Ollama Embeddor
Local Embeddings
Overview
Generate embeddings using Ollama's local models. Run embeddings locally with no cloud dependencies, perfect for privacy-focused and offline applications.
Popular Models
- llama2
- nomic-embed-text
- mistral
- codellama
Key Features
- Local processing
- No API keys needed
- Custom model support
- Offline capability
Configuration
Required Parameters
ollamaModelName of the Ollama model
Optional Parameters
ollamaBaseUrlDefault: http://localhost:11434
Example Usage
// Basic configuration with default base URL
const embedder = new OllamaEmbeddor({
ollamaModel: "nomic-embed-text"
});
// Custom base URL configuration
const customEmbedder = new OllamaEmbeddor({
ollamaModel: "llama2",
ollamaBaseUrl: "http://your-ollama-server:11434"
});
// Generate embeddings
const result = await embedder.embed({
input: "Your text to embed"
});
// Batch processing
const batchResult = await embedder.embedBatch({
inputs: [
"First text to embed",
"Second text to embed"
]
});Best Practices
- Choose appropriate model size
- Monitor system resources
- Cache frequent embeddings
- Implement error handling
Performance Tips
- Use GPU acceleration if available
- Batch similar length texts
- Pre-download models
Response Format
{
"embeddings": {
"vectors": number[][],
"dimensions": number,
"model": string
},
"metadata": {
"model_name": string,
"processing_time": number,
"total_tokens": number
},
"status": {
"success": boolean,
"error": string | null
}
}