Skip to main content

Gradio

There are many 1000s of Gradio apps on Hugging Face Spaces. This library puts them at the tips of your LLM's fingers 🦾

Specifically, gradio-tools is a Python library for converting Gradio apps into tools that can be leveraged by a large language model (LLM)-based agent to complete its task. For example, an LLM could use a Gradio tool to transcribe a voice recording it finds online and then summarize it for you. Or it could use a different Gradio tool to apply OCR to a document on your Google Drive and then answer questions about it.

It's very easy to create you own tool if you want to use a space that's not one of the pre-built tools. Please see this section of the gradio-tools documentation for information on how to do that. All contributions are welcome!

%pip install --upgrade --quiet  gradio_tools

Using a tool

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)

Using within an agent

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.

Was this page helpful?


You can leave detailed feedback on GitHub.