{"id":28760815,"url":"https://github.com/satunix/aatis-skms","last_synced_at":"2026-05-16T13:04:36.890Z","repository":{"id":297939538,"uuid":"997155750","full_name":"SATUNIX/AATIS-SKMS","owner":"SATUNIX","description":"Private and Local - Smart Knowledge Management System - SKMS","archived":false,"fork":false,"pushed_at":"2025-07-08T10:57:23.000Z","size":86,"stargazers_count":0,"open_issues_count":2,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-08T11:49:37.939Z","etag":null,"topics":["autogen","localai","ollama","python"],"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/SATUNIX.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":"2025-06-06T03:49:10.000Z","updated_at":"2025-07-08T10:57:27.000Z","dependencies_parsed_at":null,"dependency_job_id":"7de6e36d-1b09-42b6-858b-db85063738da","html_url":"https://github.com/SATUNIX/AATIS-SKMS","commit_stats":null,"previous_names":["satunix/aatis-skms"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/SATUNIX/AATIS-SKMS","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SATUNIX%2FAATIS-SKMS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SATUNIX%2FAATIS-SKMS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SATUNIX%2FAATIS-SKMS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SATUNIX%2FAATIS-SKMS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SATUNIX","download_url":"https://codeload.github.com/SATUNIX/AATIS-SKMS/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SATUNIX%2FAATIS-SKMS/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33103971,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-16T04:41:52.686Z","status":"ssl_error","status_checked_at":"2026-05-16T04:41:52.009Z","response_time":115,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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"}},"keywords":["autogen","localai","ollama","python"],"created_at":"2025-06-17T06:10:01.557Z","updated_at":"2026-05-16T13:04:36.884Z","avatar_url":"https://github.com/SATUNIX.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LEGACY \n\n# SKMS AATIS Module\nAgentic Assistance for Testing Information Systems\nSmart Knowledge Management System 0.0.1\n\n\u003e Fully Local \u0026 Privacy Friendly, (only outbound is websearches via Bing Web Search API)\n\nSee issues page for current known issues.\n\nA single Python-based CLI tool to:\n\n1. **generate**: Search the web and RAG store, summarize results into a timestamped markdown report.\n2. **ask**: Run a RAG-powered Question \u0026 Answer session over your previously saved reports.\n3. **refresh**: Ingest all markdown (`.md`) reports into a FAISS vector store for future queries.\n\nThis tool utilizes AutoGen 0.6.1, the Bing Web Search API (search engine), Ollama (language model), and FAISS (vector database).\n\n---\n```mermaid\nflowchart TD\n  main[main.py CLI] --\u003e|generate| gen[generate_agent.py]\n  main --\u003e|ask| ask[qa_agent.py]\n  main --\u003e|refresh| refresh[ingest_reports.py]\n\n  gen --\u003e search[BingSearchTool]\n  gen --\u003e fetch[FetchWebpageTool]\n  gen --\u003e rag1[RagStore]\n  gen --\u003e model1[OllamaChatCompletionClient]\n\n  ask --\u003e rag2[RagStore]\n  ask --\u003e model2[OllamaChatCompletionClient]\n\n  refresh --\u003e rag3[RagStore]\n\n```\n\n## Prerequisites\n\n- Python 3.8 or newer\n- Git\n- **Bing Search API Key**: Set the `BING_SEARCH_API_KEY` environment variable to your Bing Search API key.\n- **Bing Search Endpoint (optional)**: Set the `BING_SEARCH_ENDPOINT` environment variable (default: `https://api.bing.microsoft.com/v7.0/search`).\n- Running Ollama server (default URL: `http://localhost:11434`)\n\n---\n\n## Quickstart Guide\n\n### Step 1: Clone the Repository\n\n```bash\ngit clone https://your.repo.url/project.git\ncd project\n```\n\n### Step 2: Setup Virtual Environment\n\nLinux/macOS:\n```bash\npython3 -m venv .venv\nsource .venv/bin/activate\n```\n\nWindows:\n```bash\npython -m venv .venv\n.venv\\Scripts\u0007ctivate\n```\n\n### Step 3: Install Dependencies\n\n```bash\npip install --upgrade pip\npip install autogen-agentchat==0.6.1 \"autogen-ext[ollama]\" requests beautifulsoup4 sentence-transformers faiss-cpu\n```\n\n### Step 4: Create Initialization Files\n\n```bash\ntouch tools/__init__.py agents/__init__.py rag/__init__.py\n```\n\n### Step 5: Configure Ollama Client\n\nEdit the file `config/ollama_config.json`:\n\n```json\n{\n  \"model\": \"llama3\",\n  \"base_url\": \"http://localhost:11434\"\n}\n```\n\n---\n\n## Usage Instructions\n\n### Generate a New Report\n\nThis command searches the web, summarizes findings using Ollama, and saves the output as a timestamped markdown file:\n\n```bash\npython main.py generate \"quantum computing breakthroughs\"\n```\n\n### Refresh RAG Database\n\nIngest all existing markdown reports into the FAISS database:\n\n```bash\npython main.py refresh\n```\n\n### Ask a Question\n\nUse this to query your RAG database and model knowledge:\n\n```bash\npython main.py ask \"What did we learn about quantum entanglement?\"\n```\n\n---\n\n## Configuration Options\n\n- **Bing Search API**: Provide your API key via the `BING_SEARCH_API_KEY` environment variable and optionally override the endpoint with `BING_SEARCH_ENDPOINT`.\n- **Ollama model settings**: Adjust in `config/ollama_config.json`.\n- **Embedding model**: Set in `rag/rag_store.py` (default is `all-MiniLM-L6-v2`).\n\n---\n\n## Troubleshooting Common Issues\n\n- Connection errors to the Bing Search API or Ollama: Ensure your API key is valid, environment variables are set, and endpoints are correct.\n- No reports found during refresh: Confirm that you have run the `generate` command at least once.\n- FAISS errors: Check file permissions or delete and regenerate the `rag/index.faiss` file.\n\n---\n\nYou are now ready to use the Unified RAG \u0026 Research CLI tool.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsatunix%2Faatis-skms","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsatunix%2Faatis-skms","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsatunix%2Faatis-skms/lists"}