Any document that you want to query against should be uploaded ahead of time at https://app.vellum.ai/document-indexes.
Environment-Scoped Documents: Documents uploaded to a Document Index are Environment-scoped. Documents will only appear in search results when the search request is performed within the same Environment context. This ensures proper isolation between your different environments.
Document indexes act as a collection of documents grouped together for performing searches against for a specific use case. For example, if you are creating a chatbot to query against OpenAI’s help center documents, the text files of each article in the help center would be stored in one index. Here’s how it looks in Vellum’s UI:
You can manually upload files through the UI or via API.
Each document has a Name and an External ID which are
initially populated with the name of the file that you upload.
Name - Human readable text which is how the document will be visible in Vellum’s UI (in documents tab)
External ID - As the contents of a document change and the old documents becomes out of date, you can submit the updated document for reindexing re-uploading it and specifying the same External ID.
In addition to sending plain strings via API, Vellum also supports uploading files of the following types:
For .pdf, .png, and .jpg files, we apply an OCR process to convert the file to a text representation. If you need another file type, please reach out!
Each document can be up to 32MB and 2.5M characters
Vellum currently uses a static chunking strategy.
Chunking strategy: Overlapping windows w/ sentence splitting
Min overlap: 50%
Max characters: 1000
This configuration works well for most use cases.
For users needing more detailed metadata in their chunk data, Vellum offers an “Advanced Chunking” strategy. Advanced Chunking enhances support for the following:
Additionally, indexes with Advanced Chunking will include meta.source.start_page_num and meta.source.stop_page_num attributes on each chunk returned during a search.
Advanced Chunking is particularly valuable when:
Below are examples showing how Advanced Chunking processes various document types, converting them into LLM-friendly formats that preserve semantic meaning while enabling effective search and retrieval.
The Advanced Chunking strategy preserves the menu structure, recognizing section headers, item names, and prices while maintaining their relationships.
Advanced Chunking not only extracts the text but also generates descriptions of images, providing context that would otherwise be lost. This enables semantic search across both textual and visual content.
The system accurately parses the invoice’s tabular structure, maintaining relationships between services, quantities, rates, and amounts. This structured representation enables precise information retrieval and calculation verification.
Advanced Chunking converts complex tables into both descriptive text and structured HTML representations, making the data accessible for both semantic search and structured queries.
Advanced Chunking can be used in tandem with our Summarizing Contents of a PDF File walkthrough to extract or summarize complex documents with ease. The enhanced metadata and structural preservation make it particularly effective for:
Please reach out to support@vellum.ai if you feel your chunking strategy needs aren’t met with the capabilities listed above.
