The purpose of this paper is to explore the implementation of Retrieval-Augmented Gen- 14 eration (RAG) technology with open-source Large Language Models (LLMs). For this purpose, a 15 web-based application named PaSSER that integrates RAG with three models - Mistral:7b, 16 Llama2:7b: Orca2:7b, is developed. In its development various technologies are used, including 17 Blockchain for managing and storing assessment results of built-in testing modules. PaSSER em- 18 ploys a set of evaluation metrics for LLMs’ performance - METEOR, ROUGE, BLEU, Perplexity, 19 Cosine similarity, Pearson correlation, and F1 score. The specialized knowledge base is in the smart 20 agriculture domain. As an illustration, the paper presents results and analysis of two tests. First one 21 is assessing the performance of LLMs across different hardware configurations, the other is deter- 22 mining the model that delivers most accurate and contextually relevant responses within the RAG. 23 The paper also discusses the integration of blockchain technology with LLMs to manage and store 24 assessment results within a blockchain environment. The tests revealed that Mistral:7b demon- 25 strates the best results across most of the evaluated metrics. The discussion section comments on 26 technical and hardware considerations that affect the performance of LLMs. Future development 27 will focus in leveraging new larger pre-trained open-source LLMs, exploring different finetuning 28 approaches, and further integration with Blockchain and IPFS.

Conventional tutoring approaches are confronted with limitations such as restricted availability, inconsistent pedagogical quality, and scalability con-straints. Furthermore, the exclusive use of Large Language Models (LLMs) like ChatGPT in education has its shortcomings, including the potential for incorrect responses and the lack of customized guidance aligned with specific course con-tent. This research proposes an innovative intelligent chatbot tutoring system, in-tegrating the Retrieval Augmented Generation (RAG) approach with a custom LLM. The developed system aims to overcome the limitations of traditional tu-toring and general-purpose LLMs by providing accurate, contextually relevant, and personalized assistance, thereby enhancing student understanding and en-gagement. The system, powered by an intelligent agent, retrieves relevant information from curated academic sources, incorporates interactive features for user feedback, and utilizes machine learning algorithms for ongoing performance enhancement, ensuring a robust and effective tutoring experience. The anticipated outcome is an enriched educational experience for university students, advance-ment in personalized learning, and improved student engagement, retention, and academic performance. Through continuous research and refinement, it is expected that the intelligent chatbot tutor will assume an important role in enhancing and supporting the educational journey of students.

On average, one in ten patients die because of a diagnostic error and medical errors are the third largest cause of death in the US. While LLMs have been proposed to help doctors with diagnoses, no research results have been published on comparing the diagnostic ability of many popular LLMs on an openly accessible real-patient cohort. In thus study, we compare LLMs from Google, OpenAI, Meta, Mistral, Cohere and Anthropic using our previously published evaluation methodology and explore improving their accuracy with RAG.

A novel approach to enhance Additive Friction Stir Deposition (AFSD) is presented through the integration of Multimodal Retrieval Augmented Generation (RAG). AFSD which is a solid-state metal additive manufacturing process characterized by its complexity, necessitating advanced analytical tools. A multimodal RAG system is implemented, integrating textual, and visual data. The methodology involves text extraction using LangChain's PyPDFLoader, followed by chunking and embedding generation via Google's Generative AI model. ChromaDB is utilized for vector storage and efficient information retrieval. The system, powered by Google's Gemini large language model, demonstrates proficiency in generating detailed explanations of friction-based deposition processes, identifying manufacturing techniques from visual data, and evaluating material microstructures. Information from multiple sources is synthesized to produce context-aware responses. Process control, quality assurance, and decision-making in AFSD are significantly enhanced by this approach. The system's capabilities are illustrated through the analysis of various friction-based deposition techniques and microstructure evaluation.

As the performance of large language models is proven in general domains, we can consider applying them to specific tasks to improve the system’s specialization and responsiveness. In this paper, we will develop a lightweight software system based on RAG (Retrieval-Augmented Generation) to test whether this approach can provide effective advice and protection for patients after discharge. All patient data in this study comes from the neurology department. We will select three diseases — Acute Cerebral Infarction, Atherosclerosis, and Hypertension to test our system, and the generated results will be evaluated by professional doctors. Additionally, we will introduce a memory mechanism to enhance the system’s performance and responsiveness. Finally, we will include suggestions for system improvements and extensions. The experimental results indicate that both the foundational capabilities of large language models (such as Llama 3 and GPT-4) and the system architecture (e.g., the integration of RAG and memory mechanisms) significantly influence overall performance. By comparing different models and architectures, it is observed that the GPT-4 system combined with RAG and memory mechanisms outperforms the baseline in terms of total score and improvements, demonstrating the effectiveness of system architecture optimization in enhancing the models’ ability to handle complex tasks. Since the data still contains sensitive information of patients and hospitals after being desensitized, we cannot show all the test data. However, after obtaining the hospital’s permission, through data desensitization, we showed some of the test data. You can click here to get the prototype we developed and some test data.

The sheer number of gene variants and the extent of the observed clinical and molecular heterogeneity recorded in neuropsychiatric disorders (NPDs), could be due to the magnified downstream effects initiated by a smaller group of genomic higher order alterations in response to endogenous or environmental stress. Chromosomal common fragile sites (CFS) are functionally linked with microRNA’s, gene copy number variants (CNVs), sub-microscopic deletions and duplications of DNA, rare single-nucleotide variants (SNVs/SNPs) and small insertions/deletions (indels), as well as chromosomal translocations, gene duplications, altered methylation, microRNA and L1 transposon activity and 3-D chromosomal topology characteristics. These genomic structural features have been linked with various NPDs in mostly isolated reports, and have usually only been viewed as areas harboring potential candidate genes of interest. The suggestion to use a higher level entry point, (the ‘fragilome’ and associated features), activated by a central mechanism (‘stress’) for studying NPD genetics, has the potential to unify the existing vast number of different observations in this field. This approach may explain the continuum of gene findings distributed between affected and unaffected individuals, the clustering of NPD phenotypes and overlapping comorbidities, the extensive clinical and molecular heterogeneity and the association with certain other medical disorders.