Português | English

---

LLM & Embedding Parallel Pipeline

Projeto Python robusto e profissional para inferência paralela eficiente com LLMs (Large Language Models) e embeddings OpenAI, com retry automático e estatísticas de execução

---

Recursos

• Chamadas paralelas para LLM (chat/completions) e embeddings
• Retry automático com backoff
• Estatísticas automáticas de tempo, throughput, tokens e erros

---

Como usar

1. Crie seu arquivo de ambiente .env:

   OPENAI_API_KEY=sua-chave-openai-aqui
   

2. Instale as dependências:

   pip install -r requirements.txt

3. Execute o projeto:

   python main.py

O script main.py traz exemplos prontos de uso das funções de LLM e Embeddings em paralelo.

LLM & Embedding Parallel Pipeline

A robust, professional Python project for efficient parallel inference with LLMs (Large Language Models) and OpenAI embeddings, featuring automatic retry and execution statistics

---

Features

• Parallel calls for LLM (chat/completions) and embeddings
• Automatic retry with backoff
• Automatic time, throughput, token, and error statistics

---

How to Use

1. Create your .env file:

   OPENAI_API_KEY=your-openai-key-here
   

2. Install dependencies:

   pip install -r requirements.txt

3. Run the project:

   python main.py

The script main.py includes ready-to-run examples for parallel LLM and embedding functions.