Polyvia-1.0 is live — view SDKs and Skills on GitHub→

Multimodal
Retrieval API

Most-accurate Multimodal Retrieval Infrastructure with Semantic Memory — for your AI agents

Join GitHub Documentation

$npx skills add polyvia-ai/skills

Core Engine

Capabilities of Polyvia

Organizing scattered multimodal and visual data into a unified knowledge graph queryable by AI agents.

Structured output

From visual documents
to structured facts

~80% of enterprise knowledge lives in visual form — charts, slides, financial reports, complex tables. Polyvia extracts the actual data, not just descriptions. "Revenue of Apple | Q4 2025 | $10.67B | bar chart | page 6" — not "this chart shows revenue."

Metric	Q3 2024	Growth
Revenue	$45.2M	+12%
Users	1.2M	+8%
Churn	2.1%	-0.5%
Net Retention	118%	+3%

Ontology Knowledge Graph

Facts connected,
not scattered

Every extracted fact linked by entity, time period, source, and metric type. Cross-reference EBITDA across 500 counterparty reports in sub-50ms. The graph compounds — every new document enriches the entire corpus.

Audit-ready answers

Every answer traced
back to source

Every response grounded in verifiable visual evidence — document, page, section, bounding box. Your agents produce answers teams can actually trust and audit.

Which segments show the fastest growth?

Cloud services led growth (+42%) driven by enterprise usage expansion.cite: 10-K p.42

Consumer subscriptions rose 18%, with Asia-Pacific up 31% year-over-year.cite: Deck p.7cite: 10-K p.58

Ask across files...⏎

Multimodal Ingest

Read. See. Listen.

One pipeline for documents, slides, images, and audio — every answer cites the exact paragraph, the exact chart, the exact second.

ReadDocuments

Cited to the paragraph

Q4 revenue rose to $24.8B, up 14% year-over-year.

Cloud services led growth at +42%, driven by enterprise contract expansion across North America and APAC. Consumer hardware was flat.

Net retention reached 118%, the highest in eight quarters…

cite · 10-K · p.42 ¶3

SupportsPDFDOCXMDTXT

SeeSlides

Read the chart, not the caption

cite · deck p.7 · chart 2

SupportsPPTXPDF

SeeImages

Bounding-box precision

cite · fig 4 · (140,16)→(230,104)

SupportsPNGJPGWEBP

ListenAudio

Cited to the second, not the recording

00:0002:1402:3105:00

cite · 02:14 → 02:31 · “…retention reached 118%”

SupportsWAVMP3M4A

Built for scale

From 5 files to
50,000 documents

Drag-and-drop into ChatGPT works for 5 files — not 5,000. When you don't know which documents contain the answer, you need an infrastructure layer that organizes data before it reaches your AI agent. That's Polyvia.

Documents indexed

Query latency

Facts per corpus

Extraction confidence

Developer experience

Three ways to use Polyvia

TRY IT NOW

$npx skills add polyvia-ai/skills

Python & JS SDKsPython

# pip install polyvia
from polyvia import Polyvia

client = Polyvia(api_key=API_KEY)

# Batch ingest & wait for indexing
batch = client.ingest.batch(
  ["q4.pdf", "q3.pdf", "10k.pdf"],
  group_id="g_earnings",
)
for item in batch:
  client.ingest.wait(item.task_id)

# Query scoped to a group
answer = client.query(
  "Compare EBITDA across all filings",
  group_id="g_earnings",
).answer

Python SDK →JS / TS SDK →

MCP ServerJSON

{
  "mcpServers": {
    "polyvia": {
      "type": "http",
      "url": "https://app.polyvia.ai/mcp",
      "headers": {
        "Authorization":
          "Bearer poly_<key>"
      }
    }
  }
}

MCP Docs →Agent Skills →

Polyvia StudioWeb

// No code needed

1. Sign up at
   app.polyvia.ai

2. Upload PDFs, slides
   & reports

3. Search with
   natural language

4. Get cited answers
   across your corpus

Open Studio →

Integrations

Works with your stack

Google

Snowflake

SharePoint

CRM

ERP

Claude

Cursor

Notion

Slack

Dropbox

OpenAI

Pricing

Simple plans, scale as you grow

Start free for 7 days, no card required. Upgrade when you’re ready.

Starter

$19/ mo

or $16 / mo billed annually−17%

300 pages / month
3 hours of audio
300 chat queries

Choose Starter

Pro

$49/ mo

or $41 / mo billed annually−17%

1,500 pages / month
15 hours of audio
750 chat queries

Choose Pro

Team

$25/ seat / mo

or $21 / seat / mo billed annually−17%

1,000 pages per seat
5 hours of audio per seat
3-seat min, 5 organisations

Choose Team

🛡 Enterprise-Ready

Polyvia for
Enterprise

Same product, on your infrastructure. Private deployment with direct integrations and full data control.

Book a Demo

✓ On-prem / VPC deployment
✓ SOC2 compliant
✓ Integrations: S3, Snowflake, SharePoint, CRM, ERP
✓ BYOK — bring your own LLM
✓ Zero-training policy

Start building with
Multimodal Retrieval API

Get access to Polyvia, and stay up to date with updates!
Enter your email to join.

We're rolling out access weekly.

MultimodalRetrieval API