# TASK GUIDES

- [NATURAL LANGUAGE PROCESSING](https://boinc-ai.gitbook.io/transformers/task-guides/natural-language-processing.md)
- [Text classification](https://boinc-ai.gitbook.io/transformers/task-guides/natural-language-processing/text-classification.md)
- [Token classification](https://boinc-ai.gitbook.io/transformers/task-guides/natural-language-processing/token-classification.md)
- [Question answering](https://boinc-ai.gitbook.io/transformers/task-guides/natural-language-processing/question-answering.md)
- [Causal language modeling](https://boinc-ai.gitbook.io/transformers/task-guides/natural-language-processing/causal-language-modeling.md)
- [Masked language modeling](https://boinc-ai.gitbook.io/transformers/task-guides/natural-language-processing/masked-language-modeling.md)
- [Translation](https://boinc-ai.gitbook.io/transformers/task-guides/natural-language-processing/translation.md)
- [Summarization](https://boinc-ai.gitbook.io/transformers/task-guides/natural-language-processing/summarization.md)
- [Multiple choice](https://boinc-ai.gitbook.io/transformers/task-guides/natural-language-processing/multiple-choice.md)
- [AUDIO](https://boinc-ai.gitbook.io/transformers/task-guides/audio.md)
- [Audio classification](https://boinc-ai.gitbook.io/transformers/task-guides/audio/audio-classification.md)
- [Automatic speech recognition](https://boinc-ai.gitbook.io/transformers/task-guides/audio/automatic-speech-recognition.md)
- [COMPUTER VISION](https://boinc-ai.gitbook.io/transformers/task-guides/computer-vision.md)
- [Image classification](https://boinc-ai.gitbook.io/transformers/task-guides/computer-vision/image-classification.md)
- [Semantic segmentation](https://boinc-ai.gitbook.io/transformers/task-guides/computer-vision/semantic-segmentation.md)
- [Video classification](https://boinc-ai.gitbook.io/transformers/task-guides/computer-vision/video-classification.md)
- [Object detection](https://boinc-ai.gitbook.io/transformers/task-guides/computer-vision/object-detection.md)
- [Zero-shot object detection](https://boinc-ai.gitbook.io/transformers/task-guides/computer-vision/zero-shot-object-detection.md)
- [Zero-shot image classification](https://boinc-ai.gitbook.io/transformers/task-guides/computer-vision/zero-shot-image-classification.md)
- [Depth estimation](https://boinc-ai.gitbook.io/transformers/task-guides/computer-vision/depth-estimation.md)
- [MULTIMODAL](https://boinc-ai.gitbook.io/transformers/task-guides/multimodal.md)
- [Image captioning](https://boinc-ai.gitbook.io/transformers/task-guides/multimodal/image-captioning.md)
- [Document Question Answering](https://boinc-ai.gitbook.io/transformers/task-guides/multimodal/document-question-answering.md)
- [Visual Question Answering](https://boinc-ai.gitbook.io/transformers/task-guides/multimodal/visual-question-answering.md)
- [Text to speech](https://boinc-ai.gitbook.io/transformers/task-guides/multimodal/text-to-speech.md)
- [GENERATION](https://boinc-ai.gitbook.io/transformers/task-guides/generation.md)
- [Customize the generation strategy](https://boinc-ai.gitbook.io/transformers/task-guides/generation/customize-the-generation-strategy.md)
- [PROMPTING](https://boinc-ai.gitbook.io/transformers/task-guides/prompting.md)
- [Image tasks with IDEFICS](https://boinc-ai.gitbook.io/transformers/task-guides/prompting/image-tasks-with-idefics.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://boinc-ai.gitbook.io/transformers/task-guides.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.