LlamaIndex ‘legal-kb’: get, search, learn, and get agent on index v2 utilizing grep device

import { LlamaCloud } from '@llamaindex/llama-cloud'
import { device, ToolLoopAgent } from 'ai'
import { z } from 'zod'
import { makeCitationId } from './citations'

// One device closure per index. Wraps Index v2 retrieval APIs.
operate createLlamaParseTools(apiKey: string, projectId: string, indexId: string) {
  const shopper = new LlamaCloud({ apiKey })

  const retrieve = device({
    description: 'Run a semantic retrieval question towards an index.',
    inputSchema: z.object({
      question: z.string(),
      top_k: z.quantity().nullable(),
      score_threshold: z.quantity().nullable(),
      rerank_top_n: z.quantity().nullable(),   // set to allow reranking
      file_name: z.string().nullable(),      // metadata filter
      file_version: z.quantity().nullable(),
    }),
    execute: async ({ question, top_k, score_threshold, rerank_top_n, file_name }) => {
      const custom_filters = file_name
        ? { file_name: { operator: 'eq' as const, worth: file_name } }
        : undefined

      const response = await shopper.beta.retrieval.retrieve({
        index_id: indexId,
        project_id: projectId,
        question,
        top_k,
        score_threshold,
        rerank: rerank_top_n != null ? { enabled: true, top_n: rerank_top_n } : undefined,
        custom_filters,
      })

      // Return a model-readable record plus citations that drive the UI chips.
      const citations = response.outcomes.map((r) => ({
        id: makeCitationId(),                    // e.g. "c7f2qa"
        fileName: r.metadata?.file_name,
        rating: r.rerank_score ?? r.rating ?? null,
        preview: r.content material.slice(0, 500),
      }))
      const formatted = response.outcomes
        .map((r, i) => `### End result #${i + 1}nn${r.content material.slice(0, 600)}`)
        .be part of('nn---nn')
      return { formatted, citations }
    },
  })

  // findFiles / readFile / grepFile observe the identical form, backed by
  // shopper.beta.retrieval.discover / .learn / .grep
  return { retrieve /* , findFiles, readFile, grepFile */ }
}

export operate buildAgent(mannequin, apiKey: string, projectId: string, indexId: string) {
  return new ToolLoopAgent({
    mannequin,
    instruments: createLlamaParseTools(apiKey, projectId, indexId),
    directions:
      'All the time name findFiles first, floor each reply within the paperwork, ' +
      'and cite ids inline as `cite:<id>`.',
  })
}