The key name in the response of the queue_status endpoint has been updated from "prnding" to "pending" to fix a typo. This change ensures consistency and improves the readability of the returned data.
The job function in app.py has been converted to an async function to support asynchronous processing. This change improves the performance and responsiveness of the application by allowing other tasks to run concurrently while the job function is processing the queue.
This commit refactors the code by improving the comments in the code and updating the job function in app.py. The comments are now focused on code that is hard to understand, and unnecessary comments are removed. The job function is converted to an async function to support asynchronous processing, which improves the performance and responsiveness of the application. These changes enhance the readability and efficiency of the codebase.
The file path in the CodeRepositoryUtil.getFileContent() method is now sanitized using the LocalFile.sanitizeFilePath() function before executing the command. This change ensures that the file path is properly formatted and prevents any potential security vulnerabilities or errors caused by invalid file paths.
The job function in app.py has been converted to an async function to support asynchronous processing. This change improves the performance and responsiveness of the application by allowing other tasks to run concurrently while the job function is processing the queue.
This commit updates the Dockerfile.tpl to use the huggingface/transformers-pytorch-gpu image instead of the continuumio/anaconda3 image. This change allows the Llama app to utilize GPU resources for improved performance in AI processing. Additionally, the unnecessary installation of the transformers and accelerate libraries is removed as they are already included in the huggingface/transformers-pytorch-gpu image.
This commit updates the Llama app to log the prompt and output to the console for debugging purposes. It adds print statements to log the prompt before processing and the generated output after processing. This change improves the development workflow by providing visibility into the input and output of the AI model.
This commit updates the Llama app to use a local model path instead of a model ID. The model path is set to "/app/Models/Meta-Llama-3-8B-Instruct". This change improves the reliability and performance of the app by directly referencing the model file instead of relying on an external model ID.
This commit modifies the Dockerfile.tpl file to update the EXPOSE directive. The port number is changed from 80 to 8547 to align with the port used by the Llama application. This change ensures that the Llama application is accessible from outside the container on the correct port.
