Igor Kasianenko 9fd54a395c deprecate OctoAI (#873) 2 달 전
..
RAG_chatbot 46796d5b34 Fix more package naming (#864) 4 달 전
messenger_chatbot e5b999d29a Resolved merge conflicts 4 달 전
whatsapp_chatbot e5b999d29a Resolved merge conflicts 4 달 전
README.md de78ad9cdb spell checked 3 달 전

README.md

This repository contains various end-to-end use cases for building customer service chatbots using Meta's Llama 3. Below is an outline of the sub folders and their contents.

Outline

  • RAG_chatbot contains resources for building a Meta Llama 3 chatbot with Retrieval Augmented Generation (RAG). It contains a notebook which shows a complete example of how to build a Meta Llama 3 chatbot hosted on your browser that can answer questions based on your own data. It covers:

    • The deployment process of Meta Llama 3 8B with the Text-generation-inference framework as an API server.
    • A chatbot example built with Gradio and wired to the server.
    • Adding RAG capability with Meta Llama 3 specific knowledge based on our Getting Started guide.
  • ai_agent_chatbot contains a Sales Bot with Llama3 - A Summarization and RAG Use Case notebook that demonstrates building a sales chatbot using Llama3 for targeted product recommendations. The workflow involves:

    • Generating product review summaries using Llama3
    • Storing summaries in a vector database (Weaviate)
    • Leveraging Retrieval Augmented Generation (RAG) for intelligent sales interactions
  • messenger_chatbot section provides a step-by-step guide to building a Llama-enabled Messenger chatbot. It includes integration details with the Messenger Platform and a demo video.

  • whatsapp_chatbot folder contains a tutorial for creating a Llama 3 enabled WhatsApp chatbot, similar to the Messenger chatbot guide. A demo video showcasing the use of iOS WhatsApp to send a question to a test phone number and receive a response generated by Llama 3 can be found here.

Additional Information

  • RAG Architecture: The RAG method enhances LLMs by retrieving and augmenting data, allowing for more relevant and context-aware responses.
  • Development Tools: The repository utilizes frameworks like LangChain and LlamaIndex for building LLM applications, and Gradio for creating chatbot UI.

For more detailed information, please refer to the individual sub directory documentation and examples.