Documentation

AI Providers

Configure your preferred AI provider for content analysis

Overview

WPLink needs an AI provider for two things:

  • Embeddings: Converting content into vectors for similarity search
  • Chat: Understanding content and finding link opportunities

Supported Providers

OpenAI

Recommended

Most reliable option with good accuracy

Embedding Models

text-embedding-3-small, text-embedding-3-large

Chat Models

gpt-4o, gpt-4o-mini

Pros

  • Good accuracy
  • Fast responses
  • Stable API

Considerations

  • Requires API key
  • Usage costs

Anthropic

Claude models with good context handling

Embedding Models

voyage-3 (via Voyage AI)

Chat Models

Claude Sonnet, Claude Haiku

Pros

  • Good at understanding context
  • Handles complex content

Considerations

  • Needs two API keys (Anthropic + Voyage AI)

Google Gemini

Google AI with competitive pricing

Embedding Models

text-embedding-004

Chat Models

gemini-2.0-flash, gemini-1.5-pro

Pros

  • Good price/performance
  • Fast embeddings

Considerations

  • Newer option

Ollama

Run AI models locally on your computer

Embedding Models

nomic-embed-text

Chat Models

llama3.2, mistral

Pros

  • No API costs
  • Data stays local
  • Works offline

Considerations

  • Needs good hardware
  • Slower than cloud
  • Lower accuracy

Setting Up a Provider

  1. 1

    Open Settings

    Click the gear icon in the sidebar

  2. 2

    Select a provider

    Click one of the provider cards (OpenAI, Anthropic, Gemini, or Ollama)

  3. 3

    Enter your API key

    Paste your key and click "Connect". This tests and saves the key in one step.

  4. 4

    Choose models (optional)

    After connecting, you can select specific embedding and chat models, then click "Save".

Anthropic note: Anthropic requires two keys: one for Claude (chat) and one for Voyage AI (embeddings).

Get API Keys

OpenAI

platform.openai.com

Anthropic

console.anthropic.com

Voyage AI

For Anthropic embeddings

Google Gemini

aistudio.google.com

Using Ollama (Local)

Ollama runs on your computer, so no API key is needed. Just:

  1. Install Ollama from ollama.com
  2. Run ollama pull llama3.2 and ollama pull nomic-embed-text
  3. Make sure Ollama is running (localhost:11434)
  4. Select Ollama in WPLink and click Connect