Keywords AI
Compare Carbon (Perplexity) and Docling side by side. Both are tools in the RAG Frameworks category.
| Category | RAG Frameworks | RAG Frameworks |
| Pricing | usage-based | Open Source |
| Best For | B2B startups needing data ingestion from multiple sources | Developers and researchers who need accurate document parsing with layout and table understanding |
| Website | carbon.ai | github.com |
| Key Features |
|
|
| Use Cases | — |
|
Carbon, acquired by Perplexity in December 2024, provided pre-built data connectors for ingesting unstructured data from 25+ sources into LLM applications. Its managed API was wound down in March 2025, with its technology now integrated into Perplexity's enterprise data connectivity stack. Carbon's connectors supported Google Drive, Notion, Slack, Confluence, and other popular data sources for RAG pipelines.
Docling is IBM's open-source document conversion toolkit that transforms PDFs, DOCX, PPTX, and other document formats into structured JSON or markdown. It uses advanced layout analysis and table structure recognition to preserve document structure, making it ideal for preparing documents for RAG and LLM applications. Docling integrates with LlamaIndex and LangChain for seamless pipeline construction.
Frameworks and tools for building retrieval-augmented generation pipelines—document parsing, chunking, indexing, and query engines that connect LLMs to your data.
Browse all RAG Frameworks tools →