38 free templates

Document Ops Workflow Templates

These free document automation templates cover RAG ingestion, document Q&A, PDF extraction, and translation. Built on Heym with a self-hosted Qdrant vector store and source-available nodes, they let you ground AI answers in your own files without sending documents to a managed cloud.

RAG ingestion
document Q&A
PDF workflows
file sharing

Browse templates

Use cases

What you can automate with Document Ops templates

RAG ingestion

Chunk and embed a document into a Qdrant vector store so it can be retrieved later by the RAG Search node.

Document Q&A

Search your vector store for relevant context, then answer with an LLM grounded in your own documents.

Chat with Drive files

List your Google Drive, read the file you need, extract its text, and answer questions in plain language.

PDF and DOCX translation

Translate the full text of any uploaded document with an AI agent.

Clean web text

Fetch LLM-ready text from any URL for downstream summarization or extraction.

Batch fetching

Loop over a list of URLs, fetch each one, and merge all responses into a single payload.

Browse all Document Ops templates

Pick a workflow, copy the JSON, and adapt the nodes for your team.

38 templates·Document Ops

Sticky Note

File upload intake

Run the workflow to mint a single-use upload curl. Uploading a file to that URL starts the real run.

Main path

IncomingFile -> BuildFileReceipt -> UploadReceipt

IncomingFile

BuildFileReceipt

UploadReceipt

File Upload Intake Metadata

Document Ops

Mint a single-use upload link, receive a multipart file, and return clean metadata plus the Drive download URL.

#File Upload#Trigger#Drive

Sticky Note

Tesseract OCR PDF to Text

Upload a scanned PDF and return searchable text without an external OCR service.

Main path

ScannedPDF -> ExtractText -> OCRResult

ScannedPDF

ExtractText

OCRResult

Tesseract OCR PDF to Text

Document Ops

Upload a scanned PDF, extract searchable text with Tesseract OCR, and return page-level results.

#Tesseract#OCR#PDF

Sticky Note

Website Loader

Fetch clean, LLM-ready website text from any URL using the Jina Reader API.

Main path

Target URL -> Jina Fetch -> Page Content

Target URL

Jina Fetch

Page Content

Website Loader

Document Ops

Fetch clean, LLM-ready website text from any URL using the Jina Reader API.

#Website Loader#HTTP#Jina

Sticky Note

Before you run

Customize the demo values, then run once to inspect the node outputs in order.

Sticky Note

PDF / DOCX Translation Agent

Translate the full text of any uploaded document using an AI agent.

Main path

Document Text -> Translation Agent -> Translated Doc

Document Text

Translation Agent

GLM-4.7

Translated Doc

PDF / DOCX Translation Agent

Document Ops

Translate the full text of any uploaded document using an AI agent.

#AI#Translation#Document

Sticky Note

Before you run

Swap the demo URLs and selectors for real endpoints you control.

Sticky Note

Batch URL Fetcher

Iterate over a JSON array of URLs with the Loop node, fetch each via HTTP, and merge all responses into one payload.

Main path

URLList -> IterateURLs -> FetchEach -> CollectResults -> AllResults

URLList

IterateURLs

loop

done

FetchEach

CollectResults

AllResults

Batch URL Fetcher

Document Ops

Iterate over a JSON array of URLs with the Loop node, fetch each via HTTP, and merge all responses into one payload.

#Loop#HTTP#Batch

Sticky Note

Before you run

Fill in the storage IDs, dataset names, or file targets that belong to your workspace.

Sticky Note

RAG Document Ingest

Chunk and embed a document into a Qdrant vector store so it can be retrieved later by the RAG Search node.

Main path

DocumentText -> IngestDoc -> IngestResult

DocumentText

IngestDoc

IngestResult

RAG Document Ingest

Document Ops

Chunk and embed a document into a Qdrant vector store so it can be retrieved later by the RAG Search node.

#RAG#Vector Store#Knowledge Base

Sticky Note

Before you run

Fill in the storage IDs, dataset names, or file targets that belong to your workspace.

Sticky Note

RAG Q&A Agent

Search your Qdrant vector store for relevant context, then answer with an LLM — grounded in your own documents.

Main path

UserQuestion -> RagSearch -> AnswerLLM -> Answer

UserQuestion

RagSearch

AnswerLLM

GLM-4.7

Answer

RAG Q&A Agent

Document Ops

Search your Qdrant vector store for relevant context, then answer with an LLM — grounded in your own documents.

#RAG#Search#LLM

Sticky Note

Drive Share Link Mailer

Fetch a remote file into Drive, return the download link immediately, and email the same link asynchronously.

Main path

LinkRequest -> StoreInDrive -> ShareLink -> EmailLink

LinkRequest

StoreInDrive

ShareLink

EmailLink

Drive Share Link Mailer

Document Ops

Fetch a remote file into Drive, return the download link immediately, and email the same link asynchronously.

#Drive#Email#Files

Sticky Note

Chat With Docs (Drive)

This workflow lets you chat with your Google Drive files.
Features:

List available Drive files

Sticky Note

Drive Tools:
1. listDriveFiles — Lists all files in Drive
2. readDriveFile — Reads a specific file (returns base64)
Python Skills:

userQuery

listDriveFiles

readDriveFile

docAgent

zai-glm-4.7

answer

Chat with Drive Docs

Document Ops

Ask questions about your Google Drive PDF files. An agent lists your Drive, reads the file you need, extracts its text, and answers in plain language.

#Drive#PDF#Agent

Sticky Note

Invoice Data Extraction from PDF

Agent calls LlamaParse tool → receives markdown → returns structured invoice JSON.
Tool:

llamaParseAPI — POST PDF URL to LlamaParse, returns markdown

Sticky Note

llamaParseAPI tool:

POST PDF URL → LlamaParse
Returns: markdown text of the invoice

Agent output schema:

Sticky Note

Before you run

Open llamaParseAPI and replace YOUR_LLAMAPARSE_KEY in the curl command.
Open InvoiceExtractor and connect an OpenAI-compatible credential.
Paste a real invoice PDF URL into InvoiceURL and hit Run.

InvoiceURL

llamaParseAPI

InvoiceExtractor

GLM-4.7

InvoiceData

Invoice Data Extraction from PDF

Finance Ops

An AI agent calls LlamaParse to parse a PDF invoice, then returns structured JSON with vendor, amount, line items, and totals.

#Invoice#PDF#LlamaParse

Sticky Note

Contract review setup

Paste contract text into contractIntake or call the workflow by API.
Customize the risk policy in reviewContractRisk.
The condition looks for LEGAL_REVIEW.
Keep a qualified reviewer in the loop for legal decisions.

contractIntake

reviewContractRisk

GLM-4.7

legalRiskCheck

true

false

notifyLegalReview

legalReviewResult

contractRiskResult

Sticky Note

Live run checklist

Test both exits around legalRiskCheck before going live.
Replace sample values early so downstream expressions are validated with real data.
Double-check notifyLegalReview before sending alerts or messages to a live destination.

Contract Risk Review Queue

Legal & Compliance

Summarize pasted contract text, flag risky clauses, and send review-needed items to Slack for legal follow-up.

#Legal#Contract Review#Slack

Sticky Note

Onboarding setup

Replace the sample fields in newHireIntake with your HRIS or form payload.
Point provisionAccounts at your IT/identity provisioning webhook.
Customize the checklist policy in buildOnboardingPlan.
Keep a human owner accountable for access approvals.

newHireIntake

buildOnboardingPlan

GLM-4.7

provisionAccounts

sendWelcomeEmail

notifyPeopleOps

onboardingResult

Sticky Note

Live run checklist

Run once with sample data and inspect each node output in sequence.
Replace sample values early so downstream expressions are validated with real data.
Double-check notifyPeopleOps before sending alerts or messages to a live destination.

Employee Onboarding Orchestrator

HR & Recruiting

Turn a new-hire intake into a personalized onboarding plan, provision accounts via API, send a welcome email, and brief People Ops in Slack.

#HR#Onboarding#Employee Onboarding

Sticky Note

Proposal setup

Fill proposalInput right after a discovery call.
Adjust the structure and tone in generateProposal.
The draft goes to the rep, not the client, by default.
Confirm scope and pricing before sending.

proposalInput

generateProposal

GLM-4.7

emailDraftToRep

proposalResult

AI Sales Proposal Generator

Sales & CRM

Turn a short post-call form into a structured, customer-ready proposal draft and email it to the rep for review.

#Sales#Proposal#Document

Sticky Note

Action items setup

Paste notes or a transcript into meetingNotes.
Owners and dates are used only when the notes mention them.
Actions post to your team channel.
Edit the output format in extractActions.

meetingNotes

extractActions

GLM-4.7

postActions

actionItemsResult

Meeting Notes to Action Items

Personal Productivity

Paste meeting notes and get a clean list of action items with owners and due dates, posted to your team channel.

#Productivity#Meeting Notes#Action Items

Sticky Note

HTML table skill setup

Pick an LLM credential in tableConverterAgent.
Paste HTML containing a table into htmlInput.
The html_table_to_markdown Python skill does the parsing.
No external dependencies.

htmlInput

tableConverterAgent

z-ai/glm-4.7

markdownResult

HTML Table to Markdown (Agent Skill)

Document Ops

An agent runs a bundled Python skill that converts HTML tables into clean Markdown tables using only the standard library.

#Skills#Python#HTML

Sticky Note

PII redactor setup

Pick an LLM credential in redactionAgent.
Paste text into rawText.
The pii_redactor Python skill removes emails, phones, cards, SSNs.
A helpful first pass, not a compliance guarantee.

rawText

redactionAgent

z-ai/glm-4.7

redactedResult

PII Redactor (Agent Skill)

Legal & Compliance

An agent runs a bundled Python skill that redacts emails, phone numbers, card numbers, and SSNs from text before it is shared.

#Skills#Python#PII

Sticky Note

Offboarding setup

Fill departureIntake from your HRIS.
Tune the checklist policy in buildOffboardingPlan.
Plan posts to your IT and People Ops channel.
Keep an owner accountable for access revocation.

departureIntake

buildOffboardingPlan

GLM-4.7

notifyOffboardingTeam

offboardingResult

Employee Offboarding Checklist

HR & Recruiting

Turn a departure into a complete offboarding checklist — deprovision accounts, recover assets, transfer knowledge — and notify IT and People Ops.

#HR#Offboarding#Deprovisioning

Sticky Note

NDA generator setup

Fill ndaIntake with parties, purpose, term, governing law.
Output is a draft for review, not legal advice.
Have a qualified lawyer finalize every agreement.

ndaIntake

draftNda

GLM-4.7

ndaResult

NDA Generator from Intake

Legal & Compliance

Turn a few details about two parties and a purpose into a clean, structured NDA draft for legal review.

#Legal#NDA#Contract

Sticky Note

Obligation extractor setup

Paste contract text into contractText.
Output lists obligations, owners, and key dates.
An operations aid, not legal advice.
Verify extracted terms against the source.

contractText

extractObligations

GLM-4.7

obligationResult

Contract Obligation & Deadline Extractor

Legal & Compliance

Paste contract text and extract obligations, owners, key dates, and renewal terms into a clean structured list.

#Legal#Contract#Obligations

Sticky Note

Compliance checklist setup

Name the framework and describe your business in complianceInput.
Output gives control areas, tasks, owners, and priority.
A planning aid, not legal or audit advice.

complianceInput

buildChecklist

GLM-4.7

checklistResult

Compliance Checklist Generator

Legal & Compliance

Generate a tailored compliance checklist for a framework like SOC 2, GDPR, or HIPAA, scoped to your business context.

#Legal#Compliance#SOC 2

Sticky Note

Prior auth setup

Fill priorAuthIntake with procedure, diagnosis, payer, plan.
Output is an administrative draft, not medical advice.
A clinician must review the justification before submission.
Do not include patient identifiers in the sample.

priorAuthIntake

prepPriorAuth

GLM-4.7

priorAuthResult

Insurance Prior Authorization Prep

Healthcare

Build the documentation checklist and a draft medical-necessity justification for a prior authorization request.

#Healthcare#Prior Authorization#Insurance

Sticky Note

Cease and desist PDF setup

Pick an LLM credential in ceaseDesistAgent.
Fill the parties, issue, and deadline in cdIntake.
The cease_desist_pdf Python skill renders the PDF.
Output is a draft for review, not legal advice.

cdIntake

ceaseDesistAgent

GLM-4.7

ceaseDesistResult

Cease and Desist Letter (Agent Skill, PDF)

Legal & Compliance

An agent drafts a cease and desist letter, then a bundled Python skill renders it into a formatted, downloadable PDF.

#Skills#Python#PDF

Sticky Note

Demand letter PDF setup

Pick an LLM credential in demandAgent.
Edit creditor, debtor, line_items, and deadline in demandIntake.
The demand_letter_pdf Python skill totals amounts and renders the PDF.
Output is a draft for review, not legal advice.

demandIntake

demandAgent

GLM-4.7

demandResult

Demand Letter Generator (Agent Skill, PDF)

Legal & Compliance

An agent drafts a formal payment demand letter; a bundled Python skill totals the amounts owed and renders a downloadable PDF.

#Skills#Python#PDF

Sticky Note

Privacy policy PDF setup

Pick an LLM credential in privacyAgent.
Edit company, website, and data collected in policyIntake.
The privacy_policy_pdf Python skill renders the numbered PDF.
Output is a draft for review, not legal advice.

policyIntake

privacyAgent

GLM-4.7

privacyResult

Privacy Policy Generator (Agent Skill, PDF)

Legal & Compliance

An agent drafts a GDPR and CCPA aware privacy policy; a bundled Python skill renders the numbered sections into a downloadable PDF.

#Skills#Python#PDF

All 38 Document Ops templates, A to Z

Why teams run Document Ops workflows on Heym

Heym is a source-available, self-hosted AI workflow platform for agentic automation: agents that call tools, retrieve from your own documents, and pause for human review when a step needs it.

Free and source-available

Released under MIT with a Commons Clause, with no per-task or per-execution pricing.

Self-hosted

Runs on your own infrastructure with Docker, so your data and credentials stay yours.

One-paste import

Copy a template JSON, paste it onto the canvas, and run it in minutes.

Agentic by default

Agent nodes, MCP tools, and built-in RAG on a visual workflow canvas.

Document Ops templates FAQ

What is a RAG ingestion pipeline?

A RAG ingestion pipeline chunks a document, embeds the chunks, and stores them in a vector database so an LLM can later retrieve the right context to answer questions. The RAG Document Ingest template does this with a self-hosted Qdrant store.

Can I chat with my own documents?

Yes. The RAG Q&A Agent and Chat with Drive Docs templates retrieve relevant passages from your files and answer questions grounded in that content rather than guessing.

Can I customize a template after importing it?

Every node, prompt, credential, and connection is editable after import. Swap the model, change the trigger, add or remove tools, and rewire branches directly on the canvas without writing boilerplate.

Is Heym free and self-hosted?

Yes. Heym is source-available under an MIT license with a Commons Clause, so you can run every template on your own infrastructure with Docker. There is no per-task or per-execution pricing, and your data and credentials stay inside your environment.

What makes these different from ordinary automation templates?

Each one runs on an AI-native canvas, so agent nodes, MCP tools, and built-in RAG sit in the same workflow as the triggers, branching, and integrations. That is the difference between a fixed sequence of steps and an agentic workflow that can retrieve context, call tools, and pause for human review while it runs.

How to build a RAG pipeline RAG vs fine-tuning Browse all Heym nodes

Template categories

Explore other use cases

View all templates

Marketing & SEO

Content repurposing, social publishing, SEO research, analytics reporting, and audience monitoring for growth teams.

Sales & CRM

Lead qualification, CRM enrichment, personalized outreach, follow-up workflows, and revenue handoffs.

Customer Support

Email triage, FAQ replies, human approval checkpoints, inbox summaries, and customer escalation routing.

Legal & Compliance

Governed research, review checkpoints, policy-sensitive document handling, and audit-friendly agent workflows.

HR & Recruiting

Candidate search, resume-style ranking, recruiting summaries, interview preparation, and hiring pipeline automation.

Finance Ops

Invoice extraction, payment webhooks, receipt creation, pricing monitors, and finance data handoffs.

Data & Analytics

Spreadsheet enrichment, ETL-style syncs, schema remapping, BigQuery handoffs, and reporting pipelines.

Dev & IT Ops

Release monitoring, Sentry issue triage, API reliability, code review, WebSocket alerts, RabbitMQ jobs, and internal tool workflows.

App Integrations

Connect Slack, Discord, Telegram, HTTP APIs, MCP tools, and external systems with reusable workflow patterns.

Personal Productivity

Personal assistants, briefing emails, meeting summaries, lightweight research, reminders, and daily automation.

Education & Learning

Language learning, study guides, lesson planning, assessment feedback, research workflows, and LMS operations.

Healthcare

Clinical-style triage examples, structured health summaries, specialist review patterns, and careful human oversight.

Logistics & Supply Chain

Shipment tracking, delivery exceptions, carrier rates, freight audit, dock scheduling, and supply chain data checks.

Energy & Utilities

Smart meter anomalies, field work orders, outage updates, solar performance, utility bill checks, and interconnection reviews.

E-commerce

Return triage, review insights, order fraud screening, cart recovery, product catalog quality, and inventory checks.

AI Agents

General LLM and agent workflows for classification, generation, evaluation, image creation, and text-to-workflow examples.

Agent Teams

Orchestrator, researcher, writer, validator, and specialist agent patterns for multi-step AI work.

Operations Automation

Scheduled checks, debounce steps, generic routers, async dispatchers, and repeatable business operations.

Agent Skills

Agent templates with bundled skills, custom tools, Python actions, and repeatable expert workflows.

What you can automate with Document Ops templates

RAG ingestion

Document Q&A

Chat with Drive files

PDF and DOCX translation

Clean web text

Batch fetching

Popular Document Ops templates

RAG Document Ingest

RAG Q&A Agent

Chat with Drive Docs

PDF / DOCX Translation Agent

Website Loader

Batch URL Fetcher

Browse all Document Ops templates

File Upload Intake Metadata

Tesseract OCR PDF to Text

Website Loader

PDF / DOCX Translation Agent

Batch URL Fetcher

RAG Document Ingest

RAG Q&A Agent

Drive Share Link Mailer

Chat with Drive Docs

Invoice Data Extraction from PDF

Contract Risk Review Queue

Employee Onboarding Orchestrator

AI Sales Proposal Generator

Meeting Notes to Action Items

HTML Table to Markdown (Agent Skill)

PII Redactor (Agent Skill)

Employee Offboarding Checklist

NDA Generator from Intake

Contract Obligation & Deadline Extractor

Compliance Checklist Generator

Insurance Prior Authorization Prep

Cease and Desist Letter (Agent Skill, PDF)

Demand Letter Generator (Agent Skill, PDF)

Privacy Policy Generator (Agent Skill, PDF)

Why teams run Document Ops workflows on Heym

Free and source-available

Self-hosted

One-paste import

Agentic by default

Document Ops templates FAQ

Related guides

Explore other use cases

Marketing & SEO

Sales & CRM

Customer Support

Legal & Compliance

HR & Recruiting

Finance Ops

Data & Analytics

Dev & IT Ops

App Integrations

Personal Productivity

Education & Learning

Healthcare

Logistics & Supply Chain

Energy & Utilities

E-commerce

AI Agents

Agent Teams

Operations Automation

Agent Skills

File Upload Intake Metadata

Tesseract OCR PDF to Text

Website Loader

PDF / DOCX Translation Agent

Batch URL Fetcher

RAG Document Ingest

RAG Q&A Agent

Drive Share Link Mailer

Chat with Drive Docs

Invoice Data Extraction from PDF

Contract Risk Review Queue

Employee Onboarding Orchestrator