Skip to content
View rafaself's full-sized avatar
6 followers · 0 following

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Highlights

Organizations

@numllm

Block or report rafaself

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
rafaself/README.md

Hey, I'm Rafael, a Software Engineer working primarily with Python and TypeScript. I'm open to new projects, collaborations, and freelance opportunities.

Check out my website, where I share articles about software, AI, and other technology topics.

Pinned Loading

  1. llm-fullstack-app-nestjs llm-fullstack-app-nestjs Public

    A full-stack modular application LLM-powered chatbot built with NestJS and Vercel AI SDK for AI integration and tool calling.

    TypeScript

  2. lab-aws-bedrock-and-langchain lab-aws-bedrock-and-langchain Public

    Hands-on experiments with LangChain and Amazon Bedrock, exploring LLM integrations, RAG, document processing, text splitting, and summarization chains.

    Jupyter Notebook

  3. atf-ai-engineer-challenge atf-ai-engineer-challenge Public

    Provider-agnostic AI customer support agent built with Python, FastAPI, React, RAG, and tool calling.

    Python

  4. llm-chatbot-benchmark llm-chatbot-benchmark Public

    Benchmarking LLM-powered chatbots across response quality, accuracy, latency, and resource usage under consistent evaluation conditions.

    HTML

  5. evaluate-ai-applications-guided-lab evaluate-ai-applications-guided-lab Public

    Hands-on labs for evaluating LLMs and AI agents using Amazon Bedrock, Boto3, and Promptfoo.

    Python

  6. A Simple vLLM Chat with a minimal CL... A Simple vLLM Chat with a minimal CLI chatbot demonstrating LLM inference, conversation history, system prompts, and output validation.
    1 
    from vllm import LLM, SamplingParams
    2 
    
              
    
              
    
                3
                
    # Model configuration
    
              
    
              
    
                4
                
    MODEL_NAME = "Qwen/Qwen2.5-0.5B-Instruct"
    
              
    
              
    
                5
                
    
              
    
          
    
    
    
  
    

    7.