About 7 results · 431 indexed
- READMEgithub.com/Shubhamsaboo/awesome-llm-apps/blob/main/advanced_llm_apps/chat_with_X_tutorials/chat_with_pdf/README.md
👉 Click here to follow our complete step-by-step tutorial and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.
- Vision RAG with Cohere Embed-4 🖼️github.com/Shubhamsaboo/awesome-llm-apps/blob/main/rag_tutorials/vision_rag/README.md
A powerful visual Retrieval-Augmented Generation (RAG) system that utilizes Cohere's state-of-the-art Embed-4 model for multimodal embedding and Google's efficient Gemini 2.5 Flash model for answering questions about images and PDF pages.
- Multimodal Agentic RAGgithub.com/Shubhamsaboo/awesome-llm-apps/blob/main/rag_tutorials/multimodal_agentic_rag/README.md
This is a multimodal RAG app built with Gemini Embedding 2 and Google ADK. Add text, URLs, PDFs, images, audio, or video; ask a question; and get a grounded answer with clear citations.
- Typed Agentic RAG with Pydantic AIgithub.com/Shubhamsaboo/awesome-llm-apps/blob/main/rag_tutorials/agentic_typed_rag_pydanticai/README.md
This Streamlit app answers questions from uploaded PDFs or a documentation URL. Every response is a validated Answer object with exact source quotes, chunk IDs, a confidence score, and an answered decision. If retrieval is too weak, the app
- 🌐 Browser MCP Agentgithub.com/Shubhamsaboo/awesome-llm-apps/blob/main/mcp_ai_agents/browser_mcp_agent/README.md
https://github.com/user-attachments/assets/a01e09fa-131b-479a-8df3-2d1a61fd80f3
- Menu component conventionsgithub.com/addyosmani/agent-skills/blob/main/evals/fixtures/frontend-ui-engineering/design-system.md
The new dropdown should expose a trigger label and an array of actions. Disabled actions remain visible but cannot receive focus or execute.
- Widget Interactivitygithub.com/Shubhamsaboo/awesome-llm-apps/blob/main/generative_ui_agents/ai-mcp-app-builder/apps/mcp-use-server/.agent/skills/mcp-apps-builder/references/widgets/interactivity.md
Widgets interact with the outside world using hooks from mcp-use/react. useCallTool() provides tool calling with built-in state management. sendFollowUpMessage from useWidget() triggers LLM conversation turns.