One of the most common use-cases for an LLM application is to answer questions about a set of documents. LlamaIndex has rich support for many forms of question & answering.

Types of question answering use cases#

Q&A has all sorts of sub-types, such as:

What to do#

  • Semantic search: finding data that matches not just your query terms, but your intent and the meaning behind your question. This is sometimes known as “top k” search.

  • Summarization: condensing a large amount of data into a short summary relevant to your current question

Further examples#

For further examples of Q&A use cases, see our Q&A section in Putting it All Together.