> ## Documentation Index
> Fetch the complete documentation index at: https://docs.archetypeai.app/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Start with /introduction/getting-started. Use the Direct Query API (POST /query) with the Newton Fusion model (text, image, and video reasoning) or the Newton Omega encoder (time-series embeddings). ATAI_API_ENDPOINT must include the version path: /v0.5 for most APIs, /v0.6 for the Fine-Tuning Service. Pages whose descriptions are marked (Archived) document the legacy Lens runtime — do not use them for new projects.

# YAML Parameter Reference

> A reference for the parameters available when configuring batch jobs.

This reference describes each of the YAML parameters available when configuring each of the task
types supported by the Batch Processing API.

<Tabs>
  <Tab title="Machine State Classification">
    <ParamField path="worker" type="UserComponentParameters">
      <Expandable title="properties" defaultOpen="true">
        <ParamField path="config" type="MachineStateJobUserConfig" required="true">
          Per-worker machine state classification job configuration.

          <Expandable title="properties" defaultOpen="true">
            <ParamField path="batch_size" type="PositiveInt" default="8">
              Inference batch size. Must be an integer `1` or higher.
            </ParamField>

            <ParamField path="classifer_config" type="ClassifierConfig">
              Optional K-Nearest Neighbor (KNN) classifier over embeddings configuration.

              <Expandable title="properties">
                <ParamField path="metric" type="string" default="euclidean">
                  The type of metric to use. One of `cityblock`, `cosine`, `euclidean`, `haversine`, `l1`, `l2`, `manhattan`, `nan_euclidean`.
                </ParamField>

                <ParamField path="n_neighbors" type="PositiveInt" default="5">
                  KNN count. Must be at least `3`.
                </ParamField>

                <ParamField path="normalize_embeddings" type="boolean" default="false">
                  Whether or not to normalize embeddings before classification.
                </ParamField>

                <ParamField path="weights" type="string" default="uniform">
                  The uniform distance weighting method to use with KNN: `distance` or `uniform`.
                </ParamField>
              </Expandable>
            </ParamField>

            <ParamField path="flush_every_n_iteration" type="PositiveInt" default="150">
              The number of iterations to process between forced flushes. Must be at least `1`.
            </ParamField>

            <ParamField path="model_type" type="string">
              The type of encoder model to use for the Machine State Classification task: `omega_1_3_surface`, `omega_1_3_power_drive`, `omega_1_4_base`, `omega_1_5_base`.
            </ParamField>

            <ParamField path="reader_config" type="ReaderConfig" required="true">
              Windowed reader configuration options.

              <Expandable title="properties">
                <ParamField path="data_columns" type="string[]" required="true">
                  The names of the columns to include in the analysis.
                </ParamField>

                <ParamField path="step_size" type="PositiveInt" required="true">
                  The step between consecutive windows. Must be at least `1`.
                </ParamField>

                <ParamField path="timestamp_column" type="string" required="true">
                  The name of the column in the input data that contains the timestamps.
                </ParamField>

                <ParamField path="window_size" type="PositiveInt" required="true">
                  The number of samples in each window. Must bet at least `1`.
                </ParamField>
              </Expandable>
            </ParamField>
          </Expandable>
        </ParamField>

        <ParamField path="parallelism" type="integer" default="1">
          Number of worker pods to run in parallel for a single job. **Must be set to `1`.**
        </ParamField>
      </Expandable>
    </ParamField>

    ```yaml Example configuration theme={"system"}
    worker:
      config:
        batch_size: 32
        classifier_config:
          metric: euclidean
          n_neighbors: 5
          normalize_embeddings: false
          weights: uniform
        flush_every_n_iteration: 150
        model_type: omega_1_4_base
        reader_config:
          data_columns:
            - c1
            - c2
            - c3
          step_size: 1024
          timestamp_column: timestamp
          window_size: 64
      parallelism: 1
    ```
  </Tab>

  <Tab title="Activity Detection">
    <ParamField path="worker" type="UserComponentParameters">
      <Expandable title="properties" defaultOpen="true">
        <ParamField path="config" type="UserInferenceConfig" required="true">
          Per-worker activity detection inference configuration.

          <Expandable title="properties" defaultOpen="true">
            <ParamField path="generation" type="GenerationConfig">
              Generation hyperparameters.

              <Expandable title="properties">
                <ParamField path="do_sample" type="boolean" default="true">
                  Whether or not to enable stochastic sampling. When `false`, decoding is greedy.
                </ParamField>

                <ParamField path="max_new_tokens" type="integer" default="256">
                  The upper bound on tokens generated, per sample. Must be at least `1`.
                </ParamField>

                <ParamField path="repetition_penalty" type="float" default="1.0">
                  Penalty applied to previously-generated tokens. Must be greater than `0` and no greater than `2.0`. Values above `1.0` discourage repetition.
                </ParamField>

                <ParamField path="temperature" type="float" default="0.7">
                  Softmax temperature for sampling. Must be greater than `0` and no greater than `2.0`. The higher this value, the more diverse.
                </ParamField>

                <ParamField path="top_p" type="float" default="0.8">
                  Nucleus-sampling threshold. Keeps the smallest token set whose cumulative probability is greater than or equal to this value. Must be greater than `0` and no greater than `1.0`.
                </ParamField>

                <ParamField path="top_k" type="integer" default="20">
                  Top-k cutoff. Set to `0` to disable cutoff.
                </ParamField>
              </Expandable>
            </ParamField>

            <ParamField path="max_video_frames" type="integer" default="32">
              The maximum number of video frames sampled per video input. Extra frames are dropped uniformly. Must be between 1 and 64.
            </ParamField>

            <ParamField path="model_variant" type="string" default="newton/c:2.5.1-8b-base">
              Specifies the model bundle to use. Standard permitted values are:

              * `newton/c:2.3.0-7b-base`
              * `newton/c:2.4.0-7b-base`
              * `newton/c:2.5.0-8b-base`
              * `newton/c:2.5.1-8b-base`
              * `newton/c:2.6.0-8b-bf16-base`
              * `newton/c:2.6.0-8b-fp8-base`
              * `newton/c:2.6.0-30b-a3b-fp8-base`
              * `newton/visual-audio-c:2.5.0-v2-8b`
              * `newton/visual-audio-c:2.6.0-v2-8b-fp8`
            </ParamField>
          </Expandable>
        </ParamField>

        <ParamField path="parallelism" type="integer" default="1">
          Number of worker pods to run in parallel for a single job. **Must be set to `1`.**
        </ParamField>
      </Expandable>
    </ParamField>

    ```yaml Example configuration theme={"system"}
    worker:
      config:
        generation:
          do_sample: true
          max_new_tokens: 256
          repetition_penalty: 1
          temperature: 0.7
          top_k: 20
          top_p: 0.8
        max_video_frames: 32
        model_variant: newton/c:2.5.1-8b-base
      parallelism: 1
    ```
  </Tab>
</Tabs>