Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.
Releases
@gradio/client@1.3.0
Fixes
012da05
- Ensure JS clientstatus_callback
functionality works and improve status messages. Thanks @hannahblair!2943d6d
- Add Timer component. Thanks @aliabid94!a6b3c6c
- Ensure@gradio/client
'ssubmit
iterator releases as expected. Thanks @pngwn!e834d30
- ensure@gradio/client
always returns the correct data. Thanks @pngwn!1b5b5b0
- Bindfetch
andstream
in JS client. Thanks @hannahblair!936c713
- Documents auth in the guides, in the view API page, and also types the Blocks.config object. Thanks @abidlabs!gradio_client@1.1.0
Fixes
2943d6d
- Add Timer component. Thanks @aliabid94!gradio@4.38.0
Highlights
Support message format in chatbot 💬 (#8422
4221290
)gr.Chatbot
andgr.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
andgr.ChatInterface
now have atype
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 withcontent
androle
keys is expected. See below -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 atitle
key andvalue
. This will display the assistant message in an expandable message box to show the result of a tool or intermediate step.Thanks @freddyaboulton!
Features
a92c3e8
- Warn against Falsy credentials. Thanks @Paillat-dev!ee497d5
- Perform CORS validation when the request has a cookie. Thanks @abidlabs!b736c8d
- Refactorgr.ParamViewer
to use HTML<details>
and other tweaks. Thanks @abidlabs!3b8238c
- Add c/cpp code support. Thanks @ginazhouhuiwu!e3c7079
- Time range component. Thanks @aliabid94!280a3f4
- GRADIO_ALLOWED_PATHS & GRADIO_BLOCKED_PATHS comma separated environme…. Thanks @cocktailpeanut!fb0daf3
- Improvements togr.Examples
: adds events as attributes and documents, them, addssample_labels
, andvisible
properties. Thanks @abidlabs!5e36144
- Add guides for msg format and llm agents. Thanks @freddyaboulton!bc1d45d
- Model3D point cloud and wireframe display modes. Thanks @dawoodkhan82!Fixes
012da05
- Ensure JS clientstatus_callback
functionality works and improve status messages. Thanks @hannahblair!c1ecfde
- 8394 df hidden items. Thanks @pngwn!2943d6d
- Add Timer component. Thanks @aliabid94!a6b3c6c
- Ensure@gradio/client
'ssubmit
iterator releases as expected. Thanks @pngwn!26cdd0f
- Revert chatbot styling. Thanks @pngwn!0482453
- Chatbot LaTeX Crash Fix. Thanks @dawoodkhan82!e834d30
- ensure@gradio/client
always returns the correct data. Thanks @pngwn!31a876d
- FixShare to community
button for images. Thanks @hannahblair!d15ada9
- Fix multimodal textbox custom components. Thanks @freddyaboulton!1b5b5b0
- Bindfetch
andstream
in JS client. Thanks @hannahblair!c946c6f
- Allow supplying customgr.Chatbot
with events togr.ChatInterface
. Thanks @abidlabs!a9307c6
- Chatbot generating scroll and click fix. Thanks @freddyaboulton!936c713
- Documents auth in the guides, in the view API page, and also types the Blocks.config object. Thanks @abidlabs!@gradio/atoms@0.7.6
Dependency updates
@gradio/audio@0.12.2
Dependency updates
@gradio/box@0.1.20
Dependency updates
@gradio/button@0.2.46
Dependency updates
@gradio/chatbot@0.12.0
Highlights
Support message format in chatbot 💬 (#8422
4221290
)gr.Chatbot
andgr.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
andgr.ChatInterface
now have atype
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 withcontent
androle
keys is expected. See below -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 atitle
key andvalue
. This will display the assistant message in an expandable message box to show the result of a tool or intermediate step.Thanks @freddyaboulton!
Fixes
26cdd0f
- Revert chatbot styling. Thanks @pngwn!Dependency updates
@gradio/checkbox@0.3.8
Dependency updates
@gradio/checkboxgroup@0.5.8
Dependency updates
@gradio/code@0.7.0
Features
3b8238c
- Add c/cpp code support. Thanks @ginazhouhuiwu!Dependency updates
@gradio/colorpicker@0.3.8
Dependency updates
@gradio/dataframe@0.8.13
Fixes
c1ecfde
- 8394 df hidden items. Thanks @pngwn!Dependency updates
@gradio/dataset@0.2.0
Features
fb0daf3
- Improvements togr.Examples
: adds events as attributes and documents, them, addssample_labels
, andvisible
properties. Thanks @abidlabs!Dependency updates
@gradio/datetime@0.0.2
Dependency updates
@gradio/downloadbutton@0.1.23
Dependency updates
@gradio/dropdown@0.7.8
Dependency updates
@gradio/fallback@0.3.8
Dependency updates
@gradio/file@0.8.5
Dependency updates
@gradio/form@0.1.20
Dependency updates
@gradio/gallery@0.11.2
Dependency updates
@gradio/highlightedtext@0.7.2
Dependency updates
@gradio/html@0.3.1
Dependency updates
@gradio/icons@0.6.0
Features
e3c7079
- Time range component. Thanks @aliabid94!@gradio/image@0.12.2
Fixes
31a876d
- FixShare to community
button for images. Thanks @hannahblair!Dependency updates
@gradio/imageeditor@0.7.13
Dependency updates
@gradio/json@0.2.8
Dependency updates
@gradio/label@0.3.8
Dependency updates
@gradio/lite@4.38.0
Dependency updates
@gradio/markdown@0.8.1
Fixes
0482453
- Chatbot LaTeX Crash Fix. Thanks @dawoodkhan82!Dependency updates
@gradio/model3d@0.11.0
Features
bc1d45d
- Model3D point cloud and wireframe display modes. Thanks @dawoodkhan82!Dependency updates
@gradio/multimodaltextbox@0.5.2
Dependency updates
@gradio/number@0.4.8
Dependency updates
@gradio/paramviewer@0.4.17
Features
b736c8d
- Refactorgr.ParamViewer
to use HTML<details>
and other tweaks. Thanks @abidlabs!Dependency updates
@gradio/plot@0.6.0
Features
e3c7079
- Time range component. Thanks @aliabid94!Dependency updates
@gradio/preview@0.10.1
Fixes
078663a
- Fix issue with virtual module in custom components. Thanks @pngwn!@gradio/radio@0.5.8
Dependency updates
@gradio/simpledropdown@0.2.8
Dependency updates
@gradio/simpleimage@0.6.2
Dependency updates
@gradio/simpletextbox@0.2.8
Dependency updates
@gradio/slider@0.4.8
Dependency updates
@gradio/statustracker@0.7.1
Fixes
a9307c6
- Chatbot generating scroll and click fix. Thanks @freddyaboulton!Dependency updates
@gradio/tabitem@0.2.12
Dependency updates
@gradio/tabs@0.2.11
Dependency updates
@gradio/textbox@0.6.7
Dependency updates
@gradio/timer@0.3.0
Fixes
2943d6d
- Add Timer component. Thanks @aliabid94!Dependency updates
@gradio/tootils@0.6.0
Highlights
Support message format in chatbot 💬 (#8422
4221290
)gr.Chatbot
andgr.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
andgr.ChatInterface
now have atype
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 withcontent
androle
keys is expected. See below -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 atitle
key andvalue
. This will display the assistant message in an expandable message box to show the result of a tool or intermediate step.Thanks @freddyaboulton!
Features
3a6142f
- Lite load perf ci. Thanks @whitphx!Dependency updates
@gradio/upload@0.11.5
Fixes
1b5b5b0
- Bindfetch
andstream
in JS client. Thanks @hannahblair!Dependency updates
@gradio/uploadbutton@0.6.14
Dependency updates
@gradio/utils@0.5.1
Fixes
31a876d
- FixShare to community
button for images. Thanks @hannahblair!@gradio/video@0.9.2
Dependency updates
website@0.34.0
Highlights
Support message format in chatbot 💬 (#8422
4221290
)gr.Chatbot
andgr.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
andgr.ChatInterface
now have atype
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 withcontent
androle
keys is expected. See below -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 atitle
key andvalue
. This will display the assistant message in an expandable message box to show the result of a tool or intermediate step.Thanks @freddyaboulton!
Features
fb0daf3
- Improvements togr.Examples
: adds events as attributes and documents, them, addssample_labels
, andvisible
properties. Thanks @abidlabs!64ac05b
- Better spacing for codeblocks on docs. Thanks @aliabd!740364e
- Add guide on best practices for ZeroGPU limits with the python client. Thanks @freddyaboulton!edcd574
- Fix playground to display errors. Thanks @whitphx!ba59bb8
- Add search to website. Thanks @aliabd!Fixes
2943d6d
- Add Timer component. Thanks @aliabid94!c946c6f
- Allow supplying customgr.Chatbot
with events togr.ChatInterface
. Thanks @abidlabs!Dependency updates
@gradio/accordion@0.3.18
Dependency updates
@gradio/annotatedimage@0.6.13
Dependency updates
@gradio/app@1.38.0
Features
e3c7079
- Time range component. Thanks @aliabid94!Fixes
2943d6d
- Add Timer component. Thanks @aliabid94!936c713
- Documents auth in the guides, in the view API page, and also types the Blocks.config object. Thanks @abidlabs!Dependency updates
@gradio/fileexplorer@0.4.14
Dependency updates