Hugging Face Spaces에는 수천 개의 Gradio 앱이 있습니다. 이 라이브러리는 이러한 앱들을 LLM의 손끝에 가져다 놓습니다 🦾 구체적으로, gradio-tools는 Gradio 앱을 대규모 언어 모델(LLM) 기반 agent가 작업을 완료하는 데 활용할 수 있는 tool로 변환하는 Python 라이브러리입니다. 예를 들어, LLM은 Gradio tool을 사용하여 온라인에서 찾은 음성 녹음을 전사하고 요약할 수 있습니다. 또는 다른 Gradio tool을 사용하여 Google Drive의 문서에 OCR을 적용하고 이에 대한 질문에 답변할 수 있습니다. 사전 구축된 tool이 아닌 space를 사용하고 싶다면 자신만의 tool을 만드는 것은 매우 쉽습니다. 이를 수행하는 방법에 대한 정보는 gradio-tools 문서의 해당 섹션을 참조하세요. 모든 기여를 환영합니다! 
pip install -qU  gradio_tools langchain-community

​
tool 사용하기

from gradio_tools.tools import StableDiffusionTool

local_file_path = StableDiffusionTool().langchain.run(
    "Please create a photo of a dog riding a skateboard"
)
local_file_path

Loaded as API: https://gradio-client-demos-stable-diffusion.hf.space ✔

Job Status: Status.STARTING eta: None

'/Users/harrisonchase/workplace/langchain/docs/modules/agents/tools/integrations/b61c1dd9-47e2-46f1-a47c-20d27640993d/tmp4ap48vnm.jpg'

from PIL import Image

im = Image.open(local_file_path)

from IPython.display import display

display(im)

​
agent 내에서 사용하기

from gradio_tools.tools import (
    ImageCaptioningTool,
    StableDiffusionPromptGeneratorTool,
    StableDiffusionTool,
    TextToVideoTool,
)
from langchain.agents import initialize_agent
from langchain.memory import ConversationBufferMemory
from langchain_openai import OpenAI

llm = OpenAI(temperature=0)
memory = ConversationBufferMemory(memory_key="chat_history")
tools = [
    StableDiffusionTool().langchain,
    ImageCaptioningTool().langchain,
    StableDiffusionPromptGeneratorTool().langchain,
    TextToVideoTool().langchain,
]


agent = initialize_agent(
    tools, llm, memory=memory, agent="conversational-react-description", verbose=True
)
output = agent.run(
    input=(
        "Please create a photo of a dog riding a skateboard "
        "but improve my prompt prior to using an image generator."
        "Please caption the generated image and create a video for it using the improved prompt."
    )
)

Loaded as API: https://gradio-client-demos-stable-diffusion.hf.space ✔
Loaded as API: https://taesiri-blip-2.hf.space ✔
Loaded as API: https://microsoft-promptist.hf.space ✔
Loaded as API: https://damo-vilab-modelscope-text-to-video-synthesis.hf.space ✔


> Entering new AgentExecutor chain...

Thought: Do I need to use a tool? Yes
Action: StableDiffusionPromptGenerator
Action Input: A dog riding a skateboard
Job Status: Status.STARTING eta: None

Observation: A dog riding a skateboard, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha
Thought: Do I need to use a tool? Yes
Action: StableDiffusion
Action Input: A dog riding a skateboard, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha
Job Status: Status.STARTING eta: None

Job Status: Status.PROCESSING eta: None

Observation: /Users/harrisonchase/workplace/langchain/docs/modules/agents/tools/integrations/2e280ce4-4974-4420-8680-450825c31601/tmpfmiz2g1c.jpg
Thought: Do I need to use a tool? Yes
Action: ImageCaptioner
Action Input: /Users/harrisonchase/workplace/langchain/docs/modules/agents/tools/integrations/2e280ce4-4974-4420-8680-450825c31601/tmpfmiz2g1c.jpg
Job Status: Status.STARTING eta: None

Observation: a painting of a dog sitting on a skateboard
Thought: Do I need to use a tool? Yes
Action: TextToVideo
Action Input: a painting of a dog sitting on a skateboard
Job Status: Status.STARTING eta: None
Due to heavy traffic on this app, the prediction will take approximately 73 seconds.For faster predictions without waiting in queue, you may duplicate the space using: Client.duplicate(damo-vilab/modelscope-text-to-video-synthesis)

Job Status: Status.IN_QUEUE eta: 73.89824726581574
Due to heavy traffic on this app, the prediction will take approximately 42 seconds.For faster predictions without waiting in queue, you may duplicate the space using: Client.duplicate(damo-vilab/modelscope-text-to-video-synthesis)

Job Status: Status.IN_QUEUE eta: 42.49370198879602

Job Status: Status.IN_QUEUE eta: 21.314297944849187

Observation: /var/folders/bm/ylzhm36n075cslb9fvvbgq640000gn/T/tmp5snj_nmzf20_cb3m.mp4
Thought: Do I need to use a tool? No
AI: Here is a video of a painting of a dog sitting on a skateboard.

> Finished chain.
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I