> ## 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.granite3.granite33.output

> Parser which receives Granite 3.3 model output and returns the constituents of the output.

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 />

Parser which receives Granite 3.3 model output and returns the constituents of the output.

The output from the lowest level of the parser is a dictionary as follows:

* "citations": List of citations
* "docs": List of document references
* "hallucinations": List of hallucinations
* "response": Model response text without the above constituents

This dict is further refined into dataclasses before being returned as an extended
`AssistantMessage`.

## 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> `Granite33OutputProcessor` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/granite3/granite33/output.py#L533" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Output processor for version 3.3 of the main Granite models, all sizes.

<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> `transform` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/formatters/granite/granite3/granite33/output.py#L536" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

```python theme={null}
transform(self, model_output: str, chat_completion: ChatCompletion | None = None) -> AssistantMessage
```

Parse Granite 3.3 model output into a structured assistant message.

**Args:**

* `model_output`: Raw text output from the Granite 3.3 model.
* `chat_completion`: The original chat completion
  request that produced `model_output`. Used to determine which
  output features (thinking, tools, citations, hallucinations) to
  parse. Defaults to `None`.

**Returns:**

* A :class:`Granite3AssistantMessage` containing the
  parsed response text, optional tool calls, chain-of-thought
  reasoning, citations, documents, and hallucination annotations.

**Raises:**

* `ValueError`: If parsing citations, documents, or hallucinations from
  the model output fails.

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