OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

LLM Recommender

LLM Recommender is a Python and Streamlit hotel-recommendation application that combines Redis review search with OpenAI language-model steps. It creates a hypothetical review from a user's preferences, retrieves semantically similar hotel reviews, and generates recommendations with citations to the returned reviews.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

LLM Recommender — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it to explore hotel recommendations grounded in retrieved reviews when the documented location and quality criteria fit the query.

Who it is for

  • Travellers comparing US hotels using city or state and positive or negative qualities.
  • Developers exploring a self-hosted, review-grounded recommendation application built with Redis, OpenAI and Streamlit.

Documented uses

  • Search hotel reviews by location and desired or unwanted qualities.
  • Generate hotel recommendations from reviews retrieved for a preference-based query.
  • Inspect cited reviews alongside generated recommendations.
Before you choose

Requirements & limits

The repository documents Docker Compose and local Streamlit setup paths. Both require environment values, especially an OpenAI API key.

  • The search flow uses a generated hypothetical review as a semantic query before retrieving matching reviews.
  • Redis supports vector search alongside tag and text search in the application.
  • The README says the dataset is relatively sparse and hotels with the same name in different cities are not handled well.
  • Price and geographic filtering are listed as future work.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run the app with Docker Compose

Set up and open the hotel recommender using the repository’s Docker Compose instructions.

Before you start

  • A copy of the public repository
  • Values for the environment file, especially an OpenAI API key
  • Docker Compose

Steps

  1. Copy .env.template to .env and fill in the required values.

  2. Run the command below from the project directory.

    Documented command
    docker compose up

  3. Open http://localhost:8501/.

Expected outcome

The README’s documented local app address is available at localhost:8501 after starting the Compose services.

Guide limitations

  • The README identifies sparse review data and poor handling of hotels with the same name in different cities.
  • Price and geographic filtering are listed as future work.
Documentation 1 ↗
Source-based practical guide

Set up a local Streamlit run

Install the documented dependencies and launch the application locally.

Before you start

  • Python and pip
  • An OpenAI API key and other required environment values

Steps

  1. Copy .env.template to .env and fill in the values, especially OPENAI_API_KEY.

  2. Clone the repository.

  3. Install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  4. Start the app with streamlit run run.py.

Expected outcome

The README provides the Streamlit command for launching the local application.

Guide limitations

  • The README identifies sparse review data and poor handling of hotels with the same name in different cities.
  • Price and geographic filtering are listed as future work.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
redis-developer/LLM-Recommender · Official homepage title · retained in its source language
How we review sourcesSuggest a correction