The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

AI Integration

library(TextAnalysisR)
packageVersion("TextAnalysisR")
## [1] '0.1.4'
mydata <- SpecialEduTech[seq_len(20), c("title", "abstract")]
united <- unite_cols(mydata, listed_vars = c("title", "abstract"))
toks   <- prep_texts(united, text_field = "united_texts")
dfm    <- quanteda::dfm(toks)
extract_keywords_tfidf(dfm, top_n = 10)
##         Keyword TF_IDF_Score Frequency
## 1           was    15.258649        44
## 2      practice    10.837080        18
## 3        groups    10.484550        15
## 4      educable    10.000000        10
## 5          were     9.948500        25
## 6         drill     9.785580        14
## 7   achievement     9.550560        24
## 8      mentally     9.062996        11
## 9  experimental     9.030900        15
## 10     assisted     9.016475        26

TextAnalysisR provides AI features via cloud-based providers.

On the hosted web app, Gemini usage is free, supported by the Google Cloud Research program. OpenAI calls require a personal API key.

Providers

Provider Type API Key Best For
OpenAI Web-based OPENAI_API_KEY Quality, speed
Gemini Web-based None on hosted app; otherwise GEMINI_API_KEY Quality, speed
spaCy Local None Linguistic analysis
Transformers Local None Embeddings, sentiment

Setup

Set keys via .Renviron (persistent) or Sys.setenv() (session). The cloud chat, embedding, and RAG functions (call_llm_api(), call_openai_chat(), call_gemini_chat(), get_api_embeddings(), run_rag_search()) require an API key and network access; see their reference pages for usage.

Default Models

Provider Chat Model Embedding Model
OpenAI gpt-4.1-mini text-embedding-3-small
Gemini gemini-2.5-flash gemini-embedding-001
Local - all-MiniLM-L6-v2

Responsible AI Design

All AI features follow NIST AI Risk Management Framework principles:

Principle Implementation
Human oversight AI suggests; review and approve
User control Edit, regenerate, or override any output
Transparency View prompts and parameters used
Privacy Local sentence-transformers and spaCy options for sensitive data
Grounding Content based on input data, not generic knowledge

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.