Direct edit of llm_models.json structure. Use with care.
Unsaved Changes
You have unsaved admin changes. Save or discard them before closing?
LLM Settings
Endpoint
Start New Chat?
You have unsaved chat history. Are you sure you want to start a new chat?
About
What is Rocket Enterprise CoreAI?
A Retrieval-Augmented Generation (RAG) chatbot is an AI system that enhances the capabilities of large language models (LLMs) by integrating them with external data sources. This integration allows the chatbot to provide more accurate, context-aware, and up-to-date responses by retrieving relevant information from specified documents or databases before generating an answer.
How a RAG Chat Bot Works
Data Ingestion and Embedding: Your local documents (e.g., PDFs, Word files, or text files) are processed and converted into vector embeddings using models like OpenAI text-embedding-ada-002. These embeddings capture the semantic meaning of the text.
Storage in a Vector Database: The generated embeddings are stored in a vector database such as FAISS, Weaviate, or pgvector. This database allows for efficient similarity searches based on the vector representations of the data.
Query Processing: When a user poses a question, the chatbot converts the query into a vector using the same embedding model. It then searches the vector database to find the most semantically similar documents or text chunks.
Response Generation: The retrieved information is combined with the original user query and passed to the LLM (e.g., OpenAI's GPT-4) to generate a response that is grounded in the retrieved context.
Fallback to LLM Knowledge: If no relevant information is found in the local data, the chatbot can default to the LLM's pre-existing knowledge to answer the query.
Benefits of a RAG Chat Bot
Enhanced Accuracy: By grounding responses in specific documents, the chatbot reduces the likelihood of generating incorrect or "hallucinated" information.
Up-to-Date Information: RAG allows the chatbot to access the most recent data without the need to retrain the entire model.
Domain Specificity: The chatbot can be tailored to specific domains or industries by providing it with relevant documents.
Data Privacy: Sensitive information remains within your controlled environment, as the chatbot accesses local data sources.
This Rocket Software RAG Bot searches your local Rocket Software documentation for answers, and only falls back to the LLM if no relevant information is found.