fetch_data

Extracts content and metadata from local documents or websites. Supports PDF, DOCX, PPTX, TXT, HTML files
and performs BFS web crawling up to the specified depth.

Enables Retrieval-Augmented Generation (RAG) workflows in R by combining
local vector search using 'DuckDB' with optional web search via the 'Tavily' API.
Supports OpenAI- and Ollama-compatible embedding models, full-text and HNSW
(Hierarchical Navigable Small World) indexing, and modular large language model
(LLM) invocation. Designed for advanced question-answering, chat-based
applications, and production-ready AI pipelines. This package is the R
equivalent of the 'python' package 'RAGFlowChain' available at
<https://pypi.org/project/RAGFlowChain/>.

Kwadwo Daddy Nyame Owusu Boakye

RAGFlowChainR

Retrieval-Augmented Generation (RAG) Workflows in R with Local
and Web Search

fetch_data function

<dl><dt>local_paths</dt>
<dd>A character vector of file paths or directories to scan for documents.</dd>
<dt>website_urls</dt>
<dd>A character vector of website URLs to crawl and extract text from.</dd>
<dt>crawl_depth</dt>
<dd>Integer indicating BFS crawl depth; set to NULL for infinite crawl.</dd></dl>

Arguments

Fetch Data from Local Files and Websites — fetch_data

<dl>

<dt>local_paths</dt>
<dd>A character vector of file paths or directories to scan for documents.</dd>


<dt>website_urls</dt>
<dd>A character vector of website URLs to crawl and extract text from.</dd>


<dt>crawl_depth</dt>
<dd>Integer indicating BFS crawl depth; set to NULL for infinite crawl.</dd>

</dl>

fetch_data: Fetch Data from Local Files and Websites

Description

Usage

Value

Arguments