No faster way to get started than by diving in and playing around with one of our demos.
Demo | Description |
---|---|
ArxivChatGuru | Streamlit demo of RAG over Arxiv documents with Redis & OpenAI |
Redis VSS - Simple Streamlit Demo | Streamlit demo of Redis Vector Search |
Vertex AI & Redis | A tutorial featuring Redis with Vertex AI |
Agentic RAG | A tutorial focused on agentic RAG with LlamaIndex and Cohere |
ArXiv Search | Full stack implementation of Redis with React FE |
Product Search | Vector search with Redis Stack and Redis Enterprise |
Need specific sample code to help get started with Redis? Start here.
Recipe | Description |
---|---|
/redis-intro/redis_intro.ipynb | The place to start if brand new to Redis |
/vector-search/00_redispy.ipynb | Vector search with Redis python client |
/vector-search/01_redisvl.ipynb | Vector search with Redis Vector Library |
Retrieval Augmented Generation (aka RAG) is a technique to enhance the ability of an LLM to respond to user queries. The retrieval part of RAG is supported by a vector database, which can return semantically relevant results to a user’s query, serving as contextual information to augment the generative capabilities of an LLM.
To get started with RAG, either from scratch or using a popular framework like Llamaindex or LangChain, go with these recipes:
Recipe | Description |
---|---|
/RAG/01_redisvl.ipynb | RAG from scratch with the Redis Vector Library |
/RAG/02_langchain.ipynb | RAG using Redis and LangChain |
/RAG/03_llamaindex.ipynb | RAG using Redis and LlamaIndex |
/RAG/04_advanced_redisvl.ipynb | Advanced RAG with redisvl |
/RAG/05_nvidia_ai_rag_redis.ipynb | RAG using Redis and Nvidia |
/RAG/06_ragas_evaluation.ipynb | Utilize RAGAS framework to evaluate RAG performance |
LLMs are stateless. To maintain context within a conversation chat sessions must be stored and resent to the LLM. Redis manages the storage and retrieval of chat sessions to maintain context and conversational relevance. | Recipe | Description |
---|---|---|
/llm-session-manager/00_session_manager.ipynb | LLM session manager with semantic similarity | |
/llm-session-manager/01_multiple_sessions.ipynb | Handle multiple simultaneous chats with one instance |
An estimated 31% of LLM queries are potentially redundant (source). Redis enables semantic caching to help cut down on LLM costs quickly.
Recipe | Description |
---|---|
/semantic-cache/semantic_caching_gemini.ipynb | Build a semantic cache with Redis and Google Gemini |
For further insights on enhancing RAG applications with dense content representations, query re-writing, and other techniques.
Recipe | Description |
---|---|
/RAG/04_advanced_redisvl.ipynb | Notebook for additional tips and techniques to improve RAG quality |
An exciting example of how Redis can power production-ready systems is highlighted in our collaboration with NVIDIA to construct a state-of-the-art recommendation system.
Within this repository, you'll find three examples, each escalating in complexity, showcasing the process of building such a system.