{
 "schema_version": 1,
 "generated": "2026-10-31",
 "id": "infiniflow-ragflow--answer-hard-questions-with-agentic-retrieval",
 "repo": "infiniflow/ragflow",
 "repo_url": "https://github.com/infiniflow/ragflow",
 "repo_slug": "infiniflow-ragflow",
 "title": "Answer multi-step questions with agentic retrieval",
 "page_title": "How to answer multi-step questions with agentic retrieval with Ragflow",
 "summary": "Turn on Agentic Retrieval so the model breaks down a hard question, retrieves several times and checks evidence.",
 "who": "An analyst asking questions that span several documents, such as comparing terms across contracts.",
 "problem": "Single-shot retrieval returns a few chunks and misses context spread across many files.",
 "outcome": "Better grounded answers built from multiple rounds of retrieval, at a thinking depth you choose.",
 "steps": [
  "Deploy RAGFlow and load the documents into a dataset",
  "Enable Agentic Retrieval for complex questions",
  "Pick a thinking mode: Low, Medium, High or Ultra, depending on how complex the question is",
  "Optionally use Knowledge Compilation to generate a Wiki, Graph or Timeline of the dataset first",
  "Check the citations in the answer before relying on it"
 ],
 "agent_prompt": "In infiniflow/ragflow, enable Agentic Retrieval on dataset <name> and ask <question> at Medium and then High thinking mode. Compare the two answers and their citations and tell me which is better supported.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "RAGFlow 1.0 is at release candidate stage, so expect changes between versions.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "go",
 "requirements": [
  "Docker 24.0.0 or later and Docker Compose v2.26.1 or later",
  "A starting machine of 4 CPU cores, 16 GB RAM and 50 GB free disk",
  "An LLM, an embedding model and a reranker, added with their service address and API key after sign-in",
  "If you use Elasticsearch, vm.max_map_count set to at least 262144"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "cost",
   "notice": "Higher thinking modes make more model calls per question, which costs more with a paid LLM provider."
  }
 ],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/infiniflow-ragflow/answer-hard-questions-with-agentic-retrieval/",
 "md": "https://dedupedai.com/use-cases/infiniflow-ragflow/answer-hard-questions-with-agentic-retrieval/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/infiniflow-ragflow--answer-hard-questions-with-agentic-retrieval.json",
 "api_version": "v1"
}