Data sources
Unstructured
Use Unstructured to parse, chunk, and load PDFs, Word, and 25+ document types into Pinecone for LLM-ready RAG ETL pipelines and semantic search apps.
Unstructured builds ETL tools for LLMs, including an open-source Python library, a SaaS API, and an ETL platform. It extracts content and metadata from 25+ document types, including PDFs, Word documents, and PowerPoint files, and then performs preprocessing steps for LLMs, such as chunking. Unstructured maintains upstream connections to data sources such as SharePoint and Google Drive, and downstream connections to databases such as Pinecone.
The Pinecone integration with Unstructured lets you load data from any source or document type into Pinecone with a single click, so you can build LLM apps that connect to your organization’s data.
Was this page helpful?