feat: add chunk BM25 and reproducible RRF retrieval

2026-10-16 13:57:35 +08:00
parent ccf1900996
commit bb273ec724
13 changed files with 797 additions and 30 deletions
@@ -1,5 +1,6 @@
 import { apiRequest } from './services/session'
 import type { VectorRetrievalResult } from './services/vectors'
+import type { ChunkKeywordResult, HybridResult } from './services/hybrid'

 export const getHealth = () => apiRequest<{status:string}>('/api/health')
 export const askQuestion = (question:string) => apiRequest<{answer:string;status:string;sources:{title:string;source_url?:string|null}[]}>('/api/chat',{method:'POST',body:JSON.stringify({question})})
@@ -15,6 +16,6 @@ export function reviewKnowledge(id:number,payload:{expected_version:number;verif
 export type RetrievalHit={rank:number;knowledge_id:number;knowledge_version:number;document_id:number|null;document_version:number|null;source_id:number|null;source_version:number|null;source_name:string|null;source_url:string;title:string;category:string;snippet:string;snippet_start:number;snippet_end:number;score:number;matched_terms:string[]}
 export type RetrievalResult={run_id:string;query:string;mode:'keyword';status:'ok'|'no_evidence';top_k:number;category:string|null;query_terms:string[];corpus_size:number;corpus_fingerprint:string;total_hits:number;results:RetrievalHit[];elapsed_ms:number;created_at:string;config:{tokenizer:string;scorer:string;k1:number;b:number;title_weight:number;stopwords_version:string}}
 export function retrieveKnowledge(payload:{query:string;mode?:'keyword';top_k?:number;category?:string}){return apiRequest<RetrievalResult>('/api/retrieval',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify(payload)})}
-export type RetrievalRunResult = RetrievalResult | VectorRetrievalResult
+export type RetrievalRunResult = RetrievalResult | VectorRetrievalResult | ChunkKeywordResult | HybridResult
 export function getRetrievalRun(runId:string){return apiRequest<RetrievalRunResult>(`/api/retrieval/runs/${encodeURIComponent(runId)}`)}
 export function getRetrievalRuns(page=1,pageSize=20){return apiRequest<{items:RetrievalRunResult[];total:number;page:number;page_size:number}>(`/api/retrieval/runs?page=${page}&page_size=${pageSize}`)}