No packages match

edgemodelr - Local Large Language Model Inference Engine

Enables R users to run large language models locally using 'GGUF' model files and the 'llama.cpp' inference engine. Provides a complete R interface for loading models, generating text completions, extracting vector representations, and streaming responses in real-time. Includes grammar-constrained generation for structured output, text classification, and retrieval-augmented generation (RAG) pipelines. Supports local inference without requiring cloud APIs or internet connectivity, ensuring complete data privacy and control. Based on the 'llama.cpp' project by Georgi Gerganov (2023) <https://github.com/ggml-org/llama.cpp>.

Last updated

cpp

5.80 score 18 stars 35 scripts 164 downloads

r4subcore - Core Contracts, Parsers, and Scoring Primitives

Foundational package in the R4SUB (R for Regulatory Submission) ecosystem. Defines the core evidence table schema, parsers, indicator abstractions, and scoring primitives needed to quantify clinical submission readiness. Provides a standardized contract for ingesting heterogeneous sources (validation outputs, metadata, traceability) into a single evidence framework.

Last updated

5.48 score 5 dependents 170 downloads

r4subtrace - Traceability Engine for Clinical Submission Readiness

Quantifies and explains end-to-end traceability between clinical submission artifacts (ADaM (Analysis Data Model) outputs, derivations, SDTM (Study Data Tabulation Model) sources, specs, code). Builds trace models from metadata and mapping sheets, computes trace levels, and emits standardized R4SUB (R for Regulatory Submission) evidence table rows via 'r4subcore'.

Last updated

4.65 score 1 dependents 160 downloads

r4subscore - Submission Confidence Index Engine

Converts standardized R4SUB (R for Regulatory Submission) evidence into indicator scores, pillar scores, and a Submission Confidence Index (SCI). Provides sensitivity analysis, explainability tables, and decision band classification to answer the question: are we ready for regulatory submission.

Last updated

4.65 score 1 dependents 147 downloads

r4subrisk - Risk Quantification Engine for Clinical Submission Readiness

Quantifies submission risk using a Failure Modes and Effects Analysis (FMEA)-inspired framework (probability, impact, detectability). Builds risk registers from evidence, computes Risk Priority Numbers (RPN), classifies risk levels, and emits standardized R4SUB (R for Regulatory Submission) evidence table rows via 'r4subcore'. Supports risk mitigation tracking and trend analysis across submission milestones.

Last updated

4.65 score 1 dependents 156 downloads

r4subprofile - Regulatory Submission Profiles for Clinical Submission Readiness

Defines submission profiles per regulatory authority with authority-specific pillar weights, decision thresholds, indicator requirements, and risk configuration. Supports the U.S. Food and Drug Administration (FDA), European Medicines Agency (EMA), Pharmaceuticals and Medical Devices Agency (PMDA), Health Canada, Therapeutic Goods Administration (TGA), and Medicines and Healthcare products Regulatory Agency (MHRA). Integrates with 'r4subscore' and 'r4subrisk' configuration systems.

Last updated

4.65 score 1 dependents 147 downloads

r4subdata - Example Datasets for Clinical Submission Readiness

Provides realistic synthetic example datasets for the R4SUB (R for Regulatory Submission) ecosystem. Includes a pharma study evidence table, ADaM (Analysis Data Model) and SDTM (Study Data Tabulation Model) metadata following CDISC (Clinical Data Interchange Standards Consortium) conventions (<https://www.cdisc.org>), traceability mappings, a risk register based on ICH (International Council for Harmonisation) Q9 quality risk management principles (<https://www.ich.org/page/quality-guidelines>), and regulatory indicator definitions. Designed for demos, vignettes, and package testing.

Last updated

4.65 score 1 dependents 148 downloads

shinypayload - Accept POST Data and URL Parameters in 'shiny' (Same-Port Integration)

Handle POST requests on a custom path (e.g., /ingress) inside the same 'shiny' HTTP server using user interface functions and HTTP responses. Expose latest payload as a reactive and provide helpers for query parameters.

Last updated

4.60 score 11 stars 12 scripts 135 downloads

r4sub - Easily Install and Load the R4SUB Ecosystem

The 'r4sub' package is a meta-package that installs and loads core packages of the R4SUB (R for Regulatory Submission) clinical submission readiness ecosystem. Loading 'r4sub' attaches 'r4subcore', 'r4subtrace', 'r4subscore', 'r4subrisk', 'r4subdata', and 'r4subprofile'.

Last updated

4.48 score 2 stars 462 downloads