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

# LLM Query Action

> Run a direct LLM query without browser context

`misc_action.llm_query` sends a prompt directly to an LLM and stores the structured response—no browser state, axtree, or screenshot is involved.

## Overview

* **Use when**: You need to transform, classify, or reason over data already in memory (e.g., reformat an extracted date, classify extracted text, compute a derived value).
* **Execution**: The action sends `prompt_instructions` to the configured LLM, parses the response according to `output_format`, and stores results in `output_data`. Specified fields are optionally promoted to `generated_variables`.
* **No browser access**: Unlike `extraction_action.llm`, this action does not read the current page. Reference earlier extracted values via `{variable_name[index]}` in your prompt.

## Properties

| Property                | Type                                  | Default              | Description                                        |
| ----------------------- | ------------------------------------- | -------------------- | -------------------------------------------------- |
| `output_format`         | `dict`                                | Required             | Expected output structure as a type-annotated dict |
| `prompt_instructions`   | `str`                                 | Required             | The full prompt to send to the LLM                 |
| `output_variable_names` | `list[str] \| None`                   | `None`               | Promote response fields to `generated_variables`   |
| `llm_provider`          | `"gemini" \| "anthropic" \| "openai"` | `"gemini"`           | LLM provider                                       |
| `llm_model_name`        | `str`                                 | `"gemini-2.5-flash"` | Model name                                         |

## JSON Example

```json theme={null}
{
  "type": "action_node",
  "misc_action": {
    "llm_query": {
      "output_format": {
        "category": "str",
        "confidence": "str"
      },
      "prompt_instructions": "Classify the following support ticket as 'billing', 'technical', or 'other'. Ticket: {ticket_text[0]}",
      "output_variable_names": ["category"]
    }
  }
}
```

## Output Format

Define the expected response structure with Python type hints:

```json theme={null}
{
  "output_format": {
    "summary": "str",
    "status": "str",
    "items": "List[str]"
  }
}
```

<Info>
  Only `str` and `List[str]` are supported types in `output_format`.
</Info>

## Using Variables in Prompts

Reference extracted values from earlier nodes using `{variable_name[index]}`:

```json theme={null}
{
  "misc_action": {
    "llm_query": {
      "output_format": { "normalized_date": "str" },
      "prompt_instructions": "Reformat this date to ISO 8601 (YYYY-MM-DD): {raw_date[0]}",
      "output_variable_names": ["normalized_date"]
    }
  }
}
```

After this action, `{normalized_date[0]}` is available in subsequent nodes.

## Storing Output as Variables

Set `output_variable_names` to promote response fields into `generated_variables`:

```json theme={null}
{
  "misc_action": {
    "llm_query": {
      "output_format": {
        "next_url": "str",
        "has_more_pages": "str"
      },
      "prompt_instructions": "Given these pagination links: {page_links[0]}, return the next page URL and whether more pages exist ('true'/'false').",
      "output_variable_names": ["next_url", "has_more_pages"]
    }
  }
}
```

<Warning>
  Every key in `output_variable_names` must appear in `output_format`. Validation fails at schema load time if a key is missing.
</Warning>

## Choosing a Provider and Model

| Provider    | Models                                           | Notes                   |
| ----------- | ------------------------------------------------ | ----------------------- |
| `gemini`    | `gemini-2.5-flash`, `gemini-2.5-pro`             | Default; cost-effective |
| `anthropic` | `claude-sonnet-4-6`, `claude-haiku-4-5-20251001` | Strong reasoning        |
| `openai`    | `gpt-4o`, `gpt-4o-mini`                          | OpenAI models           |

If `llm_provider` and `llm_model_name` are omitted, the task-level defaults are used.

## LLM Query vs LLM Extraction

|                    | `misc_action.llm_query`                        | `extraction_action.llm`                        |
| ------------------ | ---------------------------------------------- | ---------------------------------------------- |
| Browser context    | None — prompt only                             | axtree and/or screenshot of current page       |
| Typical use        | Transform / classify in-memory data            | Extract data from the page the browser is on   |
| Input source       | Variables embedded in the prompt               | Live page content                              |
| Output destination | `output_data` + optional `generated_variables` | `output_data` + optional `generated_variables` |

<Tip>
  Use `misc_action.llm_query` after an extraction step to post-process or validate extracted data without consuming a browser round-trip.
</Tip>