39 lines
1.5 KiB
TypeScript
39 lines
1.5 KiB
TypeScript
// The search: one collection, one query, cited answers. The embedding leaves the process (the
|
|
// procedure is an effect), the ranking is the vector store's, and every answer carries where it
|
|
// came from: the file, the chunk, and the snippet a person reads.
|
|
|
|
import { forbidden, internal } from "@conusai-kit/core"
|
|
import { MAX_SEARCH_RESULTS, type SearchResult } from "../contract/index.js"
|
|
import { requireCollection } from "./collections.js"
|
|
import { type KnowledgeDeps, type KnowledgeScope, knowledgeEnabled } from "./ports.js"
|
|
|
|
export async function searchKnowledge(
|
|
deps: KnowledgeDeps,
|
|
scope: KnowledgeScope,
|
|
input: { collectionName: string; query: string; limit?: number | undefined },
|
|
): Promise<{ results: SearchResult[] }> {
|
|
if (!(await knowledgeEnabled(deps, scope))) throw forbidden("knowledge is switched off for this project")
|
|
await requireCollection(deps, scope, input.collectionName)
|
|
const service = deps.search
|
|
if (!service) throw internal("the knowledge search service is not bound in this process")
|
|
const limit = Math.min(input.limit ?? 10, MAX_SEARCH_RESULTS)
|
|
const hits = await service.search(scope, {
|
|
collectionName: input.collectionName,
|
|
query: input.query,
|
|
limit,
|
|
actorId: scope.actor.userId,
|
|
})
|
|
return {
|
|
results: hits.map((hit): SearchResult => {
|
|
return {
|
|
fileId: hit.fileId,
|
|
filename: hit.filename,
|
|
collectionName: hit.collectionName,
|
|
snippet: hit.snippet,
|
|
score: hit.score,
|
|
chunk: hit.chunk,
|
|
}
|
|
}),
|
|
}
|
|
}
|