You can now equip your n8n workflows with the world’s best parsing/extraction over your most complex documents

We’re excited to announce that LlamaParse is now an officially verified community node for n8n. This includes all our core capabilities: Parse, Extract, Classify, Split, and Retrieve.

This means you can build the following:

1. A document extraction workflow over an accuracy-sensitive use case (e.g. loan processing)

2. An indexed document knowledge base that you can plug into an AI agent.

To get started, all you need is a LlamaParse key.

Blog: https://llamaindex.ai/blog/bring-your-document-workflows-to-n8n-with-the-llamaparse-node?utm_medium=socials&utm_source=twitter&utm_campaign=2026-jun-…

Come check out LlamaParse: https://cloud.llamaindex.ai/?utm_source=xjl&utm_medium=social…

LlamaParse Platform Node for n8n: Parse, Classify, Extract & Retrieve Documents with AI

Source: https://www.llamaindex.ai/blog/bring-your-document-workflows-to-n8n-with-the-llamaparse-node?utm_medium=socials&utm_source=twitter&utm_campaign=2026-jun- We’ve shippedv5 and v6of theLlamaParse Platformcommunity node forn8n, and the package is now anofficially verified****community nodeas part of a broader partnership we signed with n8n to bring document intelligence to the no-code and low-code world. This post covers what the node exposes, what changed across the two major versions, and three concrete workflows you can build with it.

What the node does

The package ships a single node,**LlamaParse Platform,**which surfaces five LlamaCloud resources behind one resource/operation dropdown. All five share the sameLlamaParse APIcredential.

ResourceInputOutputParsebinary file\{ text \}— Markdown or plain textClassifybinary file +\{ category, description \}rules\{ category, reasons, confidence \}Splitbinary file + categoriesone item per segment:\{ category, confidence, pages \}Extractbinary file + Extraction Config ID\{ result \}— serialized JSON matching your schemaRetrieveindexId,query,topK``\{ context: string\[\] \} Parse runs across four tiers (fast,cost\_effective,agentic,agentic\_plus) with optional pinned parser versions. Retrieve targets both the v1 Pipelines API and the v2 Index Retrieval API. Every resource is markedusableAsTool: true, so it can be attached to an n8nAI Agentas a callable tool rather than only living in a linear flow.

What changed in v5

v5 was a foundation rewrite:

• Dropped the SDKin favor of direct HTTP calls against the LlamaCloud API, meaning no need for bundling and maintaining the SDK, as well as a smaller, more predictable surface.
• Extract migrated from V1 to V2, aligning with the current Extract service product config model.
• Configurable API base URL, so region-specific and self-hosted deployments are a credential setting rather than a fork.
• Reworked binary file handlingso files flow cleanly from any upstream node.

What changed in v6

v6 consolidated the package. Earlier releases shipped several distinct nodes (LlamaParse, LlamaClassify, LlamaExtract, and so on); v6collapses them into the single LlamaParse Platform nodewith the resource/operation pattern used by first-party n8n nodes. It also addsindex actionsfor managing and retrieving from indexes, and incorporates fixes from the n8n verification review (linting, packaging, and class-naming corrections).

Install the node on your n8n instance

In order to install the LlamaParse Platform node, open a new n8n workflow canvas, and typeLlamaParse Platformin the node search bar: once the node appears among the search results, click on it and then onInstall node. Verify and manage the installation fromSettings → Community nodes.

## Example workflows

To use the LlamaParse integration, add aLlamaParse APIcredential (paste your key fromcloud.llamaindex.ai; base URL defaults tohttps://api\.cloud\.llamaindex\.ai) and drop the node onto the canvas.

1. Retrievers as agent tools

Because the node isusableAsTool: true, retrieval resources can be wired directly into an AI Agent’s tool list:

The agent decides whether to call the retriever tool based on the user’s query. For instance, if a user asks a domain-specific question that requires context not currently available to the agent, the agent can retrieve the relevant information from the Index. The agent invokes the tool, receives retrieved chunks back and reasons over them in the same turn: just like that, you have plugged in an agent into your own knowledge base, and you can easily expand it with more tools and connections.

A document-processing pipeline that turns raw files into structured, verified output:

Classifyroutes each document to the right branch (in the example,invoicevs.contract),Extractpulls structured fields using a schema tuned for that type, and anLLM nodeverifies the correctness of the extracted data based on theparsed contentof the file. In addition to what is shown in the example, theconfidencefield from Classify could be a convenient gate for sending low-confidence documents to a manual-review branch.

3. Evaluate Parsed Outputs

Evaluate parsed outputs with different parsing modes:

Chain Parse in Agentic and a Cost Effective mode, then pass the input file through both parsers and collect the results into an LLM prompt that looks like this:

<agentic_tier>
{agentic output}
</agentic_tier>
<cost_effective_tier>
{cost effectie output}
</cost_effective_tier>
<task>
Determine which tier has produced the highest-quality result
</task>

Finally, represent the LLM-as-a-judge verdict as a structured output you can use for evaluation: this is particularly relevant if you are trying to find the best balance between accuracy and latency for your documents.

Get started

You can get started now with the LlamaParse Platform node, by using it directly in the n8n platform or by checking out:

• the Documentation:developers.llamaindex.ai/llamaparse/integrations/n8n
• the GitHub repository:github.com/run-llama/n8n-llamacloud
• the npm package:@llamaindex/n8n-nodes-llamacloud
• the LlamaParse Platform:cloud.llamaindex.ai

LlamaIndex 🦙 (@llama_index): The @n8n_io node for the LlamaParse Platform is now an officially verified community node, as part of a broader partnership with n8n to bring cutting-edge document intelligence to the low-code and no-code world🚀

The new version of the node brings together document parsing,