diff --git a/docs/getting_started/concepts.md b/docs/getting_started/concepts.md index 1c9fd8d5bb5d6836822800a6c8262622ddc1d09d..efbf158af7dee20cd87b9c2319a204e96dfb042c 100644 --- a/docs/getting_started/concepts.md +++ b/docs/getting_started/concepts.md @@ -40,7 +40,7 @@ Once you've ingested your data, LlamaIndex will help you index the data into a f ### Querying Stage In the querying stage, the RAG pipeline retrieves the most relevant context given a user query, -and pass that to the LLM (along with the query) to synthesize a response. +and passes that to the LLM (along with the query) to synthesize a response. This gives the LLM up-to-date knowledge that is not in its original training data, (also reducing hallucination). The key challenge in the querying stage is retrieval, orchestration, and reasoning over (potentially many) knowledge bases.