Skip to main content
The parallel() strategy splits large documents into chunks, processes them concurrently, and uses an LLM to merge the extracted results.

​
Usage

import { extract, parallel } from 'struktur';
import { openai } from '@ai-sdk/openai';

const result = await extract({
  artifacts,
  schema,
  strategy: parallel({
    model: openai('gpt-4o-mini'),
    mergeModel: openai('gpt-4o'),
    chunkSize: 100000,
  }),
});

​
Configuration

​
model
LanguageModel
required
The AI SDK language model to use for extracting from each chunk.
​
mergeModel
LanguageModel
required
The AI SDK language model to use for merging extracted results. Typically a more capable model.
​
chunkSize
number
required
Maximum tokens per chunk. Documents are split into batches that fit within this limit.
​
concurrency
number
Maximum number of concurrent extraction tasks. Defaults to processing all chunks in parallel.
​
maxImages
number
Maximum number of images per chunk. Useful for controlling vision API costs.
​
outputInstructions
string
Additional instructions to guide the model’s output format or behavior.
​
execute
function
Custom retry executor function. Defaults to runWithRetries.
​
strict
boolean
Enable strict mode for structured output validation. Defaults to false.

​
When to use

  • You have large documents that exceed context limits
  • You want fast processing through parallelization
  • You need an LLM to intelligently merge results
  • You’re willing to use extra tokens for the merge step

​
Trade-offs

Advantages:
  • Fast processing through parallelization
  • Intelligent LLM-based merging
  • Handles documents of any size
  • Configurable concurrency for rate limit management
Limitations:
  • Higher token usage (chunk extractions + merge)
  • Merge quality depends on merge model capability
  • More expensive than simple strategy

​
Performance characteristics

The strategy estimates batches.length + 3 steps:
  1. Prepare
  2. Extract from batch 1 through N (parallel)
  3. Merge
  4. Complete

​
Example with concurrency control

import { extract, parallel } from 'struktur';
import { openai } from '@ai-sdk/openai';

const result = await extract({
  artifacts: largeDocumentArtifacts,
  schema: invoiceSchema,
  strategy: parallel({
    model: openai('gpt-4o-mini'),
    mergeModel: openai('gpt-4o'),
    chunkSize: 100000,
    concurrency: 5, // Process 5 chunks at a time
    maxImages: 10,  // Limit images per chunk
  }),
  events: {
    onStep: ({ step, total, label }) => {
      console.log(`Progress: ${step}/${total} - ${label}`);
    },
  },
});

Build docs developers (and LLMs) love

Get started for freeTalk to us