During my time as Head of Professional Services for a private Genomics based company I spearheaded an initiative to utilise an open source offline LLM for analysing our Jira, Confluence and Salesforce docs for quick retrieval of process and technical information.

The purpose was twofold,

a) To create a common ‘search’ tool in order to locate a source of truth as to what was configured and where, and

b) To be able to generate process documents very quickly in whole or in part through the use of generative AI.

As these were sensitive company documents, use of a service like ChatGPT was restricted, which is why we opted to trial PrivateGPT with Llama-2-7b amongst other models.

We found RAG to be less than perfect, but it did effectively allow us to search out the right documents. Text generation was better in that we managed to produce good content as an initial template for a process guides, as well as feeding a full process document to generate a RASCI chart. We ran the pilot service on AWS EC2 infrastruture.

The post RAG with Offline LLM appeared first on fitzmoskal.

I was brought in to architect and deliver an data pipeline for updating their CMDBs from multiple data sources. The CMDB itself was hosted on Salesforce and the data sources were Discovery, Active Directory, Spreadsheets and SCCM.

A particular challenge was being restricted to operating remotely using TeamViewer – which does not perform well over data instensive remote connections – and requires an active user on the end to keep the connection going. This did cause development work to go much slower than planned, but thankfully did not cause overall delay to project.

The integrations were developed, tested and deployed successfully to the satisfaction of the client.

The post Online Betting Platforms – CMDB Data appeared first on fitzmoskal.

Over the years I built a relationship with this global fashion brand in facilitating their ongoing digital transformation. The first engagement was in architecting and implementing a number of critical integrations with their CMDB from various data sources, allowing them to gain full central visiblity of their enterprise infrastructure. Later, I was again called upon to re-architect and extend the earlier integrations in preparation for a move of CMDB cloud platforms.

As a Principle Solutions Architect I also oversaw the technical delivery of their managed services – consulting on roadmaps and strategy with the client. I built a trusting working relationship and also proposed and worked on implementing a new feature of exception reporting, which helped them to identify, understand and narrow down the discrepencies between source data and CMDB data. The result was clear visibility and improved data quality of their CMDB.

The post Major Fashion Retailer – Digital Transformation appeared first on fitzmoskal.

The post ETL Tools appeared first on fitzmoskal.

However I found a couple of annoyances when running it from CLI, one was in having to keep a terminal window open, the other was having to run it from it’s install directory – particularly when it comes to relative path names for kettle jobs.

So I created an alias that runs PDI in an interactive shell allowing you to run it from one a word command, and it occurred to me that this might be useful to share. Here you go:

alias spoon='sh -c '\''cd /opt/pentaho/data-integration; ./spoon.sh&'\'''

The post Spooning with Pentaho Data Integrator appeared first on fitzmoskal.