16 KiB
@self/tootils
0.7.8
Dependency updates
- @gradio/utils@0.8.0
- @gradio/statustracker@0.9.5
0.7.7
Dependency updates
- @gradio/statustracker@0.9.4
0.7.6
Dependency updates
- @gradio/statustracker@0.9.3
0.7.5
Dependency updates
- @gradio/statustracker@0.9.2
0.7.4
Dependency updates
- @gradio/statustracker@0.9.1
0.7.3
Dependency updates
- @gradio/statustracker@0.9.0
0.7.2
Fixes
0.7.1
Dependency updates
- @gradio/statustracker@0.8.1
0.7.0
Features
Dependencies
- @gradio/statustracker@0.8.0
- @gradio/utils@0.7.0
0.7.0-beta.5
Features
Dependency updates
- @gradio/statustracker@0.8.0-beta.5
0.6.5-beta.4
Dependency updates
- @gradio/statustracker@0.8.0-beta.4
0.6.5-beta.3
Dependency updates
- @gradio/statustracker@0.8.0-beta.3
0.6.5-beta.2
Dependency updates
- @gradio/statustracker@0.8.0-beta.2
0.6.5-beta.2
Dependency updates
- @gradio/statustracker@0.8.0-beta.2
- @gradio/utils@0.7.0-beta.2
0.6.5-beta.1
Dependency updates
- @gradio/statustracker@0.8.0-beta.1
- @gradio/utils@0.7.0-beta.1
0.6.5
Fixes
Dependency updates
- @gradio/utils@0.6.1
- @gradio/statustracker@0.7.6
0.6.4
Dependency updates
- @gradio/utils@0.6.0
- @gradio/statustracker@0.7.5
0.6.3
Dependency updates
- @gradio/statustracker@0.7.4
0.6.2
Dependency updates
- @gradio/utils@0.5.2
- @gradio/statustracker@0.7.3
0.6.1
Dependency updates
- @gradio/statustracker@0.7.2
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
Dependency updates
- @gradio/utils@0.5.1
- @gradio/statustracker@0.7.1
0.5.1
Dependency updates
- @gradio/utils@0.5.0
- @gradio/statustracker@0.7.0
0.5.0
Features
Dependency updates
- @gradio/statustracker@0.6.0
0.4.5
Dependency updates
- @gradio/statustracker@0.6.0
0.4.4
Dependency updates
- @gradio/utils@0.4.2
- @gradio/statustracker@0.5.5
0.4.3
Dependency updates
- @gradio/statustracker@0.5.4
0.4.2
Dependency updates
- @gradio/statustracker@0.5.3
0.4.1
Dependency updates
- @gradio/statustracker@0.5.2
0.4.0
Features
Fixes
- #8179
6a218b4- rework upload to be a class method + pass client into each component. Thanks @pngwn!
Dependency updates
- @gradio/utils@0.4.1
- @gradio/statustracker@0.5.1
0.3.0
Highlights
Setting File Upload Limits (#7909 2afca65)
We have added a max_file_size size parameter to launch() that limits to size of files uploaded to the server. This limit applies to each individual file. This parameter can be specified as a string or an integer (corresponding to the size in bytes).
The following code snippet sets a max file size of 5 megabytes.
import gradio as gr
demo = gr.Interface(lambda x: x, "image", "image")
demo.launch(max_file_size="5mb")
# or
demo.launch(max_file_size=5 * gr.FileSize.MB)
Error states can now be cleared
When a component encounters an error, the error state shown in the UI can now be cleared by clicking on the x icon in the top right of the component. This applies to all types of errors, whether it's raised in the UI or the server.
Thanks @freddyaboulton!
Dependency updates
- @gradio/statustracker@0.5.0
- @gradio/utils@0.4.0
0.2.8
Dependency updates
- @gradio/utils@0.3.2
- @gradio/statustracker@0.4.12
0.2.7
Dependency updates
- @gradio/utils@0.3.1
- @gradio/statustracker@0.4.11
0.2.6
Dependency updates
- @gradio/statustracker@0.4.10
0.2.5
Dependency updates
- @gradio/statustracker@0.4.9
0.2.4
Features
0.2.3
Patch Changes
- Updated dependencies [
98a2719]:- @gradio/statustracker@0.4.8
0.2.2
Patch Changes
- Updated dependencies []:
- @gradio/statustracker@0.4.7
0.2.1
Patch Changes
- Updated dependencies [
065c5b1]:- @gradio/utils@0.3.0
- @gradio/statustracker@0.4.6
0.2.0
Features
0.1.9
Patch Changes
- Updated dependencies [
fdd1521]:- @gradio/utils@0.2.2
- @gradio/statustracker@0.4.5
0.1.8
Patch Changes
- Updated dependencies [
5727b92]:- @gradio/utils@0.2.1
- @gradio/statustracker@0.4.4
0.1.7
Patch Changes
- Updated dependencies [
828fb9e]:- @gradio/statustracker@0.4.3
0.1.6
Patch Changes
- Updated dependencies []:
- @gradio/statustracker@0.4.2
0.1.5
Patch Changes
- Updated dependencies []:
- @gradio/statustracker@0.4.1
0.1.4
Patch Changes
- Updated dependencies [
9caddc17b]:- @gradio/statustracker@0.4.0
0.1.3
Patch Changes
- Updated dependencies []:
- @gradio/statustracker@0.3.2
0.1.2
Patch Changes
- Updated dependencies []:
- @gradio/statustracker@0.3.1
0.1.1
Fixes
- #6234
aaa55ce85- Video/Audio fixes. Thanks @freddyaboulton! - #6236
6bce259c5- Ensuregr.CheckboxGroupupdates as expected. Thanks @pngwn! - #6249
2cffcf3c3- ensure radios have different names. Thanks @pngwn!
0.1.0
Features
- #5498
287fe6782- Publish all components to npm. Thanks @pngwn! - #5498
287fe6782- Custom components. Thanks @pngwn!
0.1.0-beta.7
Patch Changes
- Updated dependencies [
667802a6c]:- @gradio/utils@0.2.0-beta.6
0.1.0-beta.6
Features
- #6044
9053c95a1- Simplify File Component. Thanks @freddyaboulton!
Fixes
0.1.0-beta.5
Patch Changes
- Updated dependencies [
13ed8a485]:- @gradio/utils@0.2.0-beta.4
0.1.0-beta.4
Features
- #5648
c573e2339- Publish all components to npm. Thanks @freddyaboulton!
0.1.0-beta.3
Patch Changes
- Updated dependencies [
0b4fd5b6d]:- @gradio/utils@0.2.0-beta.3
0.1.0-beta.2
Patch Changes
- Updated dependencies [
14fc612d8]:- @gradio/utils@0.2.0-beta.2
0.1.0-beta.1
Patch Changes
- Updated dependencies []:
- @gradio/utils@0.2.0-beta.1
0.1.0-beta.0
Features
0.0.2
Highlights
Improve startup performance and markdown support (#5279 fe057300)
Improved markdown support
We now have better support for markdown in gr.Markdown and gr.Dataframe. Including syntax highlighting and Github Flavoured Markdown. We also have more consistent markdown behaviour and styling.
Various performance improvements
These improvements will be particularly beneficial to large applications.
- Rather than attaching events manually, they are now delegated, leading to a significant performance improvement and addressing a performance regression introduced in a recent version of Gradio. App startup for large applications is now around twice as fast.
- Optimised the mounting of individual components, leading to a modest performance improvement during startup (~30%).
- Corrected an issue that was causing markdown to re-render infinitely.
- Ensured that the
gr.3DModeldoes re-render prematurely.
Thanks @pngwn!