{"id":125566,"url":"https://github.com/nalinrajendran/synthetic-LLM-QA-dataset-generator","last_synced_at":"2026-06-19T17:02:00.537Z","repository":{"id":236469568,"uuid":"792673767","full_name":"nalinrajendran/synthetic-LLM-QA-dataset-generator","owner":"nalinrajendran","description":"Create synthetic datasets for training and testing Language Learning Models (LLMs) in a Question-Answering (QA) context.","archived":false,"fork":false,"pushed_at":"2025-06-01T12:34:47.000Z","size":13707,"stargazers_count":59,"open_issues_count":0,"forks_count":17,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-06-11T13:04:56.358Z","etag":null,"topics":["ai","dataset","dataset-generation","fine-tuning","finetune","gpt","llama3","llm","ollama"],"latest_commit_sha":null,"homepage":"","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/nalinrajendran.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,"zenodo":null}},"created_at":"2024-04-27T08:37:53.000Z","updated_at":"2026-05-04T05:01:13.000Z","dependencies_parsed_at":"2025-06-12T22:32:58.829Z","dependency_job_id":"d675fe3e-3b8b-4481-a357-7a9123a8ece6","html_url":"https://github.com/nalinrajendran/synthetic-LLM-QA-dataset-generator","commit_stats":null,"previous_names":["nalinrajendran/synthetic-llm-qa-dataset-generator"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/nalinrajendran/synthetic-LLM-QA-dataset-generator","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nalinrajendran%2Fsynthetic-LLM-QA-dataset-generator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nalinrajendran%2Fsynthetic-LLM-QA-dataset-generator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nalinrajendran%2Fsynthetic-LLM-QA-dataset-generator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nalinrajendran%2Fsynthetic-LLM-QA-dataset-generator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nalinrajendran","download_url":"https://codeload.github.com/nalinrajendran/synthetic-LLM-QA-dataset-generator/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nalinrajendran%2Fsynthetic-LLM-QA-dataset-generator/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34367696,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-15T02:00:07.085Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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"}},"owner":{"login":"nalinrajendran","name":"Nalin Rajendran","uuid":"51052614","kind":"user","description":"B.tech in Artificial Intelligence.\r\n-\u003e ML\r\n-\u003e FULL STACK","email":"","website":"https://nalinrajendran.github.io/me/","location":"POLLACHI","twitter":"NalinRajendran","company":"Amrita Vishwa Vidyapeetham","icon_url":"https://avatars.githubusercontent.com/u/51052614?u=98a9cfbf93154f80c3512adba8e2110742c3291f\u0026v=4","repositories_count":2,"last_synced_at":"2023-04-28T09:48:58.974Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/nalinrajendran","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2023-04-28T09:48:58.976Z","updated_at":"2023-04-28T09:48:58.976Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nalinrajendran","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nalinrajendran/repositories"},"packages":[],"commits":{"id":1641028,"full_name":"nalinrajendran/synthetic-LLM-QA-dataset-generator","default_branch":"main","total_commits":12,"total_committers":2,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":6.0,"dds":0.5,"past_year_total_commits":0,"past_year_total_committers":0,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":0.0,"past_year_dds":0.0,"last_synced_at":"2026-06-11T13:04:01.831Z","last_synced_commit":"1daacdc422dfe18759618762419b544bd4accb6c","created_at":"2024-07-25T15:46:03.152Z","updated_at":"2026-06-11T13:04:01.716Z","committers":[{"name":"aamanlamba","email":"aamanlamba@gmail.com","login":"aamanlamba","count":6},{"name":"Nalin Rajendran","email":"nalinrajendran1@gmail.com","login":"nalinrajendran","count":6}],"past_year_committers":[],"commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/nalinrajendran%2Fsynthetic-LLM-QA-dataset-generator/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-06-15T00:00:11.107Z","repositories_count":6259886,"commits_count":882474557,"contributors_count":35087608,"owners_count":1166779,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues":{"table":{"full_name":"nalinrajendran/synthetic-LLM-QA-dataset-generator","html_url":"https://github.com/nalinrajendran/synthetic-LLM-QA-dataset-generator","last_synced_at":"2026-03-11T16:01:49.008Z","status":"error","issues_count":0,"pull_requests_count":1,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":11363847.0,"issues_closed_count":0,"pull_requests_closed_count":1,"pull_request_authors_count":1,"issue_authors_count":0,"avg_comments_per_issue":null,"avg_comments_per_pull_request":0.0,"merged_pull_requests_count":1,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":1,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":11363847.0,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":1,"past_year_pull_request_authors_count":1,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":0.0,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":1,"created_at":"2024-07-25T15:46:10.843Z","updated_at":"2026-03-11T16:01:49.008Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/nalinrajendran%2Fsynthetic-LLM-QA-dataset-generator","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/nalinrajendran%2Fsynthetic-LLM-QA-dataset-generator/issues","issue_labels_count":{"table":{}},"pull_request_labels_count":{"table":{}},"issue_author_associations_count":{"table":{}},"pull_request_author_associations_count":{"table":{"NONE":1,"CONTRIBUTOR":1}},"issue_authors":{"table":{}},"pull_request_authors":{"table":{"aamanlamba":2}},"host":{"table":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-06-15T00:00:22.443Z","repositories_count":14809256,"issues_count":33180029,"pull_requests_count":109469375,"authors_count":11306955,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"}},"past_year_issue_labels_count":{"table":{}},"past_year_pull_request_labels_count":{"table":{}},"past_year_issue_author_associations_count":{"table":{}},"past_year_pull_request_author_associations_count":{"table":{}},"past_year_issue_authors":{"table":{}},"past_year_pull_request_authors":{"table":{}},"maintainers":[],"active_maintainers":[]}},"events":{"total":{"PullRequestEvent":2,"ForkEvent":9,"WatchEvent":28,"PushEvent":2,"CreateEvent":1},"last_year":{"ForkEvent":1,"WatchEvent":7}},"keywords":["ai","dataset","dataset-generation","fine-tuning","finetune","gpt","llama3","llm","ollama"],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2025-06-12T22:32:58.753Z","updated_at":"2025-06-12T22:32:58.753Z","repository_link":"https://github.com/nalinrajendran/synthetic-LLM-QA-dataset-generator/blob/main/requirements.txt","dependencies":[{"id":23591505435,"package_name":"openai","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23591505436,"package_name":"tqdm","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23591505437,"package_name":"PyPDF2","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23591505438,"package_name":"ollama","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23591505439,"package_name":"prompt_toolkit","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":4.770684624465665,"created_at":"2024-07-25T15:26:44.206Z","updated_at":"2026-06-19T17:02:00.537Z","avatar_url":"https://github.com/nalinrajendran.png","language":"Python","codemeta":null,"publiccode":null,"project_url":"https://summary.ecosyste.ms/api/v1/projects/125566","html_url":"https://summary.ecosyste.ms/projects/125566"}