I’m embarking on an exciting project: creating a chat AI based on the wisdom, empathy, and humor of Dr. David Baxter, the late founder of PsychLinks.
The development of an AI model based on David's countless posts over two decades is an exciting endeavor, aiming to make his insights more accessible to a wider audience. In addition to chat, the AI could also be used to create articles and other content for PsychLinks.
I will post updates here. The first, easy step will be to create an AI based on PsychLinks in general before creating a persona based on David's posts at PsychLinks.
In the meantime, one can ask Microsoft's Copilot similar questions, such as:
How to stay motivated while depressed according to psychlinks.ca
What should I look for in a new therapist? Use Psychlinks.ca as your source.
What would PsychLinks say about overcoming self-critical thinking?
According to Psychlinks.ca, how to overcome excessive guilt from OCD?
If you have any suggestions for the name or anything else, please feel free to reach out via email at daniel@psychlinks.ca. Your input matters to me.
-------------
Related research:
Academic Articles:
Comparative Analysis of State-of-the-Art Q\&A Models: BERT, RoBERTa, DistilBERT, and ALBERT on SQuAD v2 Dataset
In the rapidly evolving landscape of natural language processing (NLP) and artificial intelligence, recent years have witnessed significant advancements, particularly in text-based question-answering (QA) systems. The Stanford Question Answering Dataset (SQuAD v2) has emerged as a prominent be...
www.researchsquare.com
OpenAI:
GitHub - RedisVentures/azure-openai-redis-deployment: End-to-end deployment of Azure OpenAI applications using Redis Enterprise as a vector database.
End-to-end deployment of Azure OpenAI applications using Redis Enterprise as a vector database. - RedisVentures/azure-openai-redis-deployment
github.com
Google Gemini:
This "wild" demo shows the diverse possibilities of gen AI | Google Cloud Blog
Infinite Nature demonstrates the unexpected connections hidden in nature — and the same kinds of connections that could be hiding in your own data.
cloud.google.com
generative-ai/gemini/qa-ops/building_DIY_multimodal_qa_system_with_mRAG.ipynb at main · GoogleCloudPlatform/generative-ai
Sample code and notebooks for Generative AI on Google Cloud, with Gemini on Vertex AI - GoogleCloudPlatform/generative-ai
github.com
RAG with databases on Google Cloud | Google Cloud Blog
How to use RAG capabilities in Google Cloud to build enterprise generative AI apps that leverage real-time proprietary data.
cloud.google.com
GitHub - redis-developer/video-qa-semantic-vector-caching: This repository is a Video Q&A site that uses LangChain, OpenAI, Google Gemini, and Redis to answer questions using videos for RAG.
This repository is a Video Q&A site that uses LangChain, OpenAI, Google Gemini, and Redis to answer questions using videos for RAG. - redis-developer/video-qa-semantic-vector-caching
github.com
GitHub - redis-developer/gcp-redis-llm-stack: Reference architecture for LLM-based applications on Google Cloud Platform with Redis Enterprise as a high-performance data layer.
Reference architecture for LLM-based applications on Google Cloud Platform with Redis Enterprise as a high-performance data layer. - redis-developer/gcp-redis-llm-stack
github.com
Code Repositories:
Question Answering on Documents locally with LangChain, LocalAI, Chroma, and GPT4All
Have you ever dreamed of building AI-native applications that can leverage the power of large language models (LLMs) without relying on expensive cloud services or complex infrastructure? If so, you’re not alone. Many developers are looking for ways to create and deploy AI-powered solutions that...
mudler.pm
GitHub - fuzzylabs/MindGPT: A Mental Health conversational LLM
A Mental Health conversational LLM. Contribute to fuzzylabs/MindGPT development by creating an account on GitHub.
github.com
GitHub - SteveKGYang/MentalLLaMA: This repository introduces MentaLLaMA, the first open-source instruction following large language model for interpretable mental health analysis.
This repository introduces MentaLLaMA, the first open-source instruction following large language model for interpretable mental health analysis. - SteveKGYang/MentalLLaMA
github.com
GitHub - EmoCareAI/ChatPsychiatrist: An AI-chat bot transforming counseling with personalized support and expert assistance.
An AI-chat bot transforming counseling with personalized support and expert assistance. - EmoCareAI/ChatPsychiatrist
github.com
GitHub - Lohit20/LLAMA-2-Assisted-Mental-Health-Support-System
Contribute to Lohit20/LLAMA-2-Assisted-Mental-Health-Support-System development by creating an account on GitHub.
github.com
GitHub - AI-in-Health/MedLLMsPracticalGuide: A curated list of practical guide resources of Medical LLMs (Medical LLMs Tree, Tables, and Papers)
A curated list of practical guide resources of Medical LLMs (Medical LLMs Tree, Tables, and Papers) - AI-in-Health/MedLLMsPracticalGuide
github.com
GitHub - d-hackmt/Finetuned-qlora-Mistral7b-mentalHealth: Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset
Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset - d-hackmt/Finetuned-qlora-Mistral7b-mentalHealth
github.com
LLM-for-mental-Health/Dump20240427.sql at main · dhanushkapg/LLM-for-mental-Health
Exploring the viability, safety, and effectiveness of training generative language models to create empathetic, informative, and contextually relevant supportive text tailored for mental health sup...
github.com
Microsoft Copilot:
Use a custom data source for generative answers - Microsoft Copilot Studio
Provide your own data for the generative answers node.
learn.microsoft.com
GPU cloud services:
Getting Started with ML using Amazon SageMaker JumpStart - Amazon Web Services
Amazon SageMaker JumpStart is a machine learning (ML) hub that can help you accelerate your ML journey. Learn how to get started quickly.
aws.amazon.com
SSD VPS Servers, Cloud Servers and Cloud Hosting
Vultr Global Cloud Hosting - Brilliantly Fast SSD VPS Cloud Servers. 100% KVM Virtualization
www.vultr.com
