convez.ai
PluginBusca & PesquisaIntermediário
srtpan

Next Read

srtpan/Next-Read

Concierge pessoal de IA para descobrir seu próximo livro

Ver no GitHub
InicialPluginScore · de 0 a 100

Aplicação de recomendação de livros alimentada por Claude que analisa suas preferências de leitura, gêneros favoritos e livros já lidos para sugerir obras personalizadas. Usa processamento de linguagem natural avançado para encontrar seu próximo livro perfeito.

Instalação

$npx convez-ai srtpan/Next-Read

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
1
Saúde
28%
Último commit
há 2 anos
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Descobrir novos livros baseado em leitura anterior
  • Explorar gêneros literários específicos
  • Obter recomendações personalizadas com análise de preferências

Veredito

Plugin prático que aproveita bem o Claude para recomendações literárias personalizadas. Interface clara com Streamlit e permite fine-tuning de prompts, mas é nicholado para quem quer descobrir livros.

README

A tradução para o português deste README ainda está na fila.

Next-Read

Your personal book concierge for discovering your next page turner.

Description

I love reading and books I can talk about books for hours. When I closer to finishing a book, I always wonder 'What Should I Read Next'?

I made use of Anthropic's model to create 'Next Read': An intelligent book recommendation application designed to help you, my dear reader, find your perfect next book. Next Read analyzes your reading preferences, favorite genres, and past reads to suggest books that you're likely to love.

Application Link

You can access the application at: https://nextread.streamlit.app/

A big thanks to Streamlit Community for providing home to Next Read

Key Features:

  • Personalized Recommendations: Get tailored book suggestions based on your reading history and preferences.
  • Genre Exploration: Discover new books across various genres and styles.
  • AI-Powered Insights: Benefit from advanced natural language processing to match you with books that align with your interests.
  • User-Friendly Interface: Easy-to-use platform for seamless book discovery.
  • Detailed Book Information: Access short and sweet details about recommended books, including summaries, author information, and reader reviews.

Whether you're a voracious reader looking for your next page-turner or someone trying to rekindle their love for reading, Next Read is your go-to companion for literary exploration.

How It Works

Next Read uses the Anthropic API to analyze your inputs and generate personalized book recommendations. You provide a brief description of the book you wanna read next, like "A thriller set in a church" or "A murder mystery set in a bookstore", optionally provide a book you have read in the genre which will enhance the recommendation provided.

Getting Started

Installation Guide

  1. Clone the GitHub repository
  2. Set up API Key on Antropic AI's portal (https://console.anthropic.com/settings/keys)
  3. This application is deployed on Streamlit and uses secrets in Streamlit Cloud to secure the API Key. While running locally, replace st.secrets['API_KEY'] with os.environ['API_KEY'].
  4. Supplement your Anthropic API Key using terminal and depending on Windows/Linux/macOS, follow the instructions provided here (https://help.openai.com/en/articles/5112595-best-practices-for-api-key-safety) to provide api key as an environment variable
  5. Run your app by running: streamlit run app.py
  6. Enjoy the recommendations

Prompt Engineering Guide

Inside the guide, you can control the responses using "System" and "User" instrcutions. Under "System", you provide details about the role of the AI. According to Anthropic, "Use the system parameter to set Claude’s role. Put everything else, like task-specific instructions, in the user turn instead."

In the "User" you can further tune the prompt being provided by the user to ensure accurate, tailored and focussed responses from Calude. You can test a couple of combinations of prompts to get the results to your liking.

Contributing

You are most welcome contributions to Next Read! If you have suggestions for improvements or encounter any issues, please feel free to open an issue or submit a pull request.

Ver o original no GitHub

Bom para

Relacionados