Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[EP] Enhance Chat Interface #2

Open
antfin opened this issue Nov 19, 2024 · 1 comment
Open

[EP] Enhance Chat Interface #2

antfin opened this issue Nov 19, 2024 · 1 comment
Labels
enhancement New feature or request

Comments

@antfin
Copy link
Contributor

antfin commented Nov 19, 2024

Enhance the chat interface in the user panel to support advanced interactions with LLM tools. The interface should allow LLM tools to specify their interfaces from their manifests, support HTML forms with dependency logic, and enable enriched output formats such as tables, charts, and multimedia objects. Additionally, the interface should include references in the output, such as document metadata, original data sources, and chart references.

As a developer, I want to specify the interface for my LLM tool in its manifest so that the chatbot can call it directly using its custom interface.
•The manifest allows developers to define the HTML interface for the LLM tool.
•The chatbot can render and use the specified interface for interactions.

As a user, I want to interact with HTML forms that have dependency logic so that my inputs dynamically adjust based on my selections.
•The chat interface supports all standard HTML form elements.
•The interface dynamically updates form elements based on user inputs.

As a user, I want to receive enriched text outputs such as tables and charts so that I can better understand the information provided by the LLM tool.
•The LLM tool can output formatted tables and charts.
•The chat interface correctly renders these enriched text outputs.

As a user, I want to receive multimedia outputs such as images, videos, and audio so that I can access diverse forms of information.
•The LLM tool can include images, videos, and audio in its responses.
•The chat interface correctly displays these multimedia elements

As a user, I want to see references in the output such as document metadata and data sources so that I can verify and trace the information provided.
•The LLM tool includes references such as document metadata, original data sources, and chart references in its output.
•The chat interface displays these references in an accessible format.

@antfin antfin added the enhancement New feature or request label Nov 19, 2024
@antfin
Copy link
Contributor Author

antfin commented Nov 19, 2024

LL-Mesh 0.1 allow the tool to expose its manifest as it's possible to see in the example chatbot. But we want to address more advanced feature like the possibility to expose more advanced interface types and for instance their UI styles.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant