{"uid":"cap__Q0SGvWV35QM0WQV-WYHG","slug":"bge-document-reranker-agent-hub-56bad4e3","name":"BGE Document Reranker (Agent Hub)","description":"Rerank up to 100 documents by relevance to a query (BGE reranker). Returns indices and scores, best first. Drop-in step for RAG and search pipelines. Also callable as GET with the same fields as query parameters.","url":"https://agents.torbrooknews.com/v1/rerank?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["query","documents"],"properties":{"query":{"type":"string"},"top_k":{"type":"integer"},"documents":{"type":"string","description":"separate items with |"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_MKaN_IGbR9wxGrF6f3VmT","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Reranks up to 100 documents by relevance to a query using a BGE reranker model, returning sorted indices and scores for use in RAG and search pipelines.","exampleAgentPrompt":"Rerank these 5 document passages by how relevant they are to the query 'what are the symptoms of diabetes': 'high blood sugar causes fatigue' | 'exercise improves mood' | 'insulin regulates glucose' | 'diabetes affects millions' | 'cats are common pets' — and give me the top 3.","exampleUseCases":[{"title":"RAG pipeline retrieval refinement","prompt":"I retrieved 20 chunks from my vector database for the query 'how does photosynthesis work' — can you rerank them by relevance and return only the top 5 so I pass the best context to my LLM?"},{"title":"Search result reordering","prompt":"I have these 10 product descriptions from a keyword search for 'waterproof hiking boots' and want them sorted by how well they actually match that query — rerank them and show me the scores."},{"title":"Q&A candidate passage selection","prompt":"Given the question 'What caused the 2008 financial crisis?', rerank these 8 passages from different articles and tell me which ones are most relevant so I know which to include in my answer."}],"resultDescription":"Returns a list of objects sorted best-first, each containing the original document index and a relevance score indicating how well that document matches the query. Optionally limited to top_k results.","failureModes":["Missing required 'query' or 'documents' query parameters returns a 400 error","Documents list exceeds 100 items may be rejected or truncated","Payment not provided or insufficient (x402 payment required) returns a 402 error","Malformed document separator (not using '|') may cause parsing errors","Empty document list returns an error or empty result"],"whenToPreferThis":"Choose this endpoint when you need a lightweight, pay-per-call BGE reranking step without managing an API key or infrastructure — ideal for augmenting RAG pipelines, search result reordering, or passage selection where semantic relevance scoring is needed. Prefer it over embedding-based similarity when cross-encoder reranking quality is required and you want simple GET-based integration.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T12:46:45.157Z","isFirstParty":false,"canonicalSlug":"bge-document-reranker-agent-hub-56bad4e3"}