json2vec 0.4.5__tar.gz → 0.4.6__tar.gz

{json2vec-0.4.5/src/json2vec.egg-info → json2vec-0.4.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: json2vec
-Version: 0.4.5
+Version: 0.4.6
 Summary: {...} -> [*]
 License-Expression: Apache-2.0
 Requires-Python: >=3.12
@@ -27,16 +27,18 @@ Requires-Dist: pydantic-settings>=2.10.1; extra == "serving"
 Provides-Extra: text
 Requires-Dist: transformers>=4.55.0; extra == "text"
 Provides-Extra: docs
+Requires-Dist: litserve>=0.2.13; extra == "docs"
 Requires-Dist: mkdocs-material>=9.6; extra == "docs"
 Requires-Dist: mkdocs-jupyter>=0.26.3; extra == "docs"
 Requires-Dist: mkdocstrings[python]>=0.27; extra == "docs"
+Requires-Dist: pydantic-settings>=2.10.1; extra == "docs"
 Dynamic: license-file
 
 <p align="center">
-  <img src="https://json2vec.github.io/json2vec/diagrams/json2vec.png" alt="JSON2Vec logo" width="180">
+  <img src="https://json2vec.github.io/json2vec/diagrams/json2vec.png" alt="json2vec logo" width="180">
 </p>
 
-<h1 align="center">JSON2Vec</h1>
+<h1 align="center"><code>json2vec</code></h1>
 
 <p align="center">
   <img alt="Python 3.12+" src="https://img.shields.io/badge/python-3.12%2B-3776AB?logo=python&amp;logoColor=white" />
@@ -69,14 +71,14 @@ schemas, and checkpoints private.
 - **Extensible data types for predictive modeling.** Masked values,
   targeted fields, and explicit supervised targets all flow through the same
   datatype-specific heads. A new
-  [tensorfield type](https://json2vec.github.io/json2vec/guides/tensorfields/) brings its own embedding,
+  [tensorfield type](https://json2vec.github.io/json2vec/data-types/tensorfields/) brings its own embedding,
   decoding, loss, and writing logic, so the framework stays reusable as schemas
   grow.
 - **Schema evolution is a first-class workflow.** Between training loops
   (pretraining, finetuning, refitting, and task adaptation), the model can be
   mutated. Fields can be added (`model.extend`), removed (`model.delete`),
   updated (`model.update` / `with model.override`), and reset (`model.reset`).
-  See the [model update guide](https://json2vec.github.io/json2vec/guides/model-update/).
+  See the [mutations guide](https://json2vec.github.io/json2vec/core-concepts/mutations/).
 - **Production semantics for missingness.** `null`, `padded`, `masked`, and
   `valued` are distinct states in the tensorfield type system.
   They are not collapsed into one generic missing-value bucket.
@@ -104,7 +106,7 @@ Use `json2vec` when the hierarchy is part of the signal:
   multi-target prediction over nested records
 
 For more context on the modeling problem, read
-[Why JSON2Vec](https://json2vec.github.io/json2vec/motivation/).
+[Why `json2vec`](https://json2vec.github.io/json2vec/motivation/).
 
 ## What It Does Not Do
 
@@ -171,8 +173,8 @@ model = j2v.Model.from_schema(
     optimizer=lambda module: torch.optim.AdamW(module.parameters(), lr=1e-2),
 )
 
-datamodule = j2v.PolarsDataModule.from_model(
-    model,
+datamodule = j2v.PolarsDataModule(
+    model=model,
     train=records,
     validate=records,
     num_workers=0,
@@ -195,14 +197,11 @@ trainer = lit.Trainer(
 
 trainer.fit(model=model, datamodule=datamodule)
 
-batch = [[record] for record in records.to_dicts()[:3]]
-
-pprint(model.predict(batch))
-pprint(model.embed(batch))
+pprint(model.predict(records.to_dicts()[:3]))
 ```
 
-The prediction call returns a typed result for `record/species`. The embedding
-call returns the configured `record` embedding for each input observation.
+The prediction call returns a typed result for `record/species` and the
+configured `record` embedding for each input observation.
 
 ## Documentation
 
@@ -216,16 +215,20 @@ uv run --extra docs mkdocs build --strict
 Useful entry points:
 
 - [Getting Started](https://json2vec.github.io/json2vec/getting-started/)
-- [Why JSON2Vec](https://json2vec.github.io/json2vec/motivation/)
-- [Schemas & Queries](https://json2vec.github.io/json2vec/guides/model-schemas/)
-- [Model Updates](https://json2vec.github.io/json2vec/guides/model-update/)
+- [AI Quickstart](https://json2vec.github.io/json2vec/ai-quickstart/)
+- [Why `json2vec`](https://json2vec.github.io/json2vec/motivation/)
+- [Query Paths](https://json2vec.github.io/json2vec/core-concepts/querypaths/)
+- [Built-In Data Types](https://json2vec.github.io/json2vec/core-concepts/data-types/)
+- [Learning Modes & Embeddings](https://json2vec.github.io/json2vec/core-concepts/embeddings/)
+- [Model Tree](https://json2vec.github.io/json2vec/core-concepts/model-tree/)
+- [Mutations](https://json2vec.github.io/json2vec/core-concepts/mutations/)
 - [Hello World](https://json2vec.github.io/json2vec/tutorials/hello-world/)
-- [Masked Pretraining](https://json2vec.github.io/json2vec/tutorials/pretraining/)
 - [Nested Supervised Training](https://json2vec.github.io/json2vec/tutorials/nested-supervised-training/)
+- [Masked Pretraining](https://json2vec.github.io/json2vec/tutorials/pretraining/)
 - [Supervised Tabular Training](https://json2vec.github.io/json2vec/tutorials/supervised-tabular-training/)
-- [Field Ablation](https://json2vec.github.io/json2vec/guides/field-ablation/)
+- [Field Importance](https://json2vec.github.io/json2vec/guides/field-importance/)
 - [Preprocessors](https://json2vec.github.io/json2vec/guides/preprocessors/)
-- [Tensorfield Extensions](https://json2vec.github.io/json2vec/guides/tensorfields/)
+- [Custom Data Types](https://json2vec.github.io/json2vec/data-types/tensorfields/)
 - [Serving](https://json2vec.github.io/json2vec/tutorials/serving/)
 - [API Reference](https://json2vec.github.io/json2vec/reference/api/)
 - [Whitepaper](https://json2vec.github.io/json2vec/whitepaper.pdf)
@@ -292,7 +295,7 @@ Configured `dataset.kwargs` are passed into the preprocessor, with unsupported k
 
 Each tensorfield plugin provides a request schema plus the model components
 needed to encode values, decode predictions, compute losses, and optionally
-serialize outputs. See [Tensorfield Extensions](https://json2vec.github.io/json2vec/guides/tensorfields/)
+serialize outputs. See [Custom Data Types](https://json2vec.github.io/json2vec/data-types/tensorfields/)
 for a custom plugin walkthrough. Built-in tensorfields share the base leaf
 options `name`, `query`, `pooling`, `weight`, `n_heads`, `n_linear`, `dropout`,
 `p_mask`, and `p_prune`.

{json2vec-0.4.5 → json2vec-0.4.6}/README.md

@@ -1,8 +1,8 @@
 <p align="center">
-  <img src="https://json2vec.github.io/json2vec/diagrams/json2vec.png" alt="JSON2Vec logo" width="180">
+  <img src="https://json2vec.github.io/json2vec/diagrams/json2vec.png" alt="json2vec logo" width="180">
 </p>
 
-<h1 align="center">JSON2Vec</h1>
+<h1 align="center"><code>json2vec</code></h1>
 
 <p align="center">
   <img alt="Python 3.12+" src="https://img.shields.io/badge/python-3.12%2B-3776AB?logo=python&amp;logoColor=white" />
@@ -35,14 +35,14 @@ schemas, and checkpoints private.
 - **Extensible data types for predictive modeling.** Masked values,
   targeted fields, and explicit supervised targets all flow through the same
   datatype-specific heads. A new
-  [tensorfield type](https://json2vec.github.io/json2vec/guides/tensorfields/) brings its own embedding,
+  [tensorfield type](https://json2vec.github.io/json2vec/data-types/tensorfields/) brings its own embedding,
   decoding, loss, and writing logic, so the framework stays reusable as schemas
   grow.
 - **Schema evolution is a first-class workflow.** Between training loops
   (pretraining, finetuning, refitting, and task adaptation), the model can be
   mutated. Fields can be added (`model.extend`), removed (`model.delete`),
   updated (`model.update` / `with model.override`), and reset (`model.reset`).
-  See the [model update guide](https://json2vec.github.io/json2vec/guides/model-update/).
+  See the [mutations guide](https://json2vec.github.io/json2vec/core-concepts/mutations/).
 - **Production semantics for missingness.** `null`, `padded`, `masked`, and
   `valued` are distinct states in the tensorfield type system.
   They are not collapsed into one generic missing-value bucket.
@@ -70,7 +70,7 @@ Use `json2vec` when the hierarchy is part of the signal:
   multi-target prediction over nested records
 
 For more context on the modeling problem, read
-[Why JSON2Vec](https://json2vec.github.io/json2vec/motivation/).
+[Why `json2vec`](https://json2vec.github.io/json2vec/motivation/).
 
 ## What It Does Not Do
 
@@ -137,8 +137,8 @@ model = j2v.Model.from_schema(
     optimizer=lambda module: torch.optim.AdamW(module.parameters(), lr=1e-2),
 )
 
-datamodule = j2v.PolarsDataModule.from_model(
-    model,
+datamodule = j2v.PolarsDataModule(
+    model=model,
     train=records,
     validate=records,
     num_workers=0,
@@ -161,14 +161,11 @@ trainer = lit.Trainer(
 
 trainer.fit(model=model, datamodule=datamodule)
 
-batch = [[record] for record in records.to_dicts()[:3]]
-
-pprint(model.predict(batch))
-pprint(model.embed(batch))
+pprint(model.predict(records.to_dicts()[:3]))
 ```
 
-The prediction call returns a typed result for `record/species`. The embedding
-call returns the configured `record` embedding for each input observation.
+The prediction call returns a typed result for `record/species` and the
+configured `record` embedding for each input observation.
 
 ## Documentation
 
@@ -182,16 +179,20 @@ uv run --extra docs mkdocs build --strict
 Useful entry points:
 
 - [Getting Started](https://json2vec.github.io/json2vec/getting-started/)
-- [Why JSON2Vec](https://json2vec.github.io/json2vec/motivation/)
-- [Schemas & Queries](https://json2vec.github.io/json2vec/guides/model-schemas/)
-- [Model Updates](https://json2vec.github.io/json2vec/guides/model-update/)
+- [AI Quickstart](https://json2vec.github.io/json2vec/ai-quickstart/)
+- [Why `json2vec`](https://json2vec.github.io/json2vec/motivation/)
+- [Query Paths](https://json2vec.github.io/json2vec/core-concepts/querypaths/)
+- [Built-In Data Types](https://json2vec.github.io/json2vec/core-concepts/data-types/)
+- [Learning Modes & Embeddings](https://json2vec.github.io/json2vec/core-concepts/embeddings/)
+- [Model Tree](https://json2vec.github.io/json2vec/core-concepts/model-tree/)
+- [Mutations](https://json2vec.github.io/json2vec/core-concepts/mutations/)
 - [Hello World](https://json2vec.github.io/json2vec/tutorials/hello-world/)
-- [Masked Pretraining](https://json2vec.github.io/json2vec/tutorials/pretraining/)
 - [Nested Supervised Training](https://json2vec.github.io/json2vec/tutorials/nested-supervised-training/)
+- [Masked Pretraining](https://json2vec.github.io/json2vec/tutorials/pretraining/)
 - [Supervised Tabular Training](https://json2vec.github.io/json2vec/tutorials/supervised-tabular-training/)
-- [Field Ablation](https://json2vec.github.io/json2vec/guides/field-ablation/)
+- [Field Importance](https://json2vec.github.io/json2vec/guides/field-importance/)
 - [Preprocessors](https://json2vec.github.io/json2vec/guides/preprocessors/)
-- [Tensorfield Extensions](https://json2vec.github.io/json2vec/guides/tensorfields/)
+- [Custom Data Types](https://json2vec.github.io/json2vec/data-types/tensorfields/)
 - [Serving](https://json2vec.github.io/json2vec/tutorials/serving/)
 - [API Reference](https://json2vec.github.io/json2vec/reference/api/)
 - [Whitepaper](https://json2vec.github.io/json2vec/whitepaper.pdf)
@@ -258,7 +259,7 @@ Configured `dataset.kwargs` are passed into the preprocessor, with unsupported k
 
 Each tensorfield plugin provides a request schema plus the model components
 needed to encode values, decode predictions, compute losses, and optionally
-serialize outputs. See [Tensorfield Extensions](https://json2vec.github.io/json2vec/guides/tensorfields/)
+serialize outputs. See [Custom Data Types](https://json2vec.github.io/json2vec/data-types/tensorfields/)
 for a custom plugin walkthrough. Built-in tensorfields share the base leaf
 options `name`, `query`, `pooling`, `weight`, `n_heads`, `n_linear`, `dropout`,
 `p_mask`, and `p_prune`.

{json2vec-0.4.5 → json2vec-0.4.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "json2vec"
-version = "0.4.5"
+version = "0.4.6"
 description = "{...} -> [*]"
 readme = "README.md"
 license = "Apache-2.0"
@@ -31,9 +31,11 @@ text = [
     "transformers>=4.55.0",
 ]
 docs = [
+    "litserve>=0.2.13",
     "mkdocs-material>=9.6",
     "mkdocs-jupyter>=0.26.3",
     "mkdocstrings[python]>=0.27",
+    "pydantic-settings>=2.10.1",
 ]
 
 [dependency-groups]

{json2vec-0.4.5 → json2vec-0.4.6}/src/json2vec/__init__.py

@@ -1,4 +1,4 @@
-"""Public JSON2Vec SDK surface.
+"""Public `json2vec` SDK surface.
 
 The top-level package exports the constructors and helpers used by most
 applications: `Model.from_schema(...)` for model construction, tensorfield
@@ -6,6 +6,8 @@ request constructors such as `Category` and `Number`, data modules, schema
 mutation predicates, and the `@preprocess` decorator.
 """
 
+from typing import TYPE_CHECKING, Any
+
 from json2vec.architecture.root import (
     Model,
     MutationLockCallback,
@@ -15,6 +17,7 @@ from json2vec.architecture.root import (
     SchedulerConfig,
 )
 from json2vec.data.datasets import PolarsDataModule, StreamingDataModule
+from json2vec.inference.callback import Postprocessor, Writer
 from json2vec.preprocessors import PREPROCESSORS, Preprocessor, PreprocessorMode, preprocess
 from json2vec.structs.enums import AttentionMode, Component, Metric, ShardingStrategy, Strata, Suffix, TensorKey, Tokens
 from json2vec.structs.experiment import (
@@ -37,20 +40,73 @@ from json2vec.tensorfields.extensions.text import Request as Text
 from json2vec.tensorfields.extensions.vector import Request as Vector
 from json2vec.tensorfields.shared.vocabulary import VocabularySyncCallback
 
+if TYPE_CHECKING:
+    from json2vec.inference.deployment import (
+        API,
+        Accelerator,
+        BatchItem,
+        Deployment,
+        ErrorItem,
+        Input,
+        ModelSource,
+        UpdateOperation,
+    )
+
+_SERVING_EXPORTS = {
+    "API",
+    "Accelerator",
+    "BatchItem",
+    "Deployment",
+    "ErrorItem",
+    "Input",
+    "ModelSource",
+    "UpdateOperation",
+}
+
+
+def __getattr__(name: str) -> Any:
+    if name not in _SERVING_EXPORTS:
+        raise AttributeError(f"module 'json2vec' has no attribute {name!r}")
+
+    try:
+        from json2vec.inference import deployment
+    except ModuleNotFoundError as error:
+        if error.name in {"litserve", "pydantic_settings"}:
+            raise ModuleNotFoundError(
+                f"json2vec.{name} requires the serving extra; install with `pip install json2vec[serving]`."
+            ) from error
+        raise
+
+    value = getattr(deployment, name)
+    globals()[name] = value
+    return value
+
+
+def __dir__() -> list[str]:
+    return sorted([*globals(), *_SERVING_EXPORTS])
+
+
 __all__ = [
     "Address",
+    "API",
+    "Accelerator",
     "Array",
     "AttentionMode",
+    "BatchItem",
     "Category",
     "Component",
     "DateParts",
     "DecoderBase",
+    "Deployment",
     "EmbedderBase",
     "Entity",
+    "ErrorItem",
     "Hyperparameters",
+    "Input",
     "Leaf",
     "Metric",
     "Model",
+    "ModelSource",
     "MutationLockCallback",
     "NodeAttribute",
     "NodePredicate",
@@ -59,6 +115,7 @@ __all__ = [
     "PREPROCESSORS",
     "Plugin",
     "PolarsDataModule",
+    "Postprocessor",
     "Preprocessor",
     "PreprocessorMode",
     "RequestBase",
@@ -76,8 +133,10 @@ __all__ = [
     "TensorKey",
     "Text",
     "Tokens",
+    "UpdateOperation",
     "Vector",
     "VocabularySyncCallback",
+    "Writer",
     "predicate",
     "preprocess",
     "where",

{json2vec-0.4.5 → json2vec-0.4.6}/src/json2vec/architecture/checkpoint.py

@@ -1,4 +1,4 @@
-"""Checkpoint serialization helpers for JSON2Vec models."""
+"""Checkpoint serialization helpers for `json2vec` models."""
 
 from __future__ import annotations
 

{json2vec-0.4.5 → json2vec-0.4.6}/src/json2vec/architecture/encoder.py

@@ -76,7 +76,7 @@ class ArrayEncoder(torch.nn.Module):
         self.encoder = torch.nn.ModuleList(layers)
 
         self.pool = LearnedQueryCrossAttention(
-            n_context=array.n_outputs,
+            n_context=1,
             d_model=hyperparameters.d_model,
             nhead=array.n_heads,
             dropout=dropout,

{json2vec-0.4.5 → json2vec-0.4.6}/src/json2vec/architecture/plot.py

@@ -88,7 +88,7 @@ def render_schema_plot(
 ) -> RenderableType:
     hyperparameters = module.hyperparameters
     root = hyperparameters.fields if address is None else resolve_node(hyperparameters=hyperparameters, address=address)
-    title = "JSON2Vec State" if state_focus else "JSON2Vec Schema"
+    title = "json2vec State" if state_focus else "json2vec Schema"
 
     tree = Tree(render_node_label(module=module, node=root, state_focus=state_focus), guide_style="dim")
     append_schema_children(tree=tree, module=module, node=root, detail=detail or state_focus, state_focus=state_focus)
@@ -252,7 +252,6 @@ def node_metadata_keys(node: Node, values: dict[str, Any], state_focus: bool) ->
             "d_model",
             "attention",
             "max_length",
-            "n_outputs",
             "n_layers",
             "n_heads",
             "batch_size",
@@ -267,7 +266,7 @@ def node_metadata_keys(node: Node, values: dict[str, Any], state_focus: bool) ->
     elif isinstance(node, Leaf):
         preferred = ["query", "pooling", "max_vocab_size", "topk", "objective", "weight"]
     else:
-        preferred = ["attention", "max_length", "n_outputs", "n_layers", "n_heads"]
+        preferred = ["attention", "max_length", "n_layers", "n_heads"]
 
     remaining = [key for key in values if key not in preferred]
     return preferred + remaining

{json2vec-0.4.5 → json2vec-0.4.6}/src/json2vec/architecture/root.py

@@ -1,4 +1,4 @@
-"""Public Lightning model facade for JSON2Vec schemas."""
+"""Public Lightning model facade for `json2vec` schemas."""
 
 from collections import Counter
 from collections.abc import Callable, Iterator, Sequence
@@ -20,7 +20,7 @@ from json2vec.architecture.contracts import ContractScheduler
 from json2vec.architecture.graph import ModelGraph
 from json2vec.architecture.mutations import SchemaEditor
 from json2vec.architecture.plot import PlotMode
-from json2vec.architecture.runtime import EvaluationResult, ModelRuntime, Postprocessor, PreprocessFn, step
+from json2vec.architecture.runtime import ModelRuntime, Postprocessor, Preprocessor, step
 from json2vec.data.datasets.base import EncodedBatch, EncodedInput
 from json2vec.structs.enums import AttentionMode, Strata
 from json2vec.structs.experiment import (
@@ -30,7 +30,7 @@ from json2vec.structs.experiment import (
     SchemaField,
 )
 from json2vec.structs.packages import Prediction
-from json2vec.structs.tree import Address, Node, PruneRate, Rate
+from json2vec.structs.tree import Address, Node, Rate
 from json2vec.tensorfields.base import TENSORFIELDS, Plugin, TensorFieldBase
 
 OptimizerConfig = torch.optim.Optimizer | Callable[["Model"], torch.optim.Optimizer]
@@ -138,11 +138,11 @@ class RollbackCheckpoint(ModelCheckpoint):
 
 
 class Model(lit.LightningModule):
-    """Neural model generated from a JSON2Vec schema tree.
+    """Neural model generated from a `json2vec` schema tree.
 
     `Model` owns the schema hyperparameters, tensorfield embedders, array
-    encoders, decoders, and convenience methods for prediction, embedding,
-    checkpointing, plotting, and schema mutation.
+    encoders, decoders, and convenience methods for prediction, checkpointing,
+    plotting, and schema mutation.
 
     Example:
         ```python
@@ -169,16 +169,13 @@ class Model(lit.LightningModule):
         n_heads: int,
         batch_size: int = 1,
         fields: Sequence[SchemaField] | None = None,
-        root: str = "record",
+        name: str = "record",
         description: str | None = None,
         embed: bool = False,
         attention: AttentionMode | str = AttentionMode.mha,
         max_length: int = 1,
-        n_outputs: int = 1,
         n_linear: int = 1,
         dropout: Rate | None = None,
-        p_mask: Rate | None = None,
-        p_prune: PruneRate | None = None,
         optimizer: OptimizerConfig | None = None,
         scheduler: SchedulerConfig | None = None,
     ) -> Self:
@@ -193,16 +190,13 @@ class Model(lit.LightningModule):
             batch_size: Batch size used by data modules, examples, and mocked
                 Lightning input arrays.
             fields: Optional sequence form of `field_args`.
-            root: Root array name. Defaults to `record`.
+            name: Root array name. Defaults to `record`.
             description: Optional description on the generated root array.
             embed: Configure the generated root array as an embedding output.
             attention: Attention mode for the generated root array.
             max_length: Maximum number of records per observation at the root.
-            n_outputs: Number of pooled outputs emitted by the generated root array.
             n_linear: Feed-forward block count on the generated root array.
             dropout: Optional dropout rate on the generated root array.
-            p_mask: Optional mask rate on the generated root array.
-            p_prune: Optional prune rate on the generated root array.
             optimizer: Optimizer instance or factory used by Lightning training.
             scheduler: Optional scheduler config or factory.
 
@@ -215,16 +209,13 @@ class Model(lit.LightningModule):
             n_layers=n_layers,
             n_heads=n_heads,
             fields=fields,
-            root=root,
+            name=name,
             description=description,
             embed=embed,
             attention=attention,
             max_length=max_length,
-            n_outputs=n_outputs,
             n_linear=n_linear,
             dropout=dropout,
-            p_mask=p_mask,
-            p_prune=p_prune,
         )
         return cls(
             hyperparameters=hyperparameters,
@@ -299,7 +290,7 @@ class Model(lit.LightningModule):
         """Mutate selected schema nodes and rebuild compatible modules.
 
         `target=True` is shorthand for `p_prune=1.0`; `target=False` clears
-        target behavior by setting `p_prune=None`.
+        target behavior by setting `p_prune=0.0`.
 
         Args:
             *predicates: Predicates used to select nodes.
@@ -507,7 +498,7 @@ class Model(lit.LightningModule):
         CheckpointState.dump(self, checkpoint)
 
     def restore_checkpoint_state(self, checkpoint: dict[str, Any]) -> None:
-        """Restore this model in place from a JSON2Vec checkpoint dictionary."""
+        """Restore this model in place from a `json2vec` checkpoint dictionary."""
         CheckpointState.restore(self, checkpoint)
 
     @classmethod
@@ -515,16 +506,14 @@ class Model(lit.LightningModule):
         """Load a `Model` checkpoint written by `Model.save(...)`."""
         return cast(Self, CheckpointState.load(cls, checkpoint))
 
-    def write(
-        self, predictions: list[Prediction]
-    ) -> tuple[dict[Address, dict[str, Any]], dict[Address, dict[str, Any]]]:
+    def write(self, predictions: list[Prediction]) -> dict[Address, dict[str, Any]]:
         return ModelRuntime.write(self, predictions)
 
     @immutable("inference")
     def encode(
         self,
         batch: EncodedBatch | list[dict[str, Any]],
-        preprocess: PreprocessFn | None = None,
+        preprocess: Preprocessor | None = None,
         strata: Strata | str = Strata.predict,
     ) -> EncodedInput:
         """Return encoded tensorfield inputs for raw or processed observations."""
@@ -536,52 +525,19 @@ class Model(lit.LightningModule):
         )
 
     @immutable("inference")
-    def evaluate(
-        self,
-        batch: EncodedBatch | list[dict[str, Any]],
-        preprocess: PreprocessFn | None = None,
-        postprocess: Postprocessor | None = None,
-    ) -> EvaluationResult:
-        """Run prediction and embedding for encoded or raw observations.
-
-        If `preprocess` is omitted, raw records are encoded unchanged.
-        """
-        return ModelRuntime.evaluate(
-            self,
-            batch=batch,
-            preprocess=preprocess,
-            postprocess=postprocess,
-        )
-
     def predict(
         self,
         batch: EncodedBatch | list[dict[str, Any]],
-        preprocess: PreprocessFn | None = None,
+        preprocess: Preprocessor | None = None,
         postprocess: Postprocessor | None = None,
     ) -> dict[Address, dict[str, Any]]:
-        """Return typed predictions for a raw or encoded batch."""
-
-        result = self.evaluate(
-            batch=batch,
-            preprocess=preprocess,
-            postprocess=postprocess,
-        )
-
-        return result.predictions
-
-    def embed(
-        self,
-        batch: EncodedBatch | list[dict[str, Any]],
-        preprocess: PreprocessFn | None = None,
-        postprocess: Postprocessor | None = None,
-    ) -> dict[Address, dict[str, Any]]:
-        """Return configured embeddings for a raw or encoded batch."""
-        result = self.evaluate(
+        """Return typed predictions and configured embeddings for a raw or encoded batch."""
+        return ModelRuntime.predict(
+            self,
             batch=batch,
             preprocess=preprocess,
             postprocess=postprocess,
         )
-        return result.embeddings
 
     training_step = partialmethod(step, strata=Strata.train)
     validation_step = partialmethod(step, strata=Strata.validate)