AI-Powered Multimodal and Financial Systems

1. Web Search Agent Objective: A web search agent that queries DuckDuckGo to retrieve information based on user requests, including references to sources. Key Technologies: Groq (LLAMA 3.2), DuckDuckGo, Python Features: Automatically fetches relevant data from the web. Provides results in markdown format for easy reading.
2. Finance AI Agent Objective: A financial analysis agent using YFinanceTools to provide stock price data, analyst recommendations, and the latest company news. Key Technologies: Groq (LLAMA 3.2), YFinanceTools, Python Features: Fetches real-time stock data, analyst opinions, and financial news. Formats responses with markdown and tables for enhanced clarity.
3. Multi-Agent Collaboration System Objective: A system that combines multiple agents to collaborate on complex tasks. The web search agent and financial agent work together to retrieve and analyze information. Key Technologies: Groq (LLAMA 3.2), DuckDuckGo, YFinanceTools, Python Features: Seamlessly integrates multiple agents to improve task efficiency. Uses Groq models for quick, accurate query responses.
4. Phidata Video AI Summarizer Objective: A multimodal AI system that analyzes uploaded videos and summarizes their content, while also retrieving additional insights from the web. Key Technologies: Gemini 2.0 Flash, DuckDuckGo, Streamlit, Python Features: Processes video files and provides content analysis based on user queries. Retrieves additional context from the web to support video insights. Interactive interface using Streamlit for easy video uploads and query submission.
5. Playground for Interactive AI Agents Objective: A web-based application that allows users to interact with AI agents for web search and financial analysis tasks. Key Technologies: OpenAI GPT-3.5 Turbo, Phi Playground, FastAPI, Python Features: Real-time interaction with AI agents in a web environment. Support for multiple agents working together for complex queries.
6. Stock Analysis Assistant with Knowledge Base Integration Objective: A stock assistant that uses a PDF-based knowledge base and semantic search for financial insights. Key Technologies: PostgreSQL, PgVector, PDFUrlKnowledgeBase, Python Features: Integrates a knowledge base of stock-related PDFs with vectorized search using PgVector. Allows conversational AI interactions for stock-related questions and insights.
7. PDF Knowledge Base for Stock Insights Objective: A knowledge base that parses stock-related PDFs and provides semantic search for financial insights. Key Technologies: PgVector, PDFUrlKnowledgeBase, Python Features: Extracts and vectorizes data from PDF documents for efficient search. Enables an AI-driven assistant to respond to stock-related queries.

Contributing Feel free to contribute to this project! If you have ideas, bug fixes, or enhancements, please submit a pull request or open an issue.

License This project is licensed under the MIT License - see the LICENSE file for details.