Manual Content Extractor for Employee Training
A manufacturing training solution that uses AI and Snowflake Cortex to enable workers to query operational manuals in natural language, providing instant assistance for complex tasks and machinery procedures.
Problem
In the manufacturing industry, workers often face complex tasks and machinery that require precise handling and understanding. Despite training, they may encounter unfamiliar situations, leading to time-consuming searches through printed manuals or delays waiting for supervisory assistance. Sometimes the workers might also feel too shy to question the trainer or authorities in case of doubts.
Proposed Solution
An advanced Automated Manuals Content Extractor application integrated with the company's digital worker manuals provides instant, reliable, and interactive assistance, enabling workers to query in natural language about any task or procedure.
How Do We Build It?
The required machine operation and training manuals are loaded to the Snowflake internal stage and Cortex's Vector Embedding function to vectorize the chunks of the manuals (previously loaded in the internal stage) and store them in a datatype column in a Snowflake table along with the details of the manual and extracted chunk. Cortex's VECTOR COSINE SIMILARITY function is used to find the most relevant chunks, and Cortex's COMPLETE function to generate responses based on the user-provided model to implement a RAG-based LLM chatbot.
How Do We Use It?
In the sidebar (left pane) users can choose:
- The type of LLM model from: mixtral-8x7b, snowflake-arctic, mistral-large, llama3-8b, llama3-70b, reka-flash, mistral-7b, llama2-70b-chat, or Gemma-7b
- Whether previous question and response history is maintained for subsequent questions
- Whether the assistant answers from operational and training manuals or from internet information
- Checkbox to show summary of previous conversations
- A download button for previous conversations
In the main pane, users have a chat box to ask questions with responses displayed below.
Future Enhancements
The application could be enhanced to support images in prompts and responses. Additionally, information related to employee experience and skills could be added to enhance response quality and improve user experience.
