Home > AI Solutions > Gen AI > White Papers > Product Support Quick Notes Retrieval > Implementation details
PSQN articles undergo regular updates by the business support teams in collaboration with content teams, providing targeted solutions for specific model issues. To incorporate these updates into a PSQN search solution, DTS requires an efficient pipeline that ensures frequent synchronization. Once prepared for search, the pipeline generates indexed data within the Embedding Store, facilitating real-time retrieval.
Articles undergo tagging to associate them with specific products and corresponding assets. DTS extracts these tags/associations at various levels (product family and asset). While the NBA tool provides the product information with the search query, it originates from a distinct taxonomy compared to the one used during article creation. To address this, DTS has implemented a product taxonomy mapping that bridges the two taxonomies, facilitating the translation to the NBA tool’s taxonomy within a data pipeline.
Before implementing a comprehensive solution for taxonomy mapping, a short-term static mapping was developed, which leveraged a Large Language Model (LLM) and fuzzy search tools. This approach facilitated a semi-automated process to align the two taxonomies. The need for automation arose due to the substantial volume of article data and nuanced labels, which necessitated human review.
To enhance article search, DTS augments human-generated data to represent each article within the search index. This augmentation combines an article summary with additional keywords to emphasize key concepts of the article. An LLM is employed in cases where human-generated summary is not available. Similarly, DTS generates keywords for all articles and appends them to their respective summaries.
The example below compares such generations and observes the LLM's ability to reduce an article of approximately 300 words into concise, accurate summaries as good as a human. Unlike alternative methods such as document chunking, DTS's approach minimizes data processing requirements and results in a smaller search index, enabling faster inference. Future work could explore further improvements if precision or adaptability issues arise, as highlighted in the section, Finding 4: Precision loss and adaptability in summarizations.
Human Generated | LLM Generated |
“OptiPlex XX50: Resolving an issue with Data Wipe in the BIOS” Keywords: “hdd password not wiped data wipe not working correctly” | “Resolving issue with Data Wipe in OptiPlex XX50 BIOS” Keywords: “OptiPlex XX50, BIOS, Data Wipe, desktop, SATA hard drive” |