152 Coding prompts, curated and searchable. Browse all categories →
Python package requirements for a LangChain, LangGraph, Qdrant, and Streamlit AI application stack.
langchain==0.3.12 langgraph==0.2.53 qdrant-client==1.12.1 langchain-openai==0.2.14 langchain-anthropic==0.3.0 tavily-python==0.5.0 langchain-community==0.3.12 langchain-core==0.3.28 streamlit==1.41.1 tenacity==8.5.0 anthropic>=0.7.0 openai>=1.12.0 tiktoken>=0.6.0 pydantic>=2.0.0 numpy>=1.24.0 PyYAML>=6.0.0 nest-asyncio>=1.5.0
A document Q&A app using hybrid search, local LLMs, and RAGLite for accurate, context-aware answers via Streamlit.
A powerful document Q&A application that leverages Hybrid Search (RAG) and local LLMs for comprehensive answers. Built with RAGLite for robust document processing and retrieval, and Streamlit for an intuitive chat interface, this system combines document-specific knowledge with local LLM capabilities to deliver accurate and contextual responses. ## Demo: https://github.com/user-attachments/asse
A requirements list for an AI application stack including OpenAI, LlamaIndex, Qdrant, DSPy, and Streamlit.
nest-asyncio openai==1.61.0 llama-index==0.12.33 llama-index-vector-stores-qdrant==0.6.0 qdrant-client==1.14.1 dspy==2.6.18 faiss-cpu==1.10.0 tavily-python==0.5.4 python-dotenv==1.1.0 streamlit==1.44.1 pandas==2.2.3 requests==2.32.3
Streamlit app to chat with any webpage using local Llama-3.1 and RAG, running fully offline.
## 💻 Local Lllama-3.1 with RAG Streamlit app that allows you to chat with any webpage using local Llama-3.1 and Retrieval Augmented Generation (RAG). This app runs entirely on your computer, making it 100% free and without the need for an internet connection. ### Features - Input a webpage URL - Ask questions about the content of the webpage - Get accurate answers using RAG and the Llama-3.1 mod
Lists Python package requirements for a Streamlit app using Ollama and LangChain integrations.
streamlit ollama langchain langchain_community langchain_ollama
Build a fully local RAG system using Llama 3.2, Qdrant vector DB, and Agno v2.0 with no external API dependencies.
## 🦙 Local RAG Agent with Llama 3.2 ### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-a-local-rag-agent) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** This application implements a Retrieval-Augmented Generation (RAG) system using Llama 3.2 via Ollama,
Specifies Python package dependencies including agno, qdrant-client, ollama, and pypdf.
agno>=2.2.10 qdrant-client ollama pypdf
RAG agentic system using Gemini 2.0, Qdrant vector storage, and Agno for intelligent document querying and web search fallback.
A RAG Agentic system built with the new Gemini 2.0 Flash Thinking model and gemini-exp-1206, Qdrant for vector storage, and Agno (phidata prev) for agent orchestration. This application features intelligent query rewriting, document processing, and web search fallback capabilities to provide comprehensive AI-powered responses. ## Features - **Document Processing** - PDF document upload and pro
A list of Python package dependencies including agno, exa, qdrant-client, langchain, and streamlit.
agno exa==0.5.26 qdrant-client==1.12.1 langchain-qdrant==0.2.0 langchain-community==0.3.13 streamlit==1.41.1
Build an autonomous RAG Streamlit app using GPT-4o, PgVector, PDF uploads, and DuckDuckGo web search.
**🎓 FREE Step-by-Step Tutorial** **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-autonomous-rag-app-using-gpt-4o-and-vector-database) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** This Streamlit application implements an Autonomous Retrieval-Augmented Generation (RAG) system using Op
Lists Python package dependencies for a Streamlit AI app with OpenAI, pgvector, and search.
streamlit agno openai psycopg-binary pgvector requests sqlalchemy pypdf duckduckgo-search nest_asyncio
Build a RAG system with real-time step-by-step reasoning using Agno, Gemini 2.5 Flash, and OpenAI embeddings.
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-an-agentic-rag-app-with-reasoning) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** A sophisticated RAG system that demonstrates an AI agent's step-by-step reasoning process using Agno, Gemini and OpenAI. T
Tutorial and setup guide for a local agentic RAG app using EmbeddingGemma, Llama 3.2, LanceDB, and Streamlit.
## 🔥 Agentic RAG with EmbeddingGemma ### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-a-local-agentic-rag-app-with-google-embeddinggemma) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** This Streamlit app demonstrates an agentic Retrieval-Augmented Gene
A list of Python package dependencies including Streamlit, Agno, LanceDB, Ollama, and PyPDF.
streamlit agno>=2.2.10 lancedb ollama pypdf
LangGraph-powered agentic RAG app using Gemini, Qdrant, and Streamlit to retrieve and answer queries from AI blog posts.
## Overview AI Blog Search is an Agentic RAG application designed to enhance information retrieval from AI-related blog posts. This system leverages LangChain, LangGraph, and Google's Gemini model to fetch, process, and analyze blog content, providing users with accurate and contextually relevant answers. ## LangGraph Workflow  for faithful, retrieval-grounded answers - Reranking of retri
A pip requirements file specifying versioned dependencies for a Streamlit and Pydantic project.
streamlit==1.40.2 contextual-client>=0.1.0 requests>=2.32.0 pydantic==2.9.2
Document Q&A app using hybrid RAG search, Claude, OpenAI embeddings, and Cohere reranking via Streamlit.
A powerful document Q&A application that leverages Hybrid Search (RAG) and Claude's advanced language capabilities to provide comprehensive answers. Built with RAGLite for robust document processing and retrieval, and Streamlit for an intuitive chat interface, this system seamlessly combines document-specific knowledge with Claude's general intelligence to deliver accurate and contextual responses
A pip requirements file listing Python packages for an AI/RAG application stack.
raglite==0.2.1 pydantic==2.10.1 sqlalchemy>=2.0.0 psycopg2-binary>=2.9.9 openai>=1.0.0 cohere>=4.37 pypdf>=3.0.0 python-dotenv>=1.0.0 rerankers==0.6.0 spacy>=3.7.0 streamlit anthropic
Agentic RAG system using Cohere, Qdrant, LangChain, and LangGraph with web search fallback.
A RAG Agentic system built with Cohere's new model Command-r7b-12-2024, Qdrant for vector storage, Langchain for RAG and LangGraph for orchestration. This application allows users to upload documents, ask questions about them, and get AI-powered responses with fallback to web search when needed. ## Features - **Document Processing** - PDF document upload and processing - Automatic text chunk
Build a production-ready RAG pipeline using Claude 3.5 Sonnet and Ragie.ai with a Streamlit UI in under 50 lines.
## 🖇️ RAG-as-a-Service with Claude 3.5 Sonnet Build and deploy a production-ready Retrieval-Augmented Generation (RAG) service using Claude 3.5 Sonnet and Ragie.ai. This implementation allows you to create a document querying system with a user-friendly Streamlit interface in less than 50 lines of Python code. ### Features - Production-ready RAG pipeline - Integration with Claude 3.5 Sonnet for
Lists Python package dependencies: streamlit, anthropic, and requests.
streamlit anthropic requests
Build a local RAG agent using Deepseek, Qdrant, and Snowflake embeddings with PDF ingestion and web search.
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-a-local-rag-reasoning-agent-with-deepseek-r1) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** A powerful reasoning agent that combines local Deepseek models with RAG capabilities. Built using Deepseek (via
A requirements list for a Python project using Agno, Exa, Qdrant, LangChain, Streamlit, and Ollama.
agno exa==0.5.26 qdrant-client==1.12.1 langchain-qdrant==0.2.0 langchain-community==0.3.13 streamlit==1.41.1 ollama
A list of Python package dependencies for a Streamlit LangChain Google Gemini RAG application.
streamlit langchain-google-genai langchain-chroma langchain-community langchain-core chromadb sentence-transformers PyPDF2 python-dotenv
Build a local RAG system using Qwen3/Gemma3 via Ollama with PDF ingestion, Qdrant vector search, and web search fallback.
This RAG Application demonstrates how to build a powerful Retrieval-Augmented Generation (RAG) system using locally running Qwen 3 and Gemma 3 models via Ollama. It combines document processing, vector search, and web search capabilities to provide accurate, context-aware responses to user queries. Built with Agno v2.0. ## Features - **🧠 Multiple Local LLM Options**: - Qwen3 (1.7b, 8b) - Alib
Streamlit app using MCP and Playwright to control a browser with natural language commands and LLMs.
https://github.com/user-attachments/assets/a01e09fa-131b-479a-8df3-2d1a61fd80f3 A Streamlit application that allows you to browse and interact with websites using natural language commands through the Model Context Protocol (MCP) and [MCP-Agent](https://github.com/lastmile-ai/mcp-agent) with Playwright integration. ## Features - **Natural Language Interface**: Control a browser with simple Engl
A requirements.txt listing Streamlit, MCP Agent, OpenAI, and asyncio package dependencies.
streamlit>=1.28.0 mcp-agent>=0.0.14 openai>=1.0.0 asyncio>=3.4.3
A Streamlit app routing queries to specialized AI agents—code reviewer, security auditor, researcher, BIM engineer—each with tailored MCP tools.
A Streamlit app that demonstrates the **multi-agent + MCP** pattern: specialized AI agents that each connect to different MCP servers to handle domain-specific tasks. Instead of one agent with all tools, The router sends your request to a **specialist** — a code reviewer, security auditor, researcher, or BIM engineer — each with access to only the MCP tools they need. ## Features - **4 Speciali