199+ AI RAG Workflows
Set of 199 workflows for building RAG (Retrieval-Augmented Generation) systems. Create chatbots that answer questions from documents, knowledge bases from Google Drive and intelligent semantic search engines using Pinecone, Supabase, Qdrant and OpenAI.
Features
- Q&A chatbots for PDF and Google Drive documents
- Automatic document indexing to vector databases
- Semantic search with Cohere reranking
- Integration with Pinecone, Supabase, Qdrant, MongoDB
- Knowledge systems for customer support
- RAG for academic research and article analysis
- Automatic Google Drive synchronization
- Multi-source RAG with multiple data sources
Talk to your documents
This pack contains 199 workflows for building RAG systems - technology that allows AI to answer questions based on your own documents. No more AI hallucinations - answers based on facts from your knowledge base.
Document Chatbots
Build a chatbot that answers questions from PDF files, Google Drive documents or websites. Users can ask questions in natural language and receive precise answers with source citations.
Vector Databases
Workflows support the most popular vector databases: Pinecone, Supabase Vector, Qdrant, MongoDB Atlas and pgVector. Choose the solution that fits your needs and budget.
Automatic Indexing
Documents from Google Drive are automatically processed, chunked and indexed. When you add a new file - the system processes and adds it to the knowledge base automatically.
Reranking and Quality
Advanced workflows use Cohere Reranker to improve result quality. The system selects the most relevant document fragments, ensuring precise answers.
Customer Support with Knowledge Base
Create support systems that answer customer questions based on product documentation, FAQs or company policies. Automatically and truthfully.