my recent post: Notes on Blogger posts to NotebookLM pipeline and using it for static school website blog posts.