One language model turn | Where objects live | What the session retains | Permissions and concurrency | Find the right reference page

Enter prompts, objects and your own R | Commands | Approve, interrupt and continue

A tool the model calls as an R function | A permission policy | A hook on a session | Prompt sections, context blocks and commands | Other kinds | Extensions and plugins

List first, connect when needed | Register a server | Call tools as R functions | Authenticate an HTTP server | Serve your R session

Find and use skills | Write a skill | Prompt templates and project instructions | Agent definition files | Package a plugin | Trust and precedence

Logical decisions and probabilities | Structured inputs and batch shape | Uncertainty in filters, functions and loops | Choices and fractional scores | Provenance and caching | System 1 routes or judges System 2 | Native Jev, local Ollama and explicit emulation

A team of named roles | A fan-out over input elements | Independent calls with gptr_parallel() | Deferred sessions and SDK control | Experimental background work | Checkpoints, usage and durable history

Calls in ordinary R scripts and functions | Continuing one session with a pipe | Recording a designated R script | Inspecting and replaying | R Markdown, Quarto and Jupyter | Asking Peter to summarize a completed workflow

Inspect objects, files and output | Shell commands and scripts | Background programs | Python, SQL and other engines | Build a versioned artifact | Inspect, reopen and stop artifacts

Scope and precedence | Settings by purpose | R options | Environment and credentials

A first call | The pipe steers one session | Stopping instead of guessing | At the console | Connecting a real model | Where to go next

Choose and connect a model | API providers | Azure OpenAI and Amazon Bedrock | Subscription command-line tools | Local Ollama models | Work with a session | Put calls in functions and scripts

Inspecting the prompt | Object descriptions and result size | Reported usage and estimated components | Budgets and partial results | Three different caches | Explicit ways to reduce context | The source benchmark

Peter Naur: make the program readable | Peter Cathcart Wason: examine the reasoning | Two ideas in one R workflow

Introduction | Installation | Example Data | simple_pheno.txt | simple_kinship.txt | Simple Example: Resolving Relatedness in a Small Cohort | Function Arguments | Output | Final Notes

Installation | Setting Up Your Environment | Basic Usage | Set up conda environment | Querying Nodes | Example Output (Nodes Data Frame): | Querying Edges | Example Output (Edges Data Frame): | Querying Netowrk in Batches | Extracting Edges in Batches | Extracting Nodes in Batches | Advanced Features