{"id":27471092,"url":"https://github.com/swish78/business-intelligence-assistant","last_synced_at":"2026-07-09T08:31:39.611Z","repository":{"id":284999653,"uuid":"956756164","full_name":"Swish78/Business-Intelligence-Assistant","owner":"Swish78","description":null,"archived":false,"fork":false,"pushed_at":"2025-03-28T20:05:19.000Z","size":8,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-28T21:22:17.352Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Swish78.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":"2025-03-28T20:03:48.000Z","updated_at":"2025-03-28T20:05:22.000Z","dependencies_parsed_at":"2025-03-28T21:22:19.572Z","dependency_job_id":"8ee1e4fb-5a90-4c41-8eb5-7310a319da38","html_url":"https://github.com/Swish78/Business-Intelligence-Assistant","commit_stats":null,"previous_names":["swish78/business-intelligence-assistant"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swish78%2FBusiness-Intelligence-Assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swish78%2FBusiness-Intelligence-Assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swish78%2FBusiness-Intelligence-Assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swish78%2FBusiness-Intelligence-Assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Swish78","download_url":"https://codeload.github.com/Swish78/Business-Intelligence-Assistant/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249182786,"owners_count":21226123,"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":[],"created_at":"2025-04-16T01:38:53.517Z","updated_at":"2025-10-25T21:36:15.416Z","avatar_url":"https://github.com/Swish78.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Business Intelligence Assistant\n\nA multi-agent system for comprehensive business data analysis using specialized AI agents.\n\n## Overview\n\nThis project implements a CrewAI-based system that uses multiple specialized AI agents to analyze business data across different domains:\n- Sales analysis\n- Marketing optimization\n- Customer support evaluation\n- Financial health assessment\n\n## Features\n\n- **Multi-Agent System**: Leverages specialized AI agents with domain expertise\n- **Comprehensive Analysis**: Examines data across sales, marketing, finance, and support\n- **Resilient Design**: Implements retry logic and model switching to handle API limitations\n- **Multiple LLM Support**: Configurable to work with various Groq models\n\n## Implementation Details\n\n### Agents\n\nThe system includes the following specialized agents:\n- **Sales Analyst**: Identifies sales trends and growth opportunities\n- **Marketing Strategist**: Analyzes campaign effectiveness and ROI\n- **Customer Support Manager**: Evaluates support efficiency\n- **Financial Advisor**: Examines financial health and cost optimization\n\n### Technical Notes\n\nI encountered TPM (Tokens Per Minute) limitations while executing the project. I implemented retry logic and model switching, but full execution wasn't possible under the current constraints. Here's my approach:\n\n- **Model Rotation**: The system can switch between multiple Groq models when rate limits are encountered\n- **Exponential Backoff**: Implements increasing wait times between retries \n- **Fallback Mechanism**: Gracefully handles API limitations by switching to alternative models\n- **Cache Support**: Enables caching to reduce duplicate API calls\n\n## Setup\n\n1. Clone the repository\n2. Install requirements\n3. Create a `.env` file with the following variables:\n   ```\n   GROQ_API_KEY=your_groq_api_key\n   SERPER_API_KEY=your_serper_api_key\n   ```\n4. Place your CSV data files in the project directory\n5. Run the application\n\n## Usage\n\nThe system can be run in two modes:\n- **Command Line**: `python crew2.py --no-ui`\n- **Gradio Interface**: `python crew2.py`\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fswish78%2Fbusiness-intelligence-assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fswish78%2Fbusiness-intelligence-assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fswish78%2Fbusiness-intelligence-assistant/lists"}