Bridging The Chasm<\/h2>\n\n\n\n
Obstacles currently exist which prevent the application of open-source AI services (e.g., ChatGPT, Microsoft Copilot, Google Gemini) to data originating from network infrastructure. To start, there\u2019s the logistical issue of transporting the on-premises network operations data to these predominantly cloud-based services. The raw data is not only spread across thousands of devices, but often originates from different domains, vendors, and protocols. Further, the data exists in multiple formats, such as metrics, logs, events, and topology, and the accompanying metadata may be inconsistent and malformed. <\/p>\n\n\n\n
Additionally, open-source AI services are trained in English\u2014not the nuanced semantics of network operations data. And lastly, these AI services mine your data and pass it along to other organizations, presenting a significant security and privacy risk. <\/p>\n\n\n\n
Selector solves these issues, and effectively bridges the chasm, through our innovative approach to data collection, processing, and analytics, in conjunction with application of precisely trained LLMs (large language models).<\/p>\n\n\n\n
Mapping English Phrases to Queries<\/h2>\n\n\n\n
Selector\u2019s processing of English phrases and subsequent application of GenAI relies on two core features. The first one involves addition of a uniform query interface to the data storage layer. For this interface, Selector chose SQL (structured query language). The second feature is LLM-translation of the English phrase to a SQL query so that it can access the query interface. <\/p>\n\n\n\n
The diagram below (Figure 1) depicts how Selector leverages our LLM to translate an English phrase into a query, as seen in the translation layer. The returned query then runs on the query layer, which exists above the data storage layer.<\/p>\n\n\n\n The Selector LLM first determines which table or tables to query. Then, it focuses on keywords (e.g., Ashburn, GigE100*, last 2 days), applying these as filters to the table.<\/p>\n\n\n\n The LLM manages these tasks through a process known as imputing, or inferring (Figure 3). A typical function takes input and computes output using a set of parameters. An LLM takes output and using a model, imputes a function and its parameters\u2014a manner of reverse mapping.\u00a0<\/p>\n\n\n\n At its core, the Selector LLM model relies on a base, open-source model from the public domain. From there, it is trained with English data, enabling it to understand English language phrases. Next, Selector fine-tunes the LLM model with a dataset that teaches it to convert from English to Selector’s SQL query interface. These two steps do not involve the customer and occur in Selector\u2019s cloud. We publish and deploy updates to this model periodically. <\/p>\n\n\n\n Then, for each customer deployment, Selector fine-tunes the LLM model with client-specific data and entities\u2014a process which occurs on-premises at the customer. In this way, models are customized to each client’s unique solution. For example, Customer A’s model is different from Customer B’s and Customer C’s (Figure 4). The models are atomic and can be on-premises or in the cloud, depending on the client’s preference.<\/p>\n\n\n\n Selector Copilot, our GenAI-driven conversational interface, enables network operators to ask questions in plain English. For example, an operator might prompt Selector Copilot to \u201cShow me errors in Ashburn\u201d or pose the question, \u201cAre there any port errors in Ashburn on all GigE100* in the last 2 days?\u201d <\/p>\n\n\n\n For each query, Selector Copilot returns a visualization and summary of the results. Users can then interact with Selector to explore these results. They can also copy and paste each visualization from Selector Copilot onto a dedicated dashboard. <\/p>\n\n\n\n![\"\"](\"https:\/\/www.selector.ai\/wp-content\/uploads\/2024\/07\/how-selector-processes-english-phrases-1024x797.png\")
Inside the Selector LLM<\/h2>\n\n\n\n
![\"\"](\"https:\/\/www.selector.ai\/wp-content\/uploads\/2024\/07\/selectors-llm-based-translation-1024x378.png\"){kind=spacer}
![\"\"](\"https:\/\/www.selector.ai\/wp-content\/uploads\/2024\/07\/how-llms-impute-1024x585.png\")
![\"\"](\"https:\/\/www.selector.ai\/wp-content\/uploads\/2024\/07\/customized-lm-models-for-each-selector-customer-1024x929.png\")
Selector Copilot <\/h2>\n\n\n\n
![\"\"](\"https:\/\/www.selector.ai\/wp-content\/uploads\/2024\/07\/selector-copilot-demo-1024x573.png\")
![\"\"](\"https:\/\/www.selector.ai\/wp-content\/uploads\/2024\/07\/a-consolidated-alert-from-selector-927x1024.png\")
![\"\"](\"https:\/\/www.selector.ai\/wp-content\/uploads\/2024\/07\/an-event-correlation-graph-within-selector-1024x797.png\")