> ## 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.core.backend

> Abstract `Backend` interface and generation-walk utilities.

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 />

Abstract `Backend` interface and generation-walk utilities.

Defines the `Backend` abstract base class whose two key abstract methods —
`generate_from_context` (context-aware single-action generation) and
`generate_from_raw` (context-free batch generation) — all concrete backends must
implement. Also provides `generate_walk`, which traverses a [`Component`](base#class-component) tree to
find un-computed [`ModelOutputThunk`](base#class-modeloutputthunk) leaves that need to be resolved before rendering.

## Functions

<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> `generate_walk` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/core/backend.py#L211" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

```python theme={null}
generate_walk(c: CBlock | Component | ModelOutputThunk) -> list[ModelOutputThunk]
```

Return all uncomputed [`ModelOutputThunk`](base#class-modeloutputthunk) leaves reachable from `c`.

**Args:**

* `c`: A [`CBlock`](base#class-cblock), [`Component`](base#class-component), or [`ModelOutputThunk`](base#class-modeloutputthunk) to traverse.

**Returns:**

* A flat list of uncomputed [`ModelOutputThunk`](base#class-modeloutputthunk) instances in the order
* they need to be resolved (depth-first over `Component.parts()`).

**Raises:**

* `ValueError`: If any element encountered during traversal is not a [`CBlock`](base#class-cblock),
  [`Component`](base#class-component), or [`ModelOutputThunk`](base#class-modeloutputthunk).

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

## 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> `Backend` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/core/backend.py#L42" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Abstract base class for all inference backends.

All concrete backends must implement `generate_from_context` (context-aware
single-action generation) and `generate_from_raw` (context-free batch
generation). The `do_generate_walk` / `do_generate_walks` helpers can be
used to pre-compute any unresolved [`ModelOutputThunk`](base#class-modeloutputthunk) leaves before rendering.

<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> `generate_from_context` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/core/backend.py#L52" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

```python theme={null}
generate_from_context(self, action: Component[C] | CBlock, ctx: Context) -> tuple[ModelOutputThunk[C], Context]
```

Generates a model output from a context. May not mutate the context. This must be called from a running event loop as it creates a task to run the generation request.

**Args:**

* `action`: The last item of the context should be passed in as an `action` instead of as part of the `ctx`. See `docs/dev/generate_signature_decisions.md`.
* `ctx`: The rest of the context.
* `format`: A response format to used for structured outputs / constrained decoding.
* `model_options`: Any model options to upsert into the defaults for this call.
* `tool_calls`: If `True`, then tool calls are extracts from the `action` [`Component`](base#class-component). Assumption: if tool\_calls is enabled, then the action [`Component`](base#class-component) has a TemplateRepresentation

**Returns:**

* a tuple of (ModelOutputThunk, Context) where the Context is the new context after the generation has been completed.

<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> `generate_from_raw` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/core/backend.py#L124" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

```python theme={null}
generate_from_raw(self, actions: list[Component[C]], ctx: Context) -> list[ModelOutputThunk[C]]
```

<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> `generate_from_raw` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/core/backend.py#L135" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

```python theme={null}
generate_from_raw(self, actions: list[Component[C] | CBlock], ctx: Context) -> list[ModelOutputThunk[C | str]]
```

<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> `generate_from_raw` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/core/backend.py#L146" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

```python theme={null}
generate_from_raw(self, actions: Sequence[Component[C] | CBlock], ctx: Context) -> list[ModelOutputThunk]
```

Generates a model output from the provided input. Does not use context or templates.

**Args:**

* `actions`: list of actions to generate responses for. Each action is separate.
* `ctx`: context passed to generation. Currently not used in generate\_from\_raw
* `format`: A response format to used for structured outputs / constrained decoding. Note: some backends do not support this parameter. They will log warnings and continue to generate.
* `model_options`: Any model options to upsert into the defaults for this call.
* `tool_calls`: Always set to false unless supported by backend.

**Returns:**

* list\[ModelOutputThunk]: A list of output thunks, one per action, in the same order as `actions`.

<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> `do_generate_walk` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/core/backend.py#L168" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

```python theme={null}
do_generate_walk(self, action: CBlock | Component | ModelOutputThunk) -> None
```

Awaits all uncomputed [`ModelOutputThunk`](base#class-modeloutputthunk) leaves reachable from `action`.

Traverses the component tree rooted at `action` via `generate_walk`, collects
any uncomputed [`ModelOutputThunk`](base#class-modeloutputthunk) nodes, and concurrently awaits them all.

**Args:**

* `action`: The root node to traverse.

<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> `do_generate_walks` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/core/backend.py#L188" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

```python theme={null}
do_generate_walks(self, actions: list[CBlock | Component | ModelOutputThunk]) -> None
```

Awaits all uncomputed [`ModelOutputThunk`](base#class-modeloutputthunk) leaves reachable from each action in `actions`.

Traverses the component tree of every action in the list via `generate_walk`, collects
all uncomputed [`ModelOutputThunk`](base#class-modeloutputthunk) nodes across all actions, and concurrently awaits them.

**Args:**

* `actions`: The list of root nodes to traverse.

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