| Version: | 0.1.1 |
| Title: | R 'shiny' Interface for Chatting with Large Language Models Offline on Local with 'ollama' |
| Description: | Chat with large language models on your machine without internet with complete privacy via 'ollama', powered by R 'shiny' interface. For more information on 'ollama', visit https://ollama.com. |
| Maintainer: | Indraneel Chakraborty <hello.indraneel@gmail.com> |
| License: | Apache License (≥ 2) |
| URL: | https://www.indraneelchakraborty.com/shiny.ollama/, https://github.com/ineelhere/shiny.ollama |
| BugReports: | https://github.com/ineelhere/shiny.ollama/issues |
| Encoding: | UTF-8 |
| Imports: | shiny (≥ 1.7.0), bslib (≥ 0.4.0), httr (≥ 1.4.0), jsonlite (≥ 1.8.0), markdown, mockery |
| Depends: | R (≥ 3.5.0) |
| Suggests: | testthat (≥ 3.0.0), pkgdown (≥ 2.0.0) |
| Config/testthat/edition: | 3 |
| RoxygenNote: | 7.3.2 |
| Date: | 2025-01-12 |
| NeedsCompilation: | no |
| Packaged: | 2025-01-27 04:59:21 UTC; neel0 |
| Author: | Indraneel Chakraborty
 [aut, cre] |
| Repository: | CRAN |
| Date/Publication: | 2025-01-27 05:40:02 UTC |
Create the Shiny server function for the chat interface
Description
Create the Shiny server function for the chat interface
Usage
create_chat_server()
Value
A Shiny server function
Create the Shiny UI for the chat interface
Description
Create the Shiny UI for the chat interface
Usage
create_chat_ui()
Value
A Shiny UI object
Fetch available models from Ollama API
Description
Fetch available models from Ollama API
Usage
fetch_models()
Value
Character vector of model names or an error message
Convert chat history to downloadable format
Description
Convert chat history to downloadable format
Usage
format_chat_history(messages, format = c("HTML", "CSV"))
Arguments
messages |
List of chat messages |
format |
Character string specifying format ("HTML" or "CSV") |
Value
Formatted chat history as a character string (HTML) or a data frame (CSV)
Format a message as markdown
Description
This helper function formats a message with a specified role (User, Assistant, or System) into a markdown-styled string.
Usage
format_message_md(role, content)
Arguments
role |
A character string specifying the role (e.g., "User", "Assistant", "System"). |
content |
A character string containing the message content. |
Value
A character string formatted as markdown.
Parse a markdown-formatted message
Description
This function extracts the role and content from a markdown-formatted message.
Usage
parse_message(message)
Arguments
message |
A character string containing the markdown-formatted message. |
Value
A list with two elements:
role |
A character string representing the role (e.g., "User", "Assistant", "System"). |
content |
A character string containing the extracted message content. |
Run shiny Application for Chat Interface
Description
Launches a shiny app for interacting with the Ollama API
Usage
run_app()
Value
No return value, called for side effects.
Send message to Ollama API and get response
Description
Send message to Ollama API and get response
Usage
send_ollama_message(message, model)
Arguments
message |
Character string containing the user message |
model |
Character string specifying the model name |
Value
A list with elements 'success' (logical) and either 'response' (character) or 'error' (character)