{"id":25637870,"url":"https://github.com/jjasghar/ai-abstract-classifier","last_synced_at":"2025-06-14T14:39:00.896Z","repository":{"id":275821555,"uuid":"923265407","full_name":"jjasghar/ai-abstract-classifier","owner":"jjasghar","description":"Run abstracts through a local LLM to give you some possible scores on what you are looking for.","archived":false,"fork":false,"pushed_at":"2025-02-14T23:11:31.000Z","size":79,"stargazers_count":0,"open_issues_count":2,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-13T16:37:22.660Z","etag":null,"topics":["abstracts","cfp","granite","llm"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jjasghar.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2025-01-27T23:09:25.000Z","updated_at":"2025-02-14T23:11:34.000Z","dependencies_parsed_at":"2025-02-04T19:35:15.894Z","dependency_job_id":"44342a52-0135-4c37-aac5-472176c04179","html_url":"https://github.com/jjasghar/ai-abstract-classifier","commit_stats":null,"previous_names":["jjasghar/ai-abstract-classifier"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jjasghar/ai-abstract-classifier","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjasghar%2Fai-abstract-classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjasghar%2Fai-abstract-classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjasghar%2Fai-abstract-classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjasghar%2Fai-abstract-classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jjasghar","download_url":"https://codeload.github.com/jjasghar/ai-abstract-classifier/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjasghar%2Fai-abstract-classifier/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259833447,"owners_count":22918919,"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":["abstracts","cfp","granite","llm"],"created_at":"2025-02-23T01:29:48.255Z","updated_at":"2025-06-14T14:39:00.870Z","avatar_url":"https://github.com/jjasghar.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ai-abstract-classifier\n\n## Scope\n\nThis is an application that takes [AnythingLLM][anythingllm] and a selection of [abstracts][abstracts]\nand asks a local LLM ([granite][granite] ideally) if the abstract has been written by an AI and/or\nis a possible sales pitch.\nIt gives a file called `overview.csv` with a confidence score of up to `100` if it's been AI or\ntoo \"sales-y.\"\n\nYou can also inject a `csv` into this instead of reading an API, either [pretalx][pretalx] or [sessionize][sessionize] for the time being.\n\n## CSV notes\n\nTake a look at [test_data/testing.csv](./test_data/testing.csv) as an example. You run it via `python main.py -c CSV_FILE`, check `python main.py -h` for help.\n\n**NOTE**: This is `,` seporated for the time being, so you'll need to remove all the `,` from the actual abstracts so it can be parsed correctly.\n\nThe sections that are needed the `csv` are as follows:\n- code\n- title\n- abstract\n- description\n\n## Configuration\n\nEverything is configured in the [config.toml](./config.toml.example) file, copy it to\nthe working directory and do something like the following:\n\nFirst install AnythingLLM, [here](https://anythingllm.com/desktop), and configure it\nwith something along these lines of [this](https://ibm.github.io/opensource-ai-workshop/lab-3/).\n\n**Note**: As of this release you will need to configure the model you want this to us via the\n\"default\" AnythingLLM configuration. It seems for _now_ you can't programaticly change the workspace\nfor different models, so this is the work around.\n\nCheck out [testing_notes.md](./test_data/testing_notes.md) for some of the numbers ran with other\nmodels on the same data.\n\nRun these following commands:\n\n```bash\ngit clone git@github.com:jjasghar/pretalx-ai-validator.git\ncd pretalx-ai-validator\npython3.11 -m venv --upgrade-deps venv\nsource venv/bin/activate\npip install -r requirements.txt\ncp config.toml.example config.toml\nvim config.toml\npython main.py -h\n```\n\n## Utils\n\nThere is a [jsons_to_markdown.py](./utils/jsons_to_markdown.py) to convert the [chat_primes](./chat_primes/jsons/) to readable format(s).\n\n## License \u0026 Authors\n\nIf you would like to see the detailed LICENSE click [here](./LICENSE).\n\n- Author: JJ Asghar \u003cawesome@ibm.com\u003e\n\n```text\nCopyright:: 2025- IBM, Inc\n\nLicensed under the Apache License, Version 2.0 (the \"License\");\nyou may not use this file except in compliance with the License.\nYou may obtain a copy of the License at\n\nhttp://www.apache.org/licenses/LICENSE-2.0\n\nUnless required by applicable law or agreed to in writing, software\ndistributed under the License is distributed on an \"AS IS\" BASIS,\nWITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\nSee the License for the specific language governing permissions and\nlimitations under the License.\n```\n\n\n\n[anythingllm]: https://github.com/Mintplex-Labs/anything-llm\n[abstracts]: https://talks.devopsdays.org/devopsdays-austin-2024/cfp\n[granite]: http://ollama.com/library/granite3.1-dense\n[sessionize]: https://sessionize.com\n[pretalx]: https://pretalx.com/p/about/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjjasghar%2Fai-abstract-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjjasghar%2Fai-abstract-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjjasghar%2Fai-abstract-classifier/lists"}