spackows / rag-cd

Samples related to Content Design for RAG

Content Design for RAG

Samples related to Content Design (CD) for retrieval-augmented generation (RAG).

Sample notebooks

Notebook	Description
1. Filter input ( link )	Use the Natural Langauge Understanding service on IBM Cloud to filter out malicious input (eg. Javascript injection)
2. Classify input ( link )	Use a large language model in IBM watsonx.ai to classify user input into one of these categories: Keyword search Question (including question type) Instruction
3. Remove HAP, PII ( link )	Remove hate, abuse, and profanity (HAP) as well as personal identifiable information (PII)
4. Identify FAQs ( link )	Match a given question with frequently asked questions
5. Boost search ( link )	Improve search success using several techniques: Add synonyms Rewrite query
6. Prompt by question type ( link )	Given relevant articles from a knowledge base, prompt a large language model to format answers to questions differently, depending on the question type: What-is How-to
7. Select best answer ( link )	Select the best of several generated answers
8. Regression testing ( link )	Test whether a change to the RAG solution causes the solution to get better or worse
9. Testing topics ( link )	Test how well a topic can answer given user questions
10. HTML to text ( link )	Convert HTML to text
11. Answer Natural Questions ( link )	Answer a subset of questions from the Natural Questions benchmark