Gradio
在 `Hugging Face Spaces` 上有數千個 `Gradio` 應用程式。這個函式庫讓你的 LLM 能夠輕鬆運用它們 🦾
具體來說，`gradio-tools` 是一個 Python 函式庫，用於將 `Gradio` 應用程式轉換為工具，這些工具可以被基於大型語言模型 (LLM) 的代理程式利用，以完成其任務。例如，LLM 可以使用 `Gradio` 工具來轉錄它在線上找到的語音錄音，然後為你總結。或者，它可以使用另一個 `Gradio` 工具對你 Google Drive 上的文件應用 OCR，然後回答關於它的問題。
如果你想使用一個不是預先建立的工具的空間，創建你自己的工具非常容易。請參閱 gradio-tools 文件的這個章節，以獲取關於如何做到這一點的資訊。歡迎所有貢獻！
%pip install --upgrade --quiet gradio_tools langchain-community
使用工具
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)
在代理程式中使用
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 ✔
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
Thought: Do I need to use a tool? Yes
Action: StableDiffusionPromptGenerator
Action Input: A dog riding a skateboard[0m
Job Status: Status.STARTING eta: None
Observation: [38;5;200m[1;3mA dog riding a skateboard, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha[0m
Thought:[32;1m[1;3m 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[0m
Job Status: Status.STARTING eta: None
Job Status: Status.PROCESSING eta: None
Observation: [36;1m[1;3m/Users/harrisonchase/workplace/langchain/docs/modules/agents/tools/integrations/2e280ce4-4974-4420-8680-450825c31601/tmpfmiz2g1c.jpg[0m
Thought:[32;1m[1;3m 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[0m
Job Status: Status.STARTING eta: None
Observation: [33;1m[1;3ma painting of a dog sitting on a skateboard[0m
Thought:[32;1m[1;3m Do I need to use a tool? Yes
Action: TextToVideo
Action Input: a painting of a dog sitting on a skateboard[0m
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: [31;1m[1;3m/var/folders/bm/ylzhm36n075cslb9fvvbgq640000gn/T/tmp5snj_nmzf20_cb3m.mp4[0m
Thought:[32;1m[1;3m Do I need to use a tool? No
AI: Here is a video of a painting of a dog sitting on a skateboard.[0m
[1m> Finished chain.[0m