feat: add generateWithOptionalTools to Kurt interface #12
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sometimes we may want to ask the LLM to produce a natural language response, but with the option of using some tools (in a structured data format) as part of its self-directed process of fulfilling the prompt. This is a bit of a mixture of the prior two methods in the interface - we are expecting the LLM to make zero or more tool calls, and then eventually produce a natural language response. See the README.md example and the spec examples to get a feel for how this works.
|
The example code in the I want to follow up in a future PR to add a higher-level function you can call which wraps the But @theoremonemehdi and I agreed together that we want to expose the "single call" version of this for apps that want full control, even if/when we add a future "repeated calls" function which wraps the loop for a more convenient interface. |
InfraK
approved these changes
May 7, 2024
andreszorro
approved these changes
May 7, 2024
jemc
added a commit
that referenced
this pull request
May 7, 2024
This will enable Kurt to provide some convenience methods in a common place (implemented as a composite of the abstract methods that each concrete class must implement. An example of the kind of convenience method I'm talking about is described in [this comment](#12 (comment)). Overall, this is a breaking change so I want to introduce it before the impending public release. BREAKING CHANGE: Kurt is now an abstract class.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Sometimes we may want to ask the LLM to produce a
natural language response, but with the option of
using some tools (in a structured data format) as
part of its self-directed process of fulfilling the prompt.
This is a bit of a mixture of the prior two methods in the interface - we are expecting the LLM to make zero or more tool calls, and then eventually produce a natural language response.
See the README.md example and the spec examples to get a feel for how this works.