UpstageAI/n8n-nodes-upstage

UpstageAI/n8n-nodes-upstage

Description: Upstage LLM and Embeddings nodes for n8n

Language: TypeScript

License: MIT

Stars: 1

Forks: 1

Open issues: 5

Created: 2025-10-26T00:31:50Z

Pushed: 2026-03-24T03:06:44Z

Default branch: main

Fork: no

Archived: no

README:

n8n-nodes-upstage

Upstage Solar LLM and Embeddings nodes for n8n workflow automation. This package provides powerful AI capabilities including chat completions, embeddings generation, and document processing through n8n's visual workflow interface.

Features

• Solar Chat Models: Use Upstage's Solar LLM (solar-mini, solar-pro, solar-pro2) for chat completions
• Embeddings Generation: Create high-quality embeddings for semantic search and vector databases
• Document Processing: Parse, OCR, classify, and extract information from documents
• AI Agent Integration: Compatible nodes for n8n AI Agent and Vector Store workflows (no external dependencies)
• Secure Authentication: Simple API key-based authentication
• Batch Processing: Efficient batch processing for embeddings and document operations
• Flexible Input: Support for single text, batch processing, binary files, and URLs

Installation

Prerequisites

• n8n: Version 1.0.0 or later
• Node.js: Version 18.0.0 or later

Install via n8n UI (Recommended)

1. Enable Community Nodes (if not already enabled):

export N8N_COMMUNITY_NODES_ENABLED=true
n8n start

2. Install via n8n UI:

• Open n8n in your browser
• Navigate to Settings → Community Nodes
• Click Install a community node
• Enter: n8n-nodes-upstage
• Click Install

Install via npm (Alternative)

npm install n8n-nodes-upstage

Then enable community nodes and restart n8n:

export N8N_COMMUNITY_NODES_ENABLED=true
n8n start

Quick Start

1. Get Your API Key

1. Sign up at Upstage Console 2. Navigate to API Keys section 3. Create a new API key 4. Copy your API key

2. Configure Credentials in n8n

1. In n8n, go to Credentials → Create New 2. Search for "Upstage API" 3. Enter your API key 4. Click Test to verify the connection 5. Click Save

3. Use the Nodes

1. Create a new workflow in n8n 2. Click Add Node and search for "Upstage" 3. Select any Upstage node (e.g., "Upstage Solar Chat") 4. Configure the node with your credentials 5. Set up your workflow and execute!

Available Nodes

Basic Nodes

Upstage Solar Chat (LmChatUpstage)

Use Upstage Solar LLM models for chat completions with conversation support.

Supported Models:

• solar-mini - Fast and efficient for basic tasks
• solar-pro - Powerful model for complex tasks
• solar-pro2 - Latest and most advanced Solar model with JSON support

Key Features:

• Message-based conversation format (system, user, assistant roles)
• Configurable parameters: temperature, max tokens, top-p
• Streaming response support
• Response format options (solar-pro2 only):
• Text (default)
• JSON Object - Generate structured JSON responses
• JSON Schema - Generate JSON with custom schema for structured outputs
• Reasoning effort control
• Frequency and presence penalty
• Function calling support (tools)

Example Use Cases:

• Customer support chatbots
• Content generation
• Code generation and explanation
• Data extraction and analysis

Upstage Embed (EmbeddingsUpstage)

Generate high-quality embeddings using Solar embedding models for semantic search and similarity matching.

Supported Models:

• embedding-query - Optimized for search queries and questions
• embedding-passage - Optimized for documents and passages

Key Features:

• Single text or batch processing (up to 100 texts per request)
• Input from node parameters or previous node data
• High-dimensional vector outputs
• Token limits: Max 204,800 total tokens, 4,000 per text (optimal: under 512)

Example Use Cases:

• Semantic search
• Document similarity matching
• Clustering and classification
• Recommendation systems

Upstage Document Parse (DocumentParsingUpstage)

Convert documents into structured HTML/Markdown format with layout preservation.

Supported Models:

• document-parse - Recommended stable model
• document-parse-nightly - Latest experimental features

Key Features:

• Sync and async document processing
• Multiple output formats (HTML, Markdown, Text)
• OCR support with auto/force modes
• Chart recognition and table merging
• Base64 encoding for figures, tables, equations, charts
• Coordinate information inclusion

Supported Formats:

• Images: JPEG, PNG, BMP, TIFF, HEIC
• Documents: PDF, DOCX, PPTX, XLSX

Example Use Cases:

• Document digitization
• Content extraction from PDFs
• Table extraction and conversion
• Document structure analysis

Upstage Document OCR (DocumentOCRUpstage)

Extract text from document images and PDFs with high accuracy.

Supported Models:

• ocr - Recommended (always points to latest stable)
• ocr-250904 - Specific version

Key Features:

• Multiple OCR models
• Schema options (Upstage, Clova, Google)
• Page-level text extraction
• Confidence scores
• Multiple return modes (full, text, pages, words, confidence)

Supported Formats:

• Images: JPEG, PNG, BMP, TIFF, HEIC
• Documents: PDF, DOCX, PPTX, XLSX, HWP, HWPX

Example Use Cases:

• Text extraction from scanned documents
• Invoice and receipt processing
• Form data extraction
• Multi-language OCR

Upstage Information Extract (InformationExtractionUpstage)

Extract structured information from documents using custom JSON schemas.

Supported Models:

• information-extract - Recommended

Key Features:

• Custom JSON schema definition
• Form-based or raw JSON schema input
• Support for nested structures
• Schema generation mode
• Binary file or URL input

Example Use Cases:

• Invoice data extraction
• Resume parsing
• Contract analysis
• Form data extraction

Upstage Document Classify (DocumentClassificationUpstage)

Classify documents into predefined categories with confidence scores.

Supported Models:

• document-classify - Document classification model

Key Features:

• Custom category definitions
• Binary file or URL input
• Form-based or JSON schema input
• Confidence scores for classifications

Example Use Cases:

• Document type classification
• Spam detection
• Content categorization
• Quality control

AI Agent…