How to Use Knowledge Base (RAG)
What is Knowledge Base?
Knowledge Base is a library of files and URLs from which your AI bot can retrieve information. It helps to provide more accurate and helpful answers. Builders can upload and manage files here.
It uses a framework called Retrieval Augmented Generation (RAG).
What is Retrieval Augmented Generation (RAG)?
Retrieval Augmented Generation (RAG) basically allows LLMs - which are trained on general knowledge from the Internet - to access your organization’s data and knowledge.
Knowledge Base Retrieval Types
Top K: A variable that sets the number of top chunks to be retrieved. A higher 'K' value means more chunks are retrieved, which can improve accuracy but may slow down response time.
Retrieval type: This allows you to determine how information is retrieved from the selection in the dropdown
- 'Chunk' retrieves specific sections that are the most similar to the user prompt.
- 'Neighbor' retrieves related content that is most similar to the user prompt, and retrieves 1 chunk before and 1 chunk after.
- 'Document' retrieves the entire document for context.
When to use which retrieval method?
- Chunk: This is best used when the answer to a user's query might be found in a small section of text within a larger document.
- Neighbor: This is useful when LLM needs more context surrounding the direct answer to the user query.
- Document: This works best when the user query requires LLM to understand the entire documents.
- When experimenting with different retrieval methods, pay attention to quality of output, latency, and context window limit.
Keep Reading
What to Do When You Hit a TPM Limit
Faith Timoh Abang
Learn about the new token limit updates in CreateAI Builder that allow rate limit request increases.
Accessing Generative AI APIs at ASU
Faith Abang Timoh
As interest in building with generative AI grows, ASU offers several pathways for API access depending on whether you're doing academic research, enterprise development, or individual experimentation.
Below is a breakdown of approved API access options, along with who to contact and what to expect.
Understanding Rate Limits on CreateAI Builder
Kofi Wood and Shailee Shah
Ever run into a message that says, “Your project has reached its Tokens per Minute limit (TPM)”? Well, just think of it as a friendly traffic signal reminding us not to zoom too fast. We’ll walk through what does a token mean, what does reaching TPM mean, which settings affect token usage, and how to optimize your AI Project to avoid hitting the limit.
AI with Integrity: ASU’s AI Acceleration Team is Setting New Standards for Ethical AI
Faith Timoh Abang
Artificial intelligence (AI) is rapidly transforming industries, from healthcare and finance to entertainment and education. At Arizona State University (ASU), the AI Acceleration team within Enterprise Technology is ensuring that this transformation happens responsibly.