Change Default ModelΒΆ

By default Rhubarb uses Claude Sonnet model, however you can also use Haiku, Opus, Nova Pro, or Nova Lite. Different Language Models are available via LanguageModel class.

  • LanguageModel.CLAUDE_HAIKU_V1

  • LanguageModel.CLAUDE_SONNET_V1

  • LanguageModel.CLAUDE_SONNET_V2 (default)

  • LanguageModel.CLAUDE_OPUS_V1

  • LanguageModel.NOVA_PRO

  • LanguageModel.NOVA_LITE

Use Claude Haiku -

  from rhubarb import DocAnalysis, LanguageModels

  da = DocAnalysis(file_path="s3://your-bucket/employee_enrollment.pdf",
                   boto3_session=session,
                   modelId=LanguageModels.CLAUDE_HAIKU_V1)
  resp = da.run(message="What is the employee's name?")

Or Claude Opus -

  from rhubarb import DocAnalysis, LanguageModels

  da = DocAnalysis(file_path="s3://your-bucket/employee_enrollment.pdf",
                   boto3_session=session,
                   modelId=LanguageModels.CLAUDE_OPUS_V1)
  resp = da.run(message="What is the employee's name?")

Or Nova Pro -

  from rhubarb import DocAnalysis, LanguageModels

  da = DocAnalysis(file_path="s3://your-bucket/employee_enrollment.pdf",
                   boto3_session=session,
                   modelId=LanguageModels.NOVA_PRO)
  resp = da.run(message="What is the employee's name?")