Batch API Reference

Materialized’s Batch API is designed to work over tables/dataframes or collections of objects. As of today, there are several ways to use Materialized: by passing a list of prompts to the API, by passing a dataframe/table to the API containing a “prompt column”, or pointing the API to s3-compatible storage containing the data. If you need to connect via s3-compatible storage, please reach out to us at team@materialized.dev.

You can also access the Batch API via our Python SDK.

• Create Batch Inference Jobs
  • Basic Example
• Retrieving and Managing Job State
  • Job Status
  • Cancelling a Job
  • Retrieving Results
  • Listing All Jobs
• Job Priority
  • Priority 0 (Prototyping)
  • Priority 1 (Production)
• Structured Outputs
  • Example
• Cost Estimates
• System Prompts
  • Basic System Prompt Example
• Cumulative Logprobs (Experimental)
• Using Random Seeds
• Increasing Quotas
• Sampling Parameters
• Embedding Models