Text Embedding 005
Text Embedding 005 is Google's latest text embedding model, delivering state-of-the-art retrieval quality with support for multiple task types. It produces embeddings optimized for specific retrieval scenarios — semantic similarity, classification, clustering, and question-answering — by accepting a task type parameter.
This task-aware embedding approach ensures optimal vector representations for each use case, improving retrieval precision compared to one-size-fits-all embedding models.
Key Features
Task-aware embeddings (retrieval, similarity, classification, clustering)
768-dimensional output vectors
Strong multilingual performance
Optimized for Google Cloud AI Platform
High retrieval precision across benchmarks
Ideal Use Cases
Semantic search with task-optimized embeddings
Document classification and clustering
Question-answering retrieval pipelines
Google Cloud-native RAG applications
Technical Specifications
| Dimensions | 768 |
| Modality | Text → Embedding |
| Provider | |
| Category | Embedding |
| Task Types | Retrieval, Similarity, Classification, Clustering |
API Usage
1 curl -X POST https://api.vincony.com/v1/chat/completions \ 2 -H "Authorization: Bearer YOUR_API_KEY" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "model": "google/text-embedding-005", 6 "messages": [ 7 { "role": "user", "content": "Hello, Text Embedding 005!" } 8 ] 9 }'
Replace YOUR_API_KEY with your Vincony API key. OpenAI-compatible endpoint — works with any OpenAI SDK.
Compare with Another Model
Frequently Asked Questions
Try Text Embedding 005 now
Start using Text Embedding 005 instantly — 100 free credits, no credit card required. Access 343+ AI models through one platform.
More from Google
Use ← → to navigate between models · Esc to go back