Recognize and locate instances of an object in an image with a local vision LLM. Wraps kuzco's tool_llm_image_recognition() ellmer tool. Use when the task needs finding, counting, or locating specific objects (faces, cars, animals) in an image.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Recognize and locate instances of an object in an image using a local vision language model, exposed as an ellmer tool by the kuzco R package.
The user wants to find a specific kind of object in an image: faces, cars, dogs, text regions. Counting instances and describing/locating each one. For general "what is in this image?" questions, use kuzco-classification instead.
library(kuzco)
library(ellmer)
chat <- chat_ollama(model = "qwen2.5vl")
chat$register_tool(tool_llm_image_recognition())
image (required): local file path to a jpeg, jpg, or png image.recognize_object (optional): the object to recognize, e.g. "face", "car", "dog".
Defaults to "face".additional_prompt (optional): extra instructions, e.g. "only count adults".language (optional): output language, e.g. "English".Compact JSON text with object_recognized, object_count, object_description,
and object_location. Report the count first, then describe/locate instances.
If the count is zero, say so plainly rather than hedging.
User: "How many faces are in img/group.jpg and where?"
- Call
kuzco_image_recognitionwithimage = "img/group.jpg",recognize_object = "face".- Report the count and describe each location.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Generate accessibility alt text for an image with a local vision LLM. Wraps kuzco's tool_llm_image_alt_text() ellmer tool. Use when the task needs a short textual description of an image, e.g. for accessibility, captions, or image indexing.
日本語の概要は準備中です。原文の説明を表示しています。
Classify an image and describe its contents with a local vision LLM. Wraps kuzco's tool_llm_image_classification() ellmer tool. Use when the task needs image classification, object identification, or a structured description of what an image contains.
日本語の概要は準備中です。原文の説明を表示しています。
Run a custom computer-vision prompt against an image with a local vision LLM. Wraps kuzco's tool_llm_image_custom() ellmer tool. Use when none of the specialized kuzco image skills (classification, OCR, recognition, sentiment, alt text) fit the task.
日本語の概要は準備中です。原文の説明を表示しています。
Extract text visible in an image (OCR) with a local vision LLM. Wraps kuzco's tool_llm_image_extract_text() ellmer tool. Use when the task needs reading text from screenshots, documents, signs, labels, or any image containing writing.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze the sentiment or mood conveyed by an image with a local vision LLM. Wraps kuzco's tool_llm_image_sentiment() ellmer tool. Use when the task needs the emotional tone of an image, e.g. for content moderation, marketing, or curation.
日本語の概要は準備中です。原文の説明を表示しています。