RAG Knowledge Base Chatbot
Ingests PDF knowledge bases via Jotform and answers user chat questions using semantic search and Google Gemini.
This directory currently includes 15 recipes for the knowledge q&a (rag) pattern, across 10 roles. Knowledge Q&A agents answer questions against a defined body of material rather than relying only on general model knowledge. They retrieve relevant documents, policies, notes, or records, then use that context to produce a focused answer. This pattern is useful when people repeatedly need help finding reliable information across a shared corpus. The examples show different domains, but the boundary is the same: the agent should make the source visible and admit when the corpus does not support an answer. Good knowledge agents depend on content quality, access control, and a sensible update process as much as on the model itself. Start with a contained, well-maintained source set and a question type with a clear owner for corrections. Every example makes its inputs, output, and handoff concrete, so you can compare real workflow boundaries before adapting the pattern to your own tools and process.
Ingests PDF knowledge bases via Jotform and answers user chat questions using semantic search and Google Gemini.
Chat with your data sources to retrieve information and perform precise calculations using an LLM and calculator tool.
Upload PDFs to a local vector store and ask questions; the agent retrieves relevant text chunks from your documents to generate accurate...
Ingests web pages via URL into a vector store and answers questions using retrieved context with reranking.
Chat with your data sources to retrieve information and perform precise calculations using an LLM and calculator tool.
Upload PDFs to a local vector store and ask questions; the agent retrieves relevant text chunks from your documents to generate accurate...
Ingests Google Docs into a vector database via Together AI and answers Telegram questions using only that retrieved context.
Ingests PDF knowledge bases via Jotform and answers user chat questions using semantic search and Google Gemini.
Users type a slash command in public Slack channels to get an instant AI-generated answer based on their question.
A voice chatbot that routes spoken questions to specialized InfraNodus knowledge graphs and returns synthesized audio answers.
Ingests web pages via URL into a vector store and answers questions using retrieved context with reranking.
Answers customer questions using live WooCommerce data and policy docs, escalating unresolved chats to human support via email.
Answers student course questions via SMS by querying an Airtable database with an AI agent.
Ask ops or finance questions; the agent queries live records, runs Python analysis, and returns tailored insights.
Turns your Google Docs into a searchable AI knowledge base that answers questions with cited sources and logs every interaction.
Ask natural language questions about your Trello board to get instant summaries, overdue items, or status updates without manual navigation.
Answers student course questions via SMS by querying an Airtable database with an AI agent.
Ask natural language questions about tax code policies and get precise answers grounded in specific sections of government documents.
Chat with your Meta Ads data to list accounts, view campaign details.
Ask ops or finance questions; the agent queries live records, runs Python analysis, and returns tailored insights.
Turns your Google Docs into a searchable AI knowledge base that answers questions with cited sources and logs every interaction.
Ingests product docs from Google Docs into a vector store to answer internal queries with accurate, context-aware AI responses.
Ask natural language questions about your Trello board to get instant summaries, overdue items, or status updates without manual navigation.
Users type a slash command in public Slack channels to get an instant AI-generated answer based on their question.
A voice chatbot that routes spoken questions to specialized InfraNodus knowledge graphs and returns synthesized audio answers.
Ingests Google Docs into a vector database via Together AI and answers Telegram questions using only that retrieved context.
It retrieves relevant material from a defined corpus and uses it to answer a question with grounded context.
Use current source material, show citations, control access, and provide a way to correct gaps or errors.
No. It should stay within its authorized corpus and clearly say when the answer is missing or uncertain.