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
Example Prompts for Text Embedding 005
Technical Specifications
| Dimensions | 768 |
| Modality | Text → Embedding |
| Provider | |
| Category | Embedding |
| Task Types | Retrieval, Similarity, Classification, Clustering |
Frequently Asked Questions
Try Text Embedding 005 now
Start using Text Embedding 005 instantly — 100 free credits, no credit card required. Access 750+ AI models through one platform.