{"id":21701433,"url":"https://github.com/aman-17/issue-management-llm","last_synced_at":"2026-05-21T14:07:43.673Z","repository":{"id":236197568,"uuid":"792120348","full_name":"aman-17/Issue-Management-LLM","owner":"aman-17","description":"Advancing MLOps and DevOps Efficiency: A Systematic Approach to Issue Management using Large Language Models","archived":false,"fork":false,"pushed_at":"2024-04-26T21:22:49.000Z","size":9211,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-25T15:11:12.375Z","etag":null,"topics":["cicd","devops","issue-management","issue-reporting","llms","mlops","python"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aman-17.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-04-26T02:42:59.000Z","updated_at":"2024-04-26T21:22:52.000Z","dependencies_parsed_at":"2024-11-25T20:30:52.012Z","dependency_job_id":null,"html_url":"https://github.com/aman-17/Issue-Management-LLM","commit_stats":null,"previous_names":["aman-17/issue-management-llm"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aman-17%2FIssue-Management-LLM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aman-17%2FIssue-Management-LLM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aman-17%2FIssue-Management-LLM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aman-17%2FIssue-Management-LLM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aman-17","download_url":"https://codeload.github.com/aman-17/Issue-Management-LLM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244645463,"owners_count":20486984,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cicd","devops","issue-management","issue-reporting","llms","mlops","python"],"created_at":"2024-11-25T20:19:56.265Z","updated_at":"2026-05-21T14:07:38.641Z","avatar_url":"https://github.com/aman-17.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Advancing MLOps and DevOps Efficiency: A Systematic Approach to Issue Management using Large Language Models\n\n\n# SWE-bench Inference\nIn this package, we provide various tools to get started on SWE-bench inference.\nIn particular, we provide the following important scripts and sub-packages:\n\n- `make_datasets`, this sub-package contains scripts to generate new datasets for SWE-bench inference with your own prompts and issues.\n- `run_api.py`, this script is used to generate API model generations for a given dataset.\n\n\n## `make_datasets`\nFor more information on how to use this sub-package, please refer to the [README](./make_datasets/README.md) in the sub-package.\n\n## Run API inference on test datasets\n\nThis python script is designed to run inference on a dataset using either the OpenAI or Anthropic API, depending on the model specified. It sorts instances by length and continually writes the outputs to a specified file, so that the script can be stopped and restarted without losing progress.\n\nFor instance, to run this script on SWE-bench context and Anthropic's Claude 3 model, you can run the following command:\n```bash\nexport ANTHROPIC_API_KEY=\u003cyour key\u003e\npython run_api.py --dataset_name_or_path princeton-nlp/SWE-bench_oracle --model_name_or_path claude-3 --output_dir ./outputs\n```\n\n## Run live inference on open GitHub issues\n\nFollow instructions [here](https://github.com/castorini/pyserini/blob/master/docs/installation.md) to install [Pyserini](https://github.com/castorini/pyserini), to perform BM25 retrieval.\n\nThen run `run_live.py` to try solving a new issue. For example, you can try solving [this issue](https://github.com/huggingface/transformers/issues/26706 ) by running the following command:\n\n```bash\nexport OPENAI_API_KEY=\u003cyour key\u003e\npython run_live.py --model_name gpt-3.5-turbo-1106 \\\n    --issue_url https://github.com/huggingface/transformers/issues/26706 \n```\n\n\n# Issue Tagging and Prioritization\nHere is the evaluation of all the datasets:\n\n## MulDIC\nRun the following files to evaluate the MulDIC datasets\n\n- `lvlm_gemini_pro.py`, This Python script appears to utilize the google.generativeai library, specifically the GenAI module, to interact with Google's Generative AI models, particularly the gemini-pro-vision model.\n  \n- `lvlm_gpt_vision.py`, This Python script utilizes the OpenAI API to generate responses to issue titles and code snippets extracted from a dataset.\n\nFor more information ont his dataset, please refer to the [here](https://github.com/chang26/MulDIC) in the sub-package.\n\n## Issue Ticket Tagger:\nRun the following files to evaluate the Issue Ticket Tagger datasets:\n- `llm_gemini_pro.py`, This Python script appears to utilize the Gemini Pro model to generate labels for a list of issue texts extracted from a file. The generated labels are then saved for further analysis or use.\n  \n- `llm_gpt3.py`, This Python script utilizes the GPT-3.5 Turbo model from OpenAI to generate labels for a list of issue texts extracted from a file.\nThe output of this script is a series of generated responses printed to the console and saved in the ticket_tagger_gpt3.json file.\n\n## NLBSE'24:\nRun the following files to evaluate the NLBSE'24 datasets:\n- `issueclassificationgpt.ipynb`, This script uses Installation of Required Libraries along with that Importing Libraries and Loading Data.\n  \n- `nlbse_eval.py`, This code snippet performs several tasks related to data cleaning and interaction with the OpenAI GPT-3 API for generating responses.\nThe output of this script is a series of generated responses printed to the console and saved in the ticket_tagger_gpt3.json file.\n- `requirements.txt`,  It provided lists specific versions of Python packages as dependencies. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faman-17%2Fissue-management-llm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faman-17%2Fissue-management-llm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faman-17%2Fissue-management-llm/lists"}