File Upload

Invero provides an integration that enables uploading single files directly in the platform. This integration offers a quick and simple way to add content to your knowledge base without setting up complex integrations or permissions.

Prerequisites​

• Files in one of the supported formats
• File size up to 100 MB per file

Data ingested​

When you upload files to Invero, the following data is ingested:

• Complete text content of the file
• For OpenAPI files, the complete API structure and documentation
• For Word documents, formatted text and structure
• For PDFs, see PDF documents

Supported file formats​

The following file types are supported:

Format	File Extension	Content Type
Markdown	.md	Documentation, guides, README files
MDX	.mdx	Documentation with embedded components
Text	.txt	Plain text content
OpenAPI	.json, .yaml, .yml	API specifications
YAML	.yaml, .yml	Configuration files
StackOverflow	.csv	Exported Q&A content
Word	.docx	Formatted documentation
PDF	.pdf	Technical documentation, misc.
Python	.py	Source code
JavaScript	.js, .jsx, .mjs, .cjs	Source code
TypeScript	.ts, .mts, .cts	Source code
TSX	.tsx	Source code
Go	.go	Source code
Java	.java	Source code
Rust	.rs	Source code
Swift	.swift	Source code
Kotlin	.kt, .kts	Source code
C#	.cs	Source code
Terraform	.tf, .tfvars, .tofu	Infrastructure as code

A .json file must contain an OpenAPI specification. A .yaml or .yml file that contains an OpenAPI specification is ingested as OpenAPI; any other is ingested as YAML.

Setup​

1. Go to the Sources tab in the Invero platform
2. Click Add new source
3. Enter a name for your source
4. Select File Upload as the source type
5. Click Choose File and select the file from your computer
6. Click Upload to begin the ingestion process

Best practices​

• Use descriptive filenames: Clear filenames help identify the content when reviewing sources
• Structure your content: Well-organized documents with headings and sections are easier for Invero to understand
• Keep files updated: If your content changes, you'll need to manually re-upload updated files
• Combine with other sources: File Upload works best as a supplement to more comprehensive sources
• PDFs: Documents with an embedded text layer give the best results. Scanned documents are processed with optical character recognition, which can be less accurate.
• Format markdown properly: Markdown files require proper structure with headings and standard syntax. See How should I format markdown files for AI ingestion?

Troubleshooting​

• File not accepted: Verify your file has one of the supported extensions
• Upload errors: Check that your file isn't corrupted and is under the size limit
• Formatting issues: Complex formatting in Word documents may not be perfectly preserved
• PDFs: As PDFs are unstructured documents, data extraction can have imperfect results