Converting PDF to JSON is a simple task that uses Python. Converting can be helpful in various pre-processing situations involving data.
Python PDF to JSON Conversion for Efficient Data Pre-processing
Getting started with Text Generation Inference (TGI) using a container to serve your LLM model
This blog post outlines a bash automation for setting up and testing Text Generation Inference (TGI) using a container. It provides instructions for creating a Python test client, starting the TGI server, and troubleshooting common issues. The post emphasizes the benefits of using containers and references the Hugging Face and Nvidia technologies.
CheatSheet: How to ensure you use the right Python environment in VS Code interpreter settings?
This post covers to ensure you set the virtual environment for Python in VS Code using venv. It details creating and activating a Python venv, and ensuring it’s used in VS Code environments. The steps include opening the VS Code command palette, selecting an interpreter, and navigating to the pyvenv.cfg file.
Unleash your creativity and design a custom visualization for the Shelly 3EM device with Grafana
The blog post details an example implementation of a connection server using Shelly 3EM, IBM Cloud Cloudant, and Grafana. It aims to store historical data for visualizing electricity consumption. The project involves detailed architecture, environment setup, Python, FastAPI, Podman, and more usage. The setup covers Raspberry Pi, Podman Compose, and IBM Cloud Code Engine environments, with prerequisites and detailed configurations. The approach allows users to monitor and visualize power consumption efficiently and cost-effectively using Grafana.
How to create a FastAPI server to use OpenAI models
Last time, I wrote a blog post about "IBM Watsonx.ai and a simple question-answering pipeline using Python and FastAPI", and I had an exchange with my family about an OpenAI sample for a FastAPI application, so I created a small FastAPI server to access OpenAI with Python.
Write a simple question-answering pipeline with IBM watsonx.ai, IBM Watson Discovery by using Python and FastAPI
This blog post contains information about a simple example implementation for a simple question-answering pipeline using an inside-search (IBM Cloud Watson Discovery) and a prompt (IBM Watsonx with prompt-lab) to create an answer.
How to set up Caikit and use Hugging Face models examples
This small blog post is about how to set up a demo environment for using Caikit and Hugging Face models on your local machine.
Change the index-url in pip.conf
You may run into the situation that you can't install libraries for Python on your local computer.
Use Label Sleuth to build your train and test data input
This blog post is written in the context of creating a text classification model. The objective is to build and train a text classification model to identify topics in a text. These topics are Kubernetes and Watson NLP. As the train and test data, we will use an export from my blog on wordpress.com. This data we will label this with the open-source tool called Label Sleuth.
How to convert XML data to CSV in a Jupyter Notebook with Python?
This blog post contains an extract of a Jupyter Notebook related to how to convert XML data to comma separated value in a Jupyter Notebook.
Thomas Suedbroecker's Blog 