{"id":14964759,"url":"https://github.com/alekseyscorpi/vacancies_server","last_synced_at":"2026-02-06T13:04:11.279Z","repository":{"id":239762307,"uuid":"795461502","full_name":"AlekseyScorpi/vacancies_server","owner":"AlekseyScorpi","description":"This is a server for vacancies generation using LLM (Saiga3)","archived":false,"fork":false,"pushed_at":"2024-05-31T10:02:39.000Z","size":30,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-27T01:15:14.027Z","etag":null,"topics":["code","cuda","cuda-toolkit","docker","dockerfile","flask","llama3","llamacpp","llm","ngrok","pydantic","saiga"],"latest_commit_sha":null,"homepage":"https://vacancies-site.vercel.app/","language":"Python","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/AlekseyScorpi.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":"2024-05-03T10:32:38.000Z","updated_at":"2024-05-31T10:02:43.000Z","dependencies_parsed_at":"2024-05-16T07:26:24.246Z","dependency_job_id":"200d5656-012e-4b73-9ddc-2b253fd3f403","html_url":"https://github.com/AlekseyScorpi/vacancies_server","commit_stats":null,"previous_names":["alekseyscorpi/vacancies_server"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlekseyScorpi%2Fvacancies_server","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlekseyScorpi%2Fvacancies_server/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlekseyScorpi%2Fvacancies_server/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlekseyScorpi%2Fvacancies_server/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AlekseyScorpi","download_url":"https://codeload.github.com/AlekseyScorpi/vacancies_server/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245761302,"owners_count":20667895,"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":["code","cuda","cuda-toolkit","docker","dockerfile","flask","llama3","llamacpp","llm","ngrok","pydantic","saiga"],"created_at":"2024-09-24T13:33:44.375Z","updated_at":"2026-02-06T13:04:06.257Z","avatar_url":"https://github.com/AlekseyScorpi.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# This is the server for the vacancies generation system\n## About this server\nThis server works in pair with front-end part https://github.com/AlekseyScorpi/vacancies_site\nIt allows you to generate job texts at the request of users based on the form they submitted.\nTo generate text, the server uses a large language model. Model is finetuned Saiga3 - https://huggingface.co/AlekseyScorpi/saiga_llama3_vacancies_lora\n## Installation\n* You need to download any saiga_llama3_vacanices GGUF model from https://huggingface.co/AlekseyScorpi/saiga_llama3_vacancies_GGUF, create new folder and put the model in it\n* Next you have to set model_config.json for your purpose or you can use my default config (default config assumes that you have created the generation_model folder and placed the model-Q5_K_M.gguf model in it)\n* You need set several environments variables in .env file (create it):\n  * NGROK_AUTH_TOKEN\n  * NGROK_SERVER_DOMAIN\n  * FLASK_PORT\n  * CLIENT_DOMAIN\n### Docker way\n* You should be sure that you have the nvidia container toolkit installed to work with cuda inside containers\n* Just build docker container with ```docker build -t {YOUR_IMAGE_NAME} . ```\n* Run it 😉 , example run script ```docker run --gpus all -p 80:80 vacancies-server-saiga3```\n\n### Default python way\n* First, create new virtual environment and activate it (for this project python 3.11 is using)\n* Second, set new environment variable ```ENV CMAKE_ARGS=\"-DLLAMA_CUDA=on\"``` to build llama_cpp_python with CUDA (be sure, that you have CUDA Toolkit on your device)\n* Then ```run pip install -r requirements.txt```\n* Now you can run your server with ```python start.py```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falekseyscorpi%2Fvacancies_server","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falekseyscorpi%2Fvacancies_server","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falekseyscorpi%2Fvacancies_server/lists"}