{"id":13576930,"url":"https://github.com/logikon-ai/logikon","last_synced_at":"2025-04-05T09:30:35.670Z","repository":{"id":209800283,"uuid":"689578430","full_name":"logikon-ai/logikon","owner":"logikon-ai","description":"Analyzing and scoring reasoning traces of LLMs","archived":false,"fork":false,"pushed_at":"2024-09-01T17:42:45.000Z","size":6333,"stargazers_count":39,"open_issues_count":10,"forks_count":0,"subscribers_count":5,"default_branch":"main","last_synced_at":"2024-11-05T13:43:14.634Z","etag":null,"topics":["ai","argument-mapping","argument-mining","argumentation","critical-thinking","explainable-ai","llmops","llms","metrics","mlops","observability","reasoning","reasoning-agent","reliable-ai"],"latest_commit_sha":null,"homepage":"https://logikon.ai","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/logikon-ai.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":"2023-09-10T09:01:23.000Z","updated_at":"2024-10-12T00:00:55.000Z","dependencies_parsed_at":"2024-08-28T13:21:57.504Z","dependency_job_id":null,"html_url":"https://github.com/logikon-ai/logikon","commit_stats":null,"previous_names":["logikon-ai/logikon"],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/logikon-ai%2Flogikon","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/logikon-ai%2Flogikon/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/logikon-ai%2Flogikon/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/logikon-ai%2Flogikon/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/logikon-ai","download_url":"https://codeload.github.com/logikon-ai/logikon/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247317884,"owners_count":20919444,"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":["ai","argument-mapping","argument-mining","argumentation","critical-thinking","explainable-ai","llmops","llms","metrics","mlops","observability","reasoning","reasoning-agent","reliable-ai"],"created_at":"2024-08-01T15:01:15.980Z","updated_at":"2025-04-05T09:30:35.644Z","avatar_url":"https://github.com/logikon-ai.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"\n\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"./docs/logo_logikon_notext_withborder.png\" alt=\"Logikon Logo\" width=100\u003e\u003c/img\u003e\n\n# Logikon\n\n*AI Analytics for Natural Language Reasoning.*\n\n🕹️ [Guided Reasoning™️ Demo](https://huggingface.co/spaces/logikon/benjamin-chat) | 📄 [Technical Report](https://arxiv.org/abs/2408.16331)\n\n\u003c/div\u003e\n\n\u003e [!NOTE]\n\u003e 🎉\u0026nbsp; We're excited to announce the release of `Logikon 0.2.0` –– a major update to our analytics toolbox for natural-language reasoning. \n\nMain changes: \n\n* All LLM-based argument analysis pipelines are now built with _LCEL/LangChain_ (and not with LMQL anymore).\n* We're introducing _Guided Reasoning™️_ (abstract interface and simple implementations) for walking arbitrary conversational AI agents through complex reasoning processes.\n* AGPL license.\n\nOur *short-term priorities* are housekeeping, code cleaning, and documentation. Don't hesitate to reach out if you have any questions or feedback, or if you'd like to contribute to the project.\n\n\n## Installation \n\n```\npip install git+https://github.com/logikon-ai/logikon@v0.2.0\n```\n\n## Basic usage\n\n```python\nimport os\nfrom logikon import ascore, ScoreConfig\n\n# 🔧 config \nconfig = ScoreConfig(\n    global_kwargs={\n        \"expert_model\": \"meta-llama/Meta-Llama-3-70B-Instruct\",\n        \"inference_server_url\": \"https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-70B-Instruct\",\n        \"llm_backend\": \"HFChat\",\n        \"api_key\": os.environ[\"HF_TOKEN\"],\n        \"classifier_kwargs\": {\n            \"model_id\": \"MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli\",\n            \"inference_server_url\": \"https://api-inference.huggingface.co/models/MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli\",\n            \"api_key\": os.environ[\"HF_TOKEN\"],\n            \"batch_size\": 8,\n        },\n    }\n)\n\n# 📝 input to evaluate\nissue = \"Should I eat animals?\",\nreasoning = \"No! Animals can suffer. Animal farming causes climate heating. Meat is not healthy.\",\n\n# 🏃‍♀️ run argument analysis\nresult = await ascore(\n    prompt = issue,\n    completion = reasoning,\n    config = config,\n)\n```\n\n## Guided Reasoning™️\n\n```mermaid\nsequenceDiagram\n    autonumber\n    actor User\n    participant C as Client LLM\n    User-\u003e\u003e+C: Problem statement\n    create participant G as Guide LLM\n    C-\u003e\u003e+G: Problem statement\n    loop \n        G-\u003e\u003e+C: Instructions...\n        C-\u003e\u003e+G: Reasoning traces...\n        G-\u003e\u003e+G: Evaluation\n    end\n    destroy G\n    G-\u003e\u003e+C: Answer + Protocol\n    C-\u003e\u003e+User: Answer (and Protocol)\n    User-\u003e\u003e+C: Why?\n    C-\u003e\u003e+User: Explanation (based on Protocol)\n```\n\n\u003c!--\n## Quickstart\n\nStart server.\n\n```sh\nbash scripts/run_vllm_server.sh\n```\n\nRun python client.\n\n```python\nfrom logikon import ascore\n\nawait ascore(\n    prompt=\"What are the main reasons for spending a week-end in New York?\",\n    completion=\"\"\"\n    The main reasons for spending a week-end in New York are:\n    1. You can do great shopping.\n    2. You can eat wonderful food.\n    3. You can meet many interesting people and friends.\n    \"\"\"\n)\n```\n\n## Development\n\n```sh\n# style check\nhatch run lint:style\n\n# format code\nhatch run lint:fmt\n\n# check types (mypy)\nhatch run lint:typing\n\n# run tests\nhatch run test\n```\n\n--\u003e\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flogikon-ai%2Flogikon","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flogikon-ai%2Flogikon","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flogikon-ai%2Flogikon/lists"}