Feat/summarise

[incizm]

Added summary function: Uses locally hosted LLM to summarise generated transcript.

[gemini-code-assist]

Summary of Changes

Hello @incizm, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request primarily introduces a new feature that allows for the summarization of audio transcripts. It integrates with an external, locally hosted Large Language Model (LLM) to process transcripts and generate concise summaries, significantly enhancing the utility of the application by providing quick insights into recorded conversations.

Highlights

• New Feature: Transcript Summarization: I've introduced a new capability to summarize generated transcripts using a locally hosted Large Language Model (LLM). This involves a new summarise_transcript function that makes an HTTP POST request to a configurable LLM API endpoint.
• New API Endpoint: A new API endpoint, /jobs/{uuid}/summarise (POST), has been added. This endpoint allows users to request a summary for a specific transcript identified by its UUID, leveraging the new summarization logic.
• Configuration Updates: The .env.example file has been updated to include new environment variables (LLM_API_URL and LLM_MODEL_NAME) required for configuring the LLM service, making the summarization feature configurable.
• Dependency Management: The requests library has been added to backend/requirements.txt to facilitate HTTP communication with the external LLM API.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a summarization feature for transcripts using an LLM. Key changes involve adding new API endpoints, utility functions for interacting with the LLM, and related configuration. The review identified several issues, including hardcoding the compute device, potential crashes due to unhandled missing environment variables, incorrect processing of transcript files which breaks existing functionality and the new feature, and unsafe dictionary access that could lead to KeyErrors. Addressing these points is crucial for the stability and correctness of the application.

[gemini-code-assist]

Accessing get_file_name(uuid)["file_name"] directly is unsafe. If get_file_name(uuid) returns an error dictionary (e.g., {"error": "UUID not found"}), this will raise a KeyError. You should check if the 'error' key exists in the response from get_file_name before attempting to access "file_name".

        file_name_response = get_file_name(uuid)
        if "error" in file_name_response:
            logging.error(f"Failed to get file name for UUID {uuid} in summarise_job: {file_name_response['error']}")
            return {"error": f"Failed to retrieve file details for UUID {uuid} to start summarization."}
        file_name = file_name_response["file_name"]