website@0.34.0

Highlights

Support message format in chatbot 💬 (#8422 4221290)

gr.Chatbot and gr.ChatInterface now support the Messages API, which is fully compatible with LLM API providers such as Hugging Face Text Generation Inference, OpenAI's chat completions API, and Llama.cpp server.

Building Gradio applications around these LLM solutions is now even easier!

gr.Chatbot and gr.ChatInterface now have a type parameter that can accept two values - 'tuples' and 'messages'. If set to 'tuples', the default chatbot data format is expected. If set to 'messages', a list of dictionaries with content and role keys is expected. See below -

def chat_greeter(msg, history):
    history.append({"role": "assistant", "content": "Hello!"})
    return history

Additionally, gradio now exposes a gr.ChatMessage dataclass you can use for IDE type hints and auto completion.

Tool use in Chatbot 🛠️

The Gradio Chatbot can now natively display tool usage and intermediate thoughts common in Agent and chain-of-thought workflows!

If you are using the new "messages" format, simply add a metadata key with a dictionary containing a title key and value. This will display the assistant message in an expandable message box to show the result of a tool or intermediate step.

import gradio as gr
from gradio import ChatMessage
import time

def generate_response(history):
    history.append(ChatMessage(role="user", content="What is the weather in San Francisco right now?"))
    yield history
    time.sleep(0.25)
    history.append(ChatMessage(role="assistant",
                               content="In order to find the current weather in San Francisco, I will need to use my weather tool.")
                               )
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="API Error when connecting to weather service.",
                              metadata={"title": "💥 Error using tool 'Weather'"})
                  )
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="I will try again",
                              ))
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="Weather 72 degrees Fahrenheit with 20% chance of rain.",
                                metadata={"title": "🛠️ Used tool 'Weather'"}
                              ))
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="Now that the API succeeded I can complete my task.",
                              ))
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="It's a sunny day in San Francisco with a current temperature of 72 degrees Fahrenheit and a 20% chance of rain. Enjoy the weather!",
                              ))
    yield history


with gr.Blocks() as demo:
    chatbot  = gr.Chatbot(type="messages")
    button = gr.Button("Get San Francisco Weather")
    button.click(generate_response, chatbot, chatbot)

if __name__ == "__main__":
    demo.launch()

Thanks @freddyaboulton!

Features

• #8733 fb0daf3 - Improvements to gr.Examples: adds events as attributes and documents, them, adds sample_labels, and visible properties. Thanks @abidlabs!
• #8686 64ac05b - Better spacing for codeblocks on docs. Thanks @aliabd!
• #8656 740364e - Add guide on best practices for ZeroGPU limits with the python client. Thanks @freddyaboulton!
• #8689 edcd574 - Fix playground to display errors. Thanks @whitphx!
• #8624 ba59bb8 - Add search to website. Thanks @aliabd!

Fixes

• #8505 2943d6d - Add Timer component. Thanks @aliabid94!
• #8677 c946c6f - Allow supplying custom gr.Chatbot with events to gr.ChatInterface. Thanks @abidlabs!

Dependency updates

• @gradio/code@0.7.0

gradio_client@1.1.0

Fixes

• #8505 2943d6d - Add Timer component. Thanks @aliabid94!

gradio@4.38.1

Features

• #8766 2b4636e - Fix width of assistant's chatbot bubble. Thanks @pngwn!

gradio@4.38.0

Highlights

Support message format in chatbot 💬 (#8422 4221290)

gr.Chatbot and gr.ChatInterface now support the Messages API, which is fully compatible with LLM API providers such as Hugging Face Text Generation Inference, OpenAI's chat completions API, and Llama.cpp server.

Building Gradio applications around these LLM solutions is now even easier!

gr.Chatbot and gr.ChatInterface now have a type parameter that can accept two values - 'tuples' and 'messages'. If set to 'tuples', the default chatbot data format is expected. If set to 'messages', a list of dictionaries with content and role keys is expected. See below -

def chat_greeter(msg, history):
    history.append({"role": "assistant", "content": "Hello!"})
    return history

Additionally, gradio now exposes a gr.ChatMessage dataclass you can use for IDE type hints and auto completion.

Tool use in Chatbot 🛠️

The Gradio Chatbot can now natively display tool usage and intermediate thoughts common in Agent and chain-of-thought workflows!

If you are using the new "messages" format, simply add a metadata key with a dictionary containing a title key and value. This will display the assistant message in an expandable message box to show the result of a tool or intermediate step.

import gradio as gr
from gradio import ChatMessage
import time

def generate_response(history):
    history.append(ChatMessage(role="user", content="What is the weather in San Francisco right now?"))
    yield history
    time.sleep(0.25)
    history.append(ChatMessage(role="assistant",
                               content="In order to find the current weather in San Francisco, I will need to use my weather tool.")
                               )
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="API Error when connecting to weather service.",
                              metadata={"title": "💥 Error using tool 'Weather'"})
                  )
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="I will try again",
                              ))
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="Weather 72 degrees Fahrenheit with 20% chance of rain.",
                                metadata={"title": "🛠️ Used tool 'Weather'"}
                              ))
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="Now that the API succeeded I can complete my task.",
                              ))
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="It's a sunny day in San Francisco with a current temperature of 72 degrees Fahrenheit and a 20% chance of rain. Enjoy the weather!",
                              ))
    yield history


with gr.Blocks() as demo:
    chatbot  = gr.Chatbot(type="messages")
    button = gr.Button("Get San Francisco Weather")
    button.click(generate_response, chatbot, chatbot)

if __name__ == "__main__":
    demo.launch()

Thanks @freddyaboulton!

Features

• #8683 a92c3e8 - Warn against Falsy credentials. Thanks @Paillat-dev!
• #8743 ee497d5 - Perform CORS validation when the request has a cookie. Thanks @abidlabs!
• #8744 b736c8d - Refactor gr.ParamViewer to use HTML <details> and other tweaks. Thanks @abidlabs!
• #8665 3b8238c - Add c/cpp code support. Thanks @ginazhouhuiwu!
• #8713 e3c7079 - Time range component. Thanks @aliabid94!
• #8705 280a3f4 - GRADIO_ALLOWED_PATHS & GRADIO_BLOCKED_PATHS comma separated environme…. Thanks @cocktailpeanut!
• #8733 fb0daf3 - Improvements to gr.Examples: adds events as attributes and documents, them, adds sample_labels, and visible properties. Thanks @abidlabs!
• #8750 5e36144 - Add guides for msg format and llm agents. Thanks @freddyaboulton!
• #8687 bc1d45d - Model3D point cloud and wireframe display modes. Thanks @dawoodkhan82!

Fixes

• #8699 012da05 - Ensure JS client status_callback functionality works and improve status messages. Thanks @hannahblair!
• #8763 c1ecfde - 8394 df hidden items. Thanks @pngwn!
• #8505 2943d6d - Add Timer component. Thanks @aliabid94!
• #8715 a6b3c6c - Ensure @gradio/client's submit iterator releases as expected. Thanks @pngwn!
• #8758 26cdd0f - Revert chatbot styling. Thanks @pngwn!
• #8658 0482453 - Chatbot LaTeX Crash Fix. Thanks @dawoodkhan82!
• #8716 e834d30 - ensure @gradio/client always returns the correct data. Thanks @pngwn!
• #8737 31a876d - Fix Share to community button for images. Thanks @hannahblair!
• #8719 d15ada9 - Fix multimodal textbox custom components. Thanks @freddyaboulton!
• #8714 1b5b5b0 - Bind fetch and stream in JS client. Thanks @hannahblair!
• #8677 c946c6f - Allow supplying custom gr.Chatbot with events to gr.ChatInterface. Thanks @abidlabs!
• #8748 a9307c6 - Chatbot generating scroll and click fix. Thanks @freddyaboulton!
• #8720 936c713 - Documents auth in the guides, in the view API page, and also types the Blocks.config object. Thanks @abidlabs!

@gradio/video@0.9.2

Dependency updates

• @gradio/atoms@0.7.6
• @gradio/utils@0.5.1
• @gradio/statustracker@0.7.1
• @gradio/client@1.3.0
• @gradio/upload@0.11.5
• @gradio/image@0.12.2
• @gradio/icons@0.6.0

@gradio/utils@0.5.1

Fixes

• #8737 31a876d - Fix Share to community button for images. Thanks @hannahblair!

@gradio/uploadbutton@0.6.14

Dependency updates

• @gradio/utils@0.5.1
• @gradio/client@1.3.0
• @gradio/upload@0.11.5
• @gradio/button@0.2.46

@gradio/upload@0.11.5

Fixes

• #8714 1b5b5b0 - Bind fetch and stream in JS client. Thanks @hannahblair!

Dependency updates

• @gradio/atoms@0.7.6
• @gradio/utils@0.5.1
• @gradio/client@1.3.0
• @gradio/icons@0.6.0

@gradio/tootils@0.6.0

Highlights

Support message format in chatbot 💬 (#8422 4221290)

gr.Chatbot and gr.ChatInterface now support the Messages API, which is fully compatible with LLM API providers such as Hugging Face Text Generation Inference, OpenAI's chat completions API, and Llama.cpp server.

Building Gradio applications around these LLM solutions is now even easier!

gr.Chatbot and gr.ChatInterface now have a type parameter that can accept two values - 'tuples' and 'messages'. If set to 'tuples', the default chatbot data format is expected. If set to 'messages', a list of dictionaries with content and role keys is expected. See below -

def chat_greeter(msg, history):
    history.append({"role": "assistant", "content": "Hello!"})
    return history

Additionally, gradio now exposes a gr.ChatMessage dataclass you can use for IDE type hints and auto completion.

Tool use in Chatbot 🛠️

The Gradio Chatbot can now natively display tool usage and intermediate thoughts common in Agent and chain-of-thought workflows!

If you are using the new "messages" format, simply add a metadata key with a dictionary containing a title key and value. This will display the assistant message in an expandable message box to show the result of a tool or intermediate step.

import gradio as gr
from gradio import ChatMessage
import time

def generate_response(history):
    history.append(ChatMessage(role="user", content="What is the weather in San Francisco right now?"))
    yield history
    time.sleep(0.25)
    history.append(ChatMessage(role="assistant",
                               content="In order to find the current weather in San Francisco, I will need to use my weather tool.")
                               )
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="API Error when connecting to weather service.",
                              metadata={"title": "💥 Error using tool 'Weather'"})
                  )
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="I will try again",
                              ))
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="Weather 72 degrees Fahrenheit with 20% chance of rain.",
                                metadata={"title": "🛠️ Used tool 'Weather'"}
                              ))
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="Now that the API succeeded I can complete my task.",
                              ))
    yield history
    time.sleep(0.25)

    history.append(ChatMessage(role="assistant",
                               content="It's a sunny day in San Francisco with a current temperature of 72 degrees Fahrenheit and a 20% chance of rain. Enjoy the weather!",
                              ))
    yield history


with gr.Blocks() as demo:
    chatbot  = gr.Chatbot(type="messages")
    button = gr.Button("Get San Francisco Weather")
    button.click(generate_response, chatbot, chatbot)

if __name__ == "__main__":
    demo.launch()

Thanks @freddyaboulton!

Features

• #8222 3a6142f - Lite load perf ci. Thanks @whitphx!

Dependency updates

• @gradio/utils@0.5.1
• @gradio/statustracker@0.7.1

@gradio/timer@0.3.0

Fixes

• #8505 2943d6d - Add Timer component. Thanks @aliabid94!

Dependency updates

• @gradio/utils@0.5.1