Vectorize Iris CLI and SDKs
Repo vectorize-io/vectorize-iris, read from GitHub 1 min ago. vectorize-io has not joined Take My Repo.
vectorize-io/vectorize-iris is a public repo on GitHub by vectorize-io. Vectorize Iris CLI and SDKs. It declares no license on GitHub. Public does not mean open source: without a license, nobody is granted the right to reuse it. It is written mainly in Rust, has 12 stars and last changed on 2026-11-04. Nobody has reviewed it on Take My Repo yet, which says nothing about its quality. Read from GitHub on 2026-11-18.
In the maintainer's words. Shown from GitHub; Take My Repo does not keep a copy.
Vectorize Iris is a model-based extraction solution that transforms how RAG systems handle PDFs. It combines extraction and chunking into one streamlined process, making it easier than ever to get clean, usable text from complex documents.
Documentation: docs.vectorize.io
Traditional OCR tools struggle with complex layouts, poor scans, and structured data. Iris uses advanced AI to understand document structure and context, delivering:
Choose your preferred tool:
from vectorize_iris import extract_text_from_file result = extract_text_from_file('document.pdf') print(result.text)
import { extractTextFromFile } from '@vectorize-io/iris'; const result = await extractTextFromFile('document.pdf'); console.log(result.text);
vectorize-iris document.pdf
CLI:
curl -fsSL https://get-iris.vectorize.io | shPython:
pip install vectorize-iris
Node.js:
npm install @vectorize-io/iris
Extract clean, structured text from any document format.
Split documents into semantic chunks perfect for RAG pipelines:
Extract structured data using JSON Schema.
Each schema must be an object with a top-level document key wrapping the JSON
Schema. Without that wrapper the extraction fails with
IllegalArgumentException: Document schema is missing.
result = extract_text_from_file('invoice.pdf', options=ExtractionOptions( metadata_schemas=[{ 'id': 'invoice-data', 'schema': { 'document': { 'type': 'object', 'properties': { 'invoice_number': {'type': 'string', 'description': 'Invoice reference number'}, 'date': {'type': 'string', 'description': 'Invoice date as printed'}, 'total_amount': {'type': 'number', 'description': 'Total amount due'}, 'vendor_name': {'type': 'string', 'description': 'Name of the vendor'} }, 'required': [] } } }], infer_metadata_schema=False )) # Returns structured JSON metadata
Give every property a type and a description โ both materially improve
extraction accuracy.
Set infer_metadata_schema=False when you supply your own schemas, so no schema
is generated and yours are used as-is. Leave it True (the default) to have a
schema inferred from the document instead.
You may optionally add a sibling sections key for per-chunk metadata; omit it
for document-level extraction only:
'schema': { 'document': { ... }, 'sections': {'line-items': { ... }} }
Guide the extraction with custom instructions:
result = extract_text_from_file('document.pdf', options=ExtractionOptions( parsing_instructions='Focus on extracting tables and ignore headers/footers' ))
Beautiful terminal output with progress indicators:
vectorize-iris document.pdf
Output:
โจ Vectorize Iris Extraction
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Upload prepared
โ File uploaded successfully
โ Extraction started
โ Extraction completed in 7s
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ Extracted Text
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
Stats: 5536 chars โข 1245 words โข 89 lines
This is the extracted text from your PDF document.
All formatting and structure is preserved.
Tables, lists, and other elements are properly extracted.
Download and extract files directly from HTTP/HTTPS URLs:
vectorize-iris https://arxiv.org/pdf/2206.01062
vectorize-iris document.pdf -o json
Output:
{
"success": true,
"text": "This is the extracted text from your PDF document...",
"chunks": null,
"metadata": null
}Pipe to jq:
vectorize-iris document.pdf -o json | jq -r '.text' > output.txt
Get only the extracted text:
vectorize-iris document.pdf -o text
Pipe directly:
vectorize-iris document.pdf -o text > output.txtUse -f to save output directly:
vectorize-iris document.pdf -o json -f output.json
Output:
โจ Vectorize Iris Extraction
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Upload prepared
โ File uploaded successfully
โ Extraction started
โ Extraction completed in 7s
โ Output written to output.json
Process all files in a directory automatically:
vectorize-iris ./documents -f ./output
Output:
๐ฆ Processing Directory
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ก Found 5 files to process
โ๏ธ Processing 1/5 - report-q1.pdf
โจ Vectorize Iris Extraction
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Upload prepared
โ File uploaded successfully
โ Extraction started
โ Extraction completed in 8s
โ Output written to output/report-q1.txt
โ๏ธ Processing 2/5 - report-q2.pdf
...
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โจ Batch Processing Complete
โ Successful: 5
With custom output format:
# Extract all PDFs to JSON vectorize-iris ./documents -o json -f ./output # Extract all files to plain text vectorize-iris ./scans -o text -f ./extracted
vectorize-iris long-document.pdf --chunk-size 512
Splits documents at semantic boundaries, perfect for RAG pipelines.
vectorize-iris report.pdf --parsing-instructions "Extract only tables and numerical data, ignore narrative text"Pass multiple metadata schemas and Iris will automatically classify which schema matches best:
vectorize-iris invoice.pdf \ --metadata-schema 'invoice:{"invoice_number":"string","date":"string","total_amount":"number","vendor":"string"}' \ --metadata-schema 'receipt:{"store_name":"string","date":"string","items":"array","total":"number"}' \ --metadata-schema 'contract:{"parties":"array","effective_date":"string","terms":"string"}' \ --metadata-schema 'cv:{"name":"string","contact_info":"object","skills":"array","experience":"array"}' \ -o json
Output:
{
"success": true,
"text": "...",
"metadata": "{\"invoice_number\":\"INV-2024-001\",\"date\":\"2024-01-15\",\"total_amount\":1250.00,\"vendor\":\"Acme Corp\"}",
"metadataSchema": "invoice"
}Iris automatically detected this was an invoice and extracted the relevant fields using the matching schema.
# Custom chunk size with metadata extraction vectorize-iris document.pdf \ --chunk-size 256 \ --infer-metadata-schema \ --parsing-instructions "Focus on extracting structured data" \ -o yaml -f output.yaml # Longer timeout for large documents vectorize-iris large-document.pdf \ --timeout 600 \ --poll-interval 5
The CLI offers multiple ways to configure your credentials:
The easiest way to get started - opens your browser for authentication:
vectorize-iris configure
What happens:
~/.vectorize-iris/credentialsIf you prefer not to use the browser, prompt for credentials manually:
vectorize-iris configure --manual
You'll be asked to enter:
Get these from platform.vectorize.io โ Account โ Org Settings โ Access Tokens
For scripts and automation, pass credentials directly:
vectorize-iris configure --api-token "your-token" --org-id "your-org-id"
Alternatively, set credentials via environment variables (works for all clients):
export VECTORIZE_TOKEN="your-token" export VECTORIZE_ORG_ID="your-org-id"
For Python and Node.js clients, use environment variables or pass credentials programmatically:
Environment variables:
export VECTORIZE_TOKEN="your-token" export VECTORIZE_ORG_ID="your-org-id"
Python:
from vectorize_iris import VectorizeIrisClient client = VectorizeIrisClient( api_token="your-token", org_id="your-org-id" )
Node.js:
import { extractTextFromFile } from '@vectorize-io/iris'; const result = await extractTextFromFile('document.pdf', { apiToken: 'your-token', orgId: 'your-org-id' });
For detailed documentation, API reference, and advanced features:
๐ docs.vectorize.io
MIT
vectorize-io/vectorize-iris is a public repo on GitHub by vectorize-io. Vectorize Iris CLI and SDKs.
It declares no license on GitHub. Public does not mean open source: without a license, nobody is granted the right to reuse it.
Its maker has not tagged a system, so it is unknown here. Its README says what it needs.
Open "Take it" on its page: Take My Repo writes an install plan for your machine and hands it to your AI agent (Claude Code, Codex or Cursor), which asks you before each step. Take My Repo has not tested it on any machine.
Its last change on GitHub was on 2026-11-04. Take My Repo does not judge from that whether it is maintained.
Nobody has reviewed it on Take My Repo yet, which says nothing about its quality.
Vectorize integrations with the Python ecosystem