Qdrant

Most retrieval agents run the same pipeline for every query: wasted compute on easy questions, under-served hard ones, and guesses when the evidence is not there. In this video you build a loop that adapts. What you'll learn to build: - An agent that picks its retrieval strategy per question, instead of forcing every query down one fixed pipeline. - Cheap in-loop signals that flag weak retrieval early, plus how to benchmark which signals actually separate good results from weak ones on your own data (most candidates do not). - A gate that routes each query to the right fix, including late-interaction reranking (ColBERT) for ranking errors, query decomposition (IRCoT) for missing multi-hop evidence. - A STOP decision, so the agent abstains when the evidence is insufficient rather than guessing. REFERENCE LINKS: - Github Repo: https://github.com/qdrant-labs/self-correcting-loops-workshop - Dataset: https://github.com/stonybrooknlp/musique - Further Reading: https://qdrant.tech/articles/predicting-weak-retrieval/