Update readme and citation

NEWS.md

@@ -5,6 +5,7 @@
 - Add `encode_images_in_messages()` to encode images in messages for `chat()` function.
 - Add `create_messages()` to create messages easily.
 - Helper functions for managing messages accept `...` parameter to pass additional options.
+- Update README and docs to reflect changes.
 
 # ollamar 1.2.0
 

README.Rmd

@@ -29,6 +29,24 @@ See [Ollama's Github page](https://github.com/ollama/ollama) for more informatio
 
 > Note: You should have at least 8 GB of RAM available to run the 7B models, 16 GB to run the 13B models, and 32 GB to run the 33B models.
 
+## Citing `ollamar`
+
+If you use this library, please cite [this paper](https://doi.org/10.31234/osf.io/zsrg5) using the following BibTeX entry:
+
+```bibtex
+@article{Lin2024Aug,
+	author = {Lin, Hause and Safi, Tawab},
+	title = {{ollamar: An R package for running large language models}},
+	journal = {PsyArXiv},
+	year = {2024},
+	month = aug,
+	urldate = {2024-08-24},
+	publisher = {OSF},
+	doi = {10.31234/osf.io/zsrg5},
+	url = {https://doi.org/10.31234/osf.io/zsrg5}
+}
+```
+
 ## Ollama R versus Ollama Python/JavaScript
 
 This library has been inspired by the official [Ollama Python](https://github.com/ollama/ollama-python) and [Ollama JavaScript](https://github.com/ollama/ollama-js) libraries. If you're coming from Python or JavaScript, you should feel right at home. Alternatively, if you plan to use Ollama with Python or JavaScript, using this R library will help you understand the Python/JavaScript libraries as well.
@@ -295,6 +313,24 @@ messages <- create_messages(
 )
 ```
 
+You can convert `data.frame`, `tibble` or `data.table` objects to `list()` of messages and vice versa with functions from base R or other popular libraries.
+
+```{r eval=FALSE}
+# create a list of messages 
+messages <- create_messages(
+  create_message("You're a knowledgeable tour guide.", role = "system"),
+  create_message("What is the capital of Australia?")  
+)
+
+# convert to dataframe
+df <- dplyr::bind_rows(messages)  # with dplyr library
+df <- data.table::rbindlist(messages)  # with data.table library
+
+# convert dataframe to list with apply, purrr functions
+apply(df, 1, as.list)  # convert each row to a list with base R apply
+purrr::transpose(df)  # with purrr library
+```
+
 ## Advanced usage
 
 ### Parallel requests

README.md

@@ -29,6 +29,26 @@ for details)](https://github.com/ollama/ollama/blob/main/docs/api.md).
 > Note: You should have at least 8 GB of RAM available to run the 7B
 > models, 16 GB to run the 13B models, and 32 GB to run the 33B models.
 
+## Citing `ollamar`
+
+If you use this library, please cite [this
+paper](https://doi.org/10.31234/osf.io/zsrg5) using the following BibTeX
+entry:
+
+``` bibtex
+@article{Lin2024Aug,
+    author = {Lin, Hause and Safi, Tawab},
+    title = {{ollamar: An R package for running large language models}},
+    journal = {PsyArXiv},
+    year = {2024},
+    month = aug,
+    urldate = {2024-08-24},
+    publisher = {OSF},
+    doi = {10.31234/osf.io/zsrg5},
+    url = {https://doi.org/10.31234/osf.io/zsrg5}
+}
+```
+
 ## Ollama R versus Ollama Python/JavaScript
 
 This library has been inspired by the official [Ollama
@@ -342,6 +362,26 @@ messages <- create_messages(
 )
 ```
 
+You can convert `data.frame`, `tibble` or `data.table` objects to
+`list()` of messages and vice versa with functions from base R or other
+popular libraries.
+
+``` r
+# create a list of messages 
+messages <- create_messages(
+  create_message("You're a knowledgeable tour guide.", role = "system"),
+  create_message("What is the capital of Australia?")  
+)
+
+# convert to dataframe
+df <- dplyr::bind_rows(messages)  # with dplyr library
+df <- data.table::rbindlist(messages)  # with data.table library
+
+# convert dataframe to list with apply, purrr functions
+apply(df, 1, as.list)  # convert each row to a list with base R apply
+purrr::transpose(df)  # with purrr library
+```
+
 ## Advanced usage
 
 ### Parallel requests

inst/CITATION

@@ -0,0 +1,18 @@
+citHeader("To cite ollamar in publications use:")
+
+citEntry(
+  entry    = "Article",
+  title    = "ollamar: An R package for running large language models",
+  author   = "Lin Hause and Tawab Safi",
+  journal  = "PsyArXiv",
+  year     = "2024",
+  month    = "aug",
+  publisher = "OSF",
+  doi      = "10.31234/osf.io/zsrg5",
+  url      = "https://doi.org/10.31234/osf.io/zsrg5",
+  textVersion = paste0(
+    "Lin, H., & Safi, T. (2024). ",
+    "ollamar: An R package for running large language models. ",
+    "PsyArXiv. https://doi.org/10.31234/osf.io/zsrg5"
+  )
+)

tests/testthat/test-utils.R

@@ -131,4 +131,25 @@ test_that("copy function works with basic input", {
     expect_true(length(messages4) == 4)
     expect_true(messages4[[2]]$new_inserted == "NEW_INS")
 
+
+
+
+    # # convert from list to data.frame
+    # messages1 <- create_messages(
+    #     list(role = "system", content = "be nice"),
+    #     list(role = "user", content = "hello"),
+    #     list(role = "assistant", content = "hi")
+    # )
+    # expect_true(nrow(dplyr::bind_rows(messages1)) == 3)
+    # expect_true(ncol(dplyr::bind_rows(messages1)) == 2)
+    # expect_true(nrow(data.table::rbindlist(messages1)) == 3)
+    # expect_true(ncol(data.table::rbindlist(messages1)) == 2)
+    #
+    # d0 <- data.table::rbindlist(messages1)
+    # # convert from data.frame to list
+    # expect_equal(apply(d0, 1, as.list), messages1)
+    # expect_equal(purrr::transpose(d0), messages1)
+    # expect_equal(lapply(1:nrow(d0), function(i) as.list(d0[i, ])), messages1)
+
+
 })