{"repo":"redis-developer/LLM-Recommender","free":true,"listed":false,"github":"https://github.com/redis-developer/LLM-Recommender","clone":"git clone https://github.com/redis-developer/LLM-Recommender.git","description":"Use OpenAI, Redis, and streamlit to recommend hotels using Large Language Models","language":"Python","stars":28,"topics":["llm","llm-chain","rag","redis","retrieval-augmented-generation","retrieval-augmented-qa","vector","vector-database"],"license":null,"category":"ai-agents","readme_excerpt":"RedisVL GitHub     RedisVL Documentation     More Projects     LLM Hotel Recommender The LLM Hotel Recommender is a Streamlit app that uses Redis and the OpenAI API to generate hotel recommendations based on a user's preferences. Because Redis can perform semantic search in addition to other operations like tag and text search users are able to search for hotels in the US based on a variety of criteria, including: - State - City - Positive Qualities - Negative Qualities The application will cite it's sources (reviews) for each recommendation and provide all the reviews that were returned. Design The recommender uses the Hypothetical Document Embeddings (HyDE) approach which uses an LLM (OpenAI in this case) to generate a fake review based on user input. The system then uses Redis vector search to semantically search for hotels with reviews that are similar to the fake review. The returned reviews are then passed to another LLM to generate a recommendation for the user. Run the Application Docker Compose 1. Create your env file: fill out values, most importantly, your OPENAI API KEY 2. Run with docker compose: add -d option to daemonize the processes to the background if you wish. Issues with dependencies? Try force-building with no-cache: 3. Navigate to: Local 1. Create your env file: fill out values, most importantly, your OPENAI API KEY 2. Clone the repo: bash $ pip install -r requirements.txt bash $ streamlit run run.py Known Bu","default_branch":null,"files":null,"tree":[],"storefront":"/r/redis-developer","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/redis-developer/LLM-Recommender/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}