Pondhouse Data Blog
Parsing pdf, word and excel documents with GPT-4o
Learn how to use GPT-4o to parse data from even the most complex of documents - multi-column PDFs, excel documents, tables, and more.
How to classify, describe and analyze images using GPT-4o vision
GPT-4o has phenomenal vision capabilities. Learn how to use the OpenAI API to send images to GPT-4o and use it's vision capabilities to describe the images, label them or provide analytical outputs from them.
What is Open WebUI? The best self hosted, open source ChatGPT alternative?
Open Source, amazing community, with a user-friendly interface, easy setup via Docker or Kubernetes, and advanced features like pipelines and Retrieval Augmented Generation (RAG), Open Web UI is a great ChatGPT alternative.
What is the VertexAI model garden - a practical example: Deploying Llama 3.1 and Claude 3.5 Sonnet
Explore how Vertex AI Model Garden simplifies AI model deployment. This guide demonstrates deployment of Llama 3.1 and Claude 3.5 Sonnet, showcasing the platform's approach to hosting advanced AI models.
Fine-tune OpenAI's GPT-4o mini LLM AI model for free
Learn how to create your custom GPT-4o mini model using OpenAI's finetuning API - for free!
Neo4j LLM Knowledge Graph Builder: How to Create Knowledge Graphs for RAG
Learn to create knowledge graphs for RAG with Neo4j LLM Knowledge Graph Builder in this easy step-by-step guide. Increase the quality of your RAG model with this modern approach to data modelling.
How to Chat with Your BigQuery? Introducing semantic search to databases.
Simplify complex BigQuery data analysis with a custom conversational interface. Learn how to use OpenAI's GPT-4o model to generate SQL queries and execute them against your BigQuery database.
How to finetune LLMs
Learn how to finetune your own LLMs with modern tools like QLoRA and flash attention, even on consumer hardware - from creating a dataset, executing the fine-tuning process, and using this new model.
LLM Document Extraction: How to use AI to get structured data from legacy documents
The more we work with AI, the more we need to extract data from documents. In a scalable manner. While conventional and machine learning based methods provide good results for most cases, especially when the data is rather technical and provides complicated layouts like multicolumn pdfs or tables, these methods often fail. Let's test whether LLMs can help us here.
Using AI directly from your database - with PostgreSQL and pgai
AI is transforming the way we create applications and interact with data. Almost every application needs some form of AI nowadays. Every data interaction leverages some sort of AI feature. In this article, we demonstrate, how one can use AI directly from a PostgreSQL database, with only needing SQL commands.