Gradio 工具
Hugging Face Spaces 上有成千上万个 Gradio 应用程序。这个库让它们可以方便地在语言模型的指尖上使用🦾
具体来说，gradio-tools 是一个 Python 库，用于将 Gradio 应用程序转换为可以被大型语言模型（LLM）代理程序利用的工具，以完成其任务。例如，一个 LLM 可以使用 Gradio 工具对其在网上找到的语音录音进行转录，然后为您进行摘要。或者它可以使用另一个 Gradio 工具对您在 Google Drive 上的文档进行 OCR，然后回答相关问题。
如果您想使用一个非预构建的工具空间，创建自己的工具非常容易。请参阅 gradio-tools 文档的相关部分，了解如何操作。欢迎您的所有贡献！
# !pip install gradio_tools
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/examples/b61c1dd9-47e2-46f1-a47c-20d27640993d/tmp4ap48vnm.jpg'
from PIL import Image
im = Image.open(local_file_path)
display(im)
在代理程序中使用
from langchain.agents import initialize_agent
from langchain.llms import OpenAI
from gradio_tools.tools import (StableDiffusionTool, ImageCaptioningTool, StableDiffusionPromptGeneratorTool,
TextToVideoTool)
from langchain.memory import ConversationBufferMemory
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/examples/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/examples/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.