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

# mellea.formatters.granite.intrinsics.output

> Classes and functions that implement common aspects of output processing for intrinsics.

export const SidebarFix = () => <script dangerouslySetInnerHTML={{
  __html: `
        (function () {
          const INTERVAL_MS = 500;

          const upgradeSidebar = () => {
            const links = document.querySelectorAll('a[href^="#"]');

            links.forEach((link) => {
              if (link.dataset.badged === "true") return;

              const rawText = (link.textContent || "").trim();

              // ========== FUNC ==========
              if (rawText.startsWith("FUNC ")) {
                const label = rawText.replace(/^FUNC\\s+/, "").trim();

                while (link.firstChild) link.removeChild(link.firstChild);

                // 👉 Make the whole link a single flex row & prevent wrapping
                link.style.display = "flex";
                link.style.alignItems = "center";
                link.style.whiteSpace = "nowrap";
                link.style.columnGap = "0.5rem";

                const badge = document.createElement("span");
                badge.style.marginRight = "0.5rem";
                badge.style.display = "inline-flex";
                badge.style.alignItems = "center";
                badge.style.borderRadius = "9999px";
                badge.style.padding = "0rem 0.6rem";
                badge.style.fontSize = "0.5rem";
                badge.style.fontWeight = "700";
                badge.style.letterSpacing = "0.05em";
                badge.style.backgroundColor = "rgba(48, 100, 227, 0.20)";
                badge.style.color = "#1D4ED8";

                badge.textContent = "FUNC";

                link.appendChild(badge);
                link.appendChild(document.createTextNode(label));
                link.dataset.badged = "true";
                return;
              }

              // ========== CLASS ==========
              if (rawText.startsWith("CLASS ")) {
                const label = rawText.replace(/^CLASS\\s+/, "").trim();

                while (link.firstChild) link.removeChild(link.firstChild);

                // 👉 Same flex / nowrap treatment for class links
                link.style.display = "flex";
                link.style.alignItems = "center";
                link.style.whiteSpace = "nowrap";
                link.style.columnGap = "0.5rem";

                const badge = document.createElement("span");
                badge.style.marginRight = "0.5rem";
                badge.style.display = "inline-flex";
                badge.style.alignItems = "center";
                badge.style.borderRadius = "9999px";
                badge.style.padding = "0rem 0.6rem";
                badge.style.fontSize = "0.5rem";
                badge.style.fontWeight = "700";
                badge.style.letterSpacing = "0.05em";
                badge.style.backgroundColor = "rgba(74, 222, 128, 0.20)";
                badge.style.color = "#15803D";

                badge.textContent = "CLASS";

                link.appendChild(badge);
                link.appendChild(document.createTextNode(label));
                link.dataset.badged = "true";
                return;
              }
            });
          };

          upgradeSidebar();
          setInterval(upgradeSidebar, INTERVAL_MS);
        })();
      `
}} />;

<SidebarFix />

Classes and functions that implement common aspects of output processing for intrinsics.

## Classes

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `TransformationRule` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L41" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Base class for transformation rules to apply to JSON outputs of intrinsics.

**Args:**

* `config`: Configuration of the parent output processor, as parsed YAML.
* `input_path_expr`: Path expression matching all
  instances of the field that this rule transforms. Elements can be
  strings for object fields, integers for list indices, or `None`
  for wildcard matches.

**Attributes:**

* `YAML_NAME`: The name used to identify this rule in YAML
  configuration files. Subclasses must set this to a non-`None` string.

<div className="h-8" />

**Methods:**

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

#### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#3064E3]/20 text-[#1D4ED8]">FUNC</span> `rule_name` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L100" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

```python theme={null}
rule_name(self) -> str
```

Return the YAML name that identifies this transformation rule.

**Returns:**

* The value of `YAML_NAME` for this rule subclass.

**Raises:**

* `ValueError`: If `YAML_NAME` has not been set by the subclass.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

#### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#3064E3]/20 text-[#1D4ED8]">FUNC</span> `apply` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L130" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

```python theme={null}
apply(self, parsed_json: Any, reparsed_json: Any, logprobs: ChatCompletionLogProbs | None, chat_completion: ChatCompletion | None) -> Any
```

Apply this transformation rule to the parsed model output.

**Args:**

* `parsed_json`: Output of running model results through
  :func:`json.loads()`, plus applying zero or more prior
  transformation rules.
* `reparsed_json`: Output of running the same model results
  through :func:`json_util.reparse_json_with_offsets()`,
  preserving position information on literal values.
* `logprobs`: Optional logprobs result
  associated with the original model output string, or `None`
  if no logprobs were present.
* `chat_completion`: The chat completion request
  that produced this output. Required by some rules.

**Returns:**

* Transformed copy of `parsed_json` after applying this rule.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `InPlaceTransformation` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L188" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Base class for TransformationRules that replace values in place in JSON.

Base class for `TransformationRule`s that replace values in place in the source
JSON. The values replaced can be a scalar, object, or list.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `AddFieldsTransformation` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L218" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Base class for TransformationRules that add values to JSON.

Base class for `TransformationRule`s that add one or more values adjacent to
an existing value in the source JSON.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `TokenToFloat` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L279" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Transformation rule that decodes token logprobs to a floating point number.

The floating point number replaces the original categorical value in the JSON.

**Args:**

* `config`: Configuration of the parent output processor, as parsed YAML.
* `input_path_expr`: Path expression matching all
  instances of the field that this rule transforms.
* `categories_to_values`: Mapping
  from categorical labels to floating-point values. Defaults to
  `None`.

**Attributes:**

* `YAML_NAME`: YAML configuration key for this rule; always
  `"likelihood"`.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `DecodeSentences` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L481" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Transformation rule that decodes sentence refs into begin, end, text tuples.

**Args:**

* `config`: Configuration of the parent output processor, as parsed YAML.
* `input_path_expr`: Path expression matching all
  instances of the field that this rule transforms.
* `source`: Name of the location to look for sentences; must be
  `"last_message"` or `"documents"`.
* `output_names`: Mapping from output role name (`"begin"`,
  `"end"`, `"text"`, `"document_id"`) to the name of the new
  field to add in the result JSON.

**Attributes:**

* `YAML_NAME`: YAML configuration key for this rule; always
  `"decode_sentences"`.
* `begin_name`: Name of the output field that receives the
  sentence begin offset; extracted from `output_names`, or `None`
  if not configured.
* `end_name`: Name of the output field that receives the
  sentence end offset; extracted from `output_names`, or `None`
  if not configured.
* `text_name`: Name of the output field that receives the
  sentence text; extracted from `output_names`, or `None` if not
  configured.
* `document_id_name`: Name of the output field that receives
  the document ID (only used when `source="documents"`); extracted
  from `output_names`, or `None` if not configured.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `Explode` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L726" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Expand list-valued attributes in a list of records.

Turn each row in a list of records into zero or more rows by expanding
the elements of a list-valued attribute.

**Attributes:**

* `YAML_NAME`: YAML configuration key for this rule; always
  `"explode"`.
* `target_field`: Name of the list-valued field within each record
  to expand.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `DropDuplicates` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L797" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Remove duplicate records from a list of records.

**Attributes:**

* `YAML_NAME`: YAML configuration key for this rule; always
  `"drop_duplicates"`.
* `target_fields`: Names of fields used to determine whether two
  records are considered duplicates.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `Project` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L851" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Project records down to a specified set of fields.

Project records down to a specified set of fields.  Can also rename the
retained fields.

**Attributes:**

* `YAML_NAME`: YAML configuration key for this rule; always
  `"project"`.
* `retained_fields`: Mapping from original field name to the
  (possibly renamed) output field name. Initialized from either a
  list of field names (identity mapping) or an explicit mapping.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `Nest` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L905" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Convert a value within a JSON structure into a record with a single field.

**Attributes:**

* `YAML_NAME`: YAML configuration key for this rule; always
  `"nest"`.
* `field_name`: Name of the single field in the output JSON object
  that wraps each matching value.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `MergeSpans` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L936" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Merge adjacent spans into larger spans.

**Args:**

* `config`: Parsed YAML config for IO processing.
* `input_path_expr`: Path expression for the list of records to merge.
* `group_fields`: List of fields used for grouping prior to merging
  spans.
* `begin_field`: Name of the field that holds the begin offset of
  spans.
* `end_field`: Name of the field that holds the end offset of spans.
* `text_field`: Optional field containing covered text strings
  that should be concatenated when spans are merged. Defaults to
  `None`.

**Attributes:**

* `YAML_NAME`: YAML configuration key for this rule; always
  `"merge_spans"`.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `IntrinsicsResultProcessor` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/intrinsics/output.py#L1202" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

General-purpose chat completion result processor for intrinsics.

General-purpose chat completion result processor for use with the models that
implement intrinsics. Reads parameters of the model's input and output formats
from a YAML configuration file and edits the input chat completion appropriately.

**Attributes:**

* `config`: Parsed YAML configuration file for the target intrinsic.
* `rules`: Ordered list of transformation rules
  that this processor applies to each choice in a chat completion
  response.

**Args:**

* `config_file`: Optional path to a YAML
  configuration file. Exactly one of `config_file` and
  `config_dict` must be provided.
* `config_dict`: Optional pre-parsed YAML configuration dict.
  Exactly one of `config_file` and `config_dict` must be
  provided.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />