PinnedMatthew HarrisinTowards Data ScienceSome Thoughts on Operationalizing LLM ApplicationsA few personal lessons learned from developing LLM applicationsJan 273Jan 273
Matthew HarrisinTowards Data SciencePredicting metadata for Humanitarian datasets with LLMs part 2 — An alternative to fine-tuningUsing LLM prompting for tagging metadata on humanitarian datasetsAug 3Aug 3
Matthew HarrisinTowards Data ScienceA Humanitarian Crises Situation Report AI Assistant: Exploring LLMOps with Prompt FlowExploring some techniques for safe deployment of LLM solutionsApr 1Apr 1
Matthew HarrisinTowards Data ScienceReframing LLM ‘Chat with Data’: Introducing LLM-Assisted Data RecipesA conversational data analysis pattern for increased transparency and safety with reduced costsJan 267Jan 267
Matthew HarrisinTowards Data SciencePreparing for Climate Change with an AI AssistantSimplifying complicated data through conversationNov 26, 20233Nov 26, 20233
Matthew HarrisinTowards Data ScienceDeveloping a Climate GPT Using NASA’s Power APICreating a climate data analysis chatbot in a few hoursNov 20, 2023Nov 20, 2023
Matthew HarrisinTowards Data ScienceResearching a Humanitarian Disaster Situation Report Chatbot — Using GPT-4-Turbo and full-context…Exploring a Brute Force Technique for Information RetrievalNov 15, 20231Nov 15, 20231
Matthew HarrisinTowards Data ScienceResearching a Multilingual FEMA Disaster Bot Using LangChain and GPT-4Some pros and cons of Retrieval-Augmented Generation (RAG) for high-risk chat applicationsAug 17, 20231Aug 17, 20231
Matthew HarrisinTowards Data ScienceAnalyzing Humanitarian Data Unstructured Excel tables with ChatGPT Code InterpreterSome Initial Exploration with Code InterpreterJul 10, 20233Jul 10, 20233
Matthew HarrisinTowards Data ScienceUsing GPT-3.5-Turbo and GPT-4 to Apply Text-defined Data Quality Checks on Humanitarian DatasetsApplying Large Language Model Unsupervised Classification Tasks as Part of Data ProcessingMar 29, 2023Mar 29, 2023