Could we get the prompt that is used for the plugin?

[iamianM]

I still don't have access to the plugin and don't know when I will. Would love to be able to replicate the results locally, but there's clearly some nice prompting going on with the official chatgpt website. Could we get the prompt along with all the ways it injects the descriptions, api calls and context.

Thank you and thanks for the plugin repo... it is fantastic.

[MojoBoingo]

what he said, please and thank you c:

[bzannah]

+1

[saschaschramm]

There is a special plugins model that knows when and how to use plugins. Maybe this helps:

Assistant is a large language model trained by OpenAI.
Knowledge Cutoff: 2021-09
Current date: 2023-04-19


# Tools
## retrieval
// Plugin for searching through the user's documents (such as files, emails, and more) to find answers to questions and retrieve relevant information. Use it whenever a user asks something that might be found in their personal information.
namespace retrieval {

// Accepts search query objects array each with query and optional filter. Break down complex questions into sub-questions. Refine results by criteria, e.g. time / source, don't do this often. Split queries if ResponseTooLargeError occurs.
type query_query_post = (_: {
queries: any[],
}) => any;

} // namespace retrieval

[iamianM]

There is a special plugins model that knows when and how to use plugins. Maybe this helps:

Assistant is a large language model trained by OpenAI.
Knowledge Cutoff: 2021-09
Current date: 2023-04-19


# Tools
## retrieval
// Plugin for searching through the user's documents (such as files, emails, and more) to find answers to questions and retrieve relevant information. Use it whenever a user asks something that might be found in their personal information.
namespace retrieval {

// Accepts search query objects array each with query and optional filter. Break down complex questions into sub-questions. Refine results by criteria, e.g. time / source, don't do this often. Split queries if ResponseTooLargeError occurs.
type query_query_post = (_: {
queries: any[],
}) => any;

} // namespace retrieval

Sorry, what are you referring to? Do you have a link? I wasn't aware of a plugin model.

[saschaschramm]

There is a special plugins model that knows when and how to use plugins. Maybe this helps:

Assistant is a large language model trained by OpenAI.
Knowledge Cutoff: 2021-09
Current date: 2023-04-19


# Tools
## retrieval
// Plugin for searching through the user's documents (such as files, emails, and more) to find answers to questions and retrieve relevant information. Use it whenever a user asks something that might be found in their personal information.
namespace retrieval {

// Accepts search query objects array each with query and optional filter. Break down complex questions into sub-questions. Refine results by criteria, e.g. time / source, don't do this often. Split queries if ResponseTooLargeError occurs.
type query_query_post = (_: {
queries: any[],
}) => any;

} // namespace retrieval

Sorry, what are you referring to? Do you have a link? I wasn't aware of a plugin model.

My apologies for the confusion. The image below shows the plugin model. I don't think there are more information available about the model.

The openapi.yaml file is transformed into TypeScript, which is then utilized in the prompt.