containers / ramalama

The goal of RamaLama is to make working with AI boring.
MIT License
272 stars 47 forks source link

Revert "Switch to llama-simple-chat" #477

Closed rhatdan closed 22 hours ago

rhatdan commented 23 hours ago

The llama-simple-chat does not work properly yet.

This reverts commit 1db401da6efc052185b23e49c67b738a102c3998.

Summary by Sourcery

Revert the integration of 'llama-simple-chat' and restore 'llama-cli' as the command-line interface for executing models due to unresolved issues with 'llama-simple-chat'. Update the system test to align with this change.

Enhancements:

Tests:

sourcery-ai[bot] commented 23 hours ago

Reviewer's Guide by Sourcery

This PR reverts a previous change that switched from llama-cli to llama-simple-chat. The implementation restores the original llama-cli command with its specific argument structure and command-line options.

Sequence diagram for reverting to llama-cli

sequenceDiagram
    actor User
    participant System
    User->>System: Execute model
    alt Using llama-cli
        System->>System: Prepare exec_args with llama-cli
        System->>System: Add --in-prefix, --in-suffix, --no-display-prompt
        System->>System: Add prompt and common_params
        opt GPU enabled
            System->>System: Add GPU arguments
        end
    end
    Note right of System: Reverted from llama-simple-chat to llama-cli

Class diagram for changes in model execution

classDiagram
    class Model {
        -exec_args: List
        -exec_model_path: String
        +run(args)
    }
    note for Model "Reverted exec_args to use llama-cli with specific options"
    class Args {
        +container: bool
        +debug: bool
        +gpu: bool
        +ARGS: List
    }
    Model --> Args : uses
    note for Args "Arguments used to configure model execution"

File-Level Changes

Change Details Files
Reverted command-line interface from llama-simple-chat back to llama-cli
  • Restored llama-cli command with its original arguments structure
  • Re-added --in-prefix and --in-suffix empty string parameters
  • Re-implemented --no-display-prompt option for non-debug mode
  • Restored -cnv flag for non-argument, interactive terminal sessions
  • Updated command construction logic with original parameter ordering
ramalama/model.py
Updated system test to match reverted CLI command
  • Modified test assertion to check for llama-cli command instead of llama-simple-chat
  • Updated expected command string pattern in test case
test/system/030-run.bats

Tips and commands #### Interacting with Sourcery - **Trigger a new review:** Comment `@sourcery-ai review` on the pull request. - **Continue discussions:** Reply directly to Sourcery's review comments. - **Generate a GitHub issue from a review comment:** Ask Sourcery to create an issue from a review comment by replying to it. - **Generate a pull request title:** Write `@sourcery-ai` anywhere in the pull request title to generate a title at any time. - **Generate a pull request summary:** Write `@sourcery-ai summary` anywhere in the pull request body to generate a PR summary at any time. You can also use this command to specify where the summary should be inserted. #### Customizing Your Experience Access your [dashboard](https://app.sourcery.ai) to: - Enable or disable review features such as the Sourcery-generated pull request summary, the reviewer's guide, and others. - Change the review language. - Add, remove or edit custom review instructions. - Adjust other review settings. #### Getting Help - [Contact our support team](mailto:support@sourcery.ai) for questions or feedback. - Visit our [documentation](https://docs.sourcery.ai) for detailed guides and information. - Keep in touch with the Sourcery team by following us on [X/Twitter](https://x.com/SourceryAI), [LinkedIn](https://www.linkedin.com/company/sourcery-ai/) or [GitHub](https://github.com/sourcery-ai).