RAG-based System Architecture

An RAG-based System Architecture is an LLM-based system arch for a RAG-based system.

• Context:
  • It can be referenced by an LLM-based End-User Application Architecture.
  • It can (typically) be composed of LLM-based System Components.
  • ...
• Example(s):
  • one expressed in (Bornstein & Radovanovic, 2023).
  • ...
• See: RAG-based System Architecture.

---

---

References

2023

• https://medium.com/@nageshmashette32/building-a-document-based-question-answering-system-with-langchain-using-llm-model-fb22e47a965c
  • QUOTE:

    Q&A Architecture using LangChain and VectorStore.

2023

• https://medium.com/@nageshmashette32/building-a-document-based-question-answering-system-with-langchain-using-llm-model-fb22e47a965c
  • QUOTE:

    Technical Architecture : Document based LLM Chatbot — Image by Author

2023

• https://medium.com/@abdullahw72/langchain-chatbot-for-multiple-pdfs-harnessing-gpt-and-free-huggingface-llm-alternatives-9a106c239975
  • QUOTE: The Langchain Chatbot for Multiple PDFs follows a modular architecture that incorporates various components to enable efficient information retrieval from PDF documents. Let’s delve into the key architectural elements:

    

  • 
  • SUMMARY:
    • User Interface: Allows users to input questions and view responses.
    • Natural Language Understanding (NLU): Understands and interprets user queries. Uses NLP techniques like tokenization and named entity recognition.
    • Vector Store: Stores vector representations of text chunks extracted from PDFs. Generated using embeddings.
    • Embeddings: Encode semantic information from text chunks into vectors. Can use OpenAI or Hugging Face models.
    • Large Language Models (LLMs): Provide advanced language capabilities. Fine-tuned models like those from OpenAI or Hugging Face's Instruct series.
    • Conversational Retrieval: Matches user query vectors to document vector representations to find relevant information.
    • Chat History: Stores conversation context to enable coherent, relevant responses.

---