Man pages for screenllm
LLM-Assisted Title/Abstract Screening for Systematic Reviews
| aggregate_scores | Aggregate scores across models and replicates for one record |
| audit_disagreements | Surface strong LLM-human disagreements for a manual audit |
| backend_mock | Mock backend for tests |
| backend_ollama | Ollama backend |
| build_prompt | Build a screening prompt for one record |
| check_setup | Verify local setup for 'screenllm' |
| clear_cache | Clear cached LLM scores for a project |
| custom_ensemble | Define a custom LLM ensemble |
| data_root | Root data directory used by the Shiny app |
| default_ensemble | The paper's default LLM ensemble |
| default_ensemble_light | A "light" ensemble that runs on a laptop |
| define_criteria | Define screening inclusion criteria |
| delete_artefact | Delete an artefact (or a whole project) |
| delete_model | Delete an Ollama model to free up disk space |
| detect_gpu | Detect a usable GPU for Ollama inference |
| estimate_runtime | Estimate wall-clock time for a ranking run |
| export_report | Render the screening report as a self-contained HTML document |
| export_worksheet | Export the human-screening worksheet |
| find_duplicates | Detect and remove duplicate records |
| find_ollama_binary | Locate the Ollama binary on disk |
| gpu_status | Live NVIDIA GPU status snapshot |
| install_prereqs | One-stop setup for a fresh machine |
| launch_app | Launch the full end-to-end Shiny app |
| launch_screening_app | Launch the interactive screening Shiny app |
| list_project_artefacts | Canonical artefact filenames |
| list_projects | List existing project names |
| load_artefact | Load an artefact from a project directory |
| load_toy_cbfm_criteria | Load the ready-made criteria for the toy CBFM corpus |
| normalise_decisions_shape | Coerce a decisions data.frame to the schema the rest of the... |
| ollama_catalog | Curated catalog of Ollama models useful for screening |
| ollama_health | Ping the Ollama server |
| ollama_installed_models | List Ollama models installed on the local server |
| ollama_installed_models_detail | Installed Ollama models with disk-space metadata |
| plan_screening | Plan the human screening set with the SAFE stopping rule |
| project_cache_dir | Return the cache directory for a project (used by... |
| project_dir | Return the absolute path of a named project directory |
| pull_job_cancel | Cancel a running pull job |
| pull_job_status | Current status of a background model pull |
| pull_model | Pull an Ollama model to the local server |
| rank_job_cancel | Cancel a running ranking job |
| rank_job_status | Read the current status of a ranking job |
| rank_records | Rank a corpus with an LLM ensemble |
| rank_worker_body | Function executed inside the background R process |
| read_decisions | Read completed screening decisions |
| read_lines_any_encoding | Read a text file, trying several encodings in turn. |
| read_records | Read a corpus of records from disk |
| save_artefact | Save an artefact into a project directory |
| start_pull_job | Start a background pull for an Ollama model |
| start_rank_job | Start a background ranking job for a project |
| summarise_screening | Summarise a completed screening session |
