Models
Embedding Models
Text embedding models for semantic search and similarity
Embedding Models
Create vector representations of text for semantic search, clustering, recommendations, and RAG applications with Assisters Embed, our multilingual embedding model.
Assisters Embed v1
Model IDstringassisters-embed-v1
Our state-of-the-art multilingual embedding model supporting 100+ languages with industry-leading performance.
| Specification | Value |
|---|---|
| Model ID | assisters-embed-v1 |
| Dimensions | 1024 |
| Max Tokens | 8,192 |
| Input Price | $0.01 / million tokens |
| Similarity Metric | Cosine |
Capabilities
- Multilingual: Native support for 100+ languages
- Long Context: Process up to 8,192 tokens per request
- High Quality: State-of-the-art performance on MTEB benchmark
- Cross-lingual: Match queries and documents across languages
- Versatile: Optimized for search, clustering, and classification
Example Usage
from openai import OpenAI
client = OpenAI(
base_url="https://api.assisters.dev/v1",
api_key="your-api-key"
)
response = client.embeddings.create(
model="assisters-embed-v1",
input="The quick brown fox jumps over the lazy dog"
)
# Returns 1024-dimensional vector
print(f"Dimensions: {len(response.data[0].embedding)}")Batch Embedding
# Embed multiple texts in one request for better throughput
texts = [
"First document to embed",
"Second document to embed",
"Third document to embed"
]
response = client.embeddings.create(
model="assisters-embed-v1",
input=texts
)
# Access each embedding
for i, embedding in enumerate(response.data):
print(f"Text {i}: {len(embedding.embedding)} dimensions")Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
input | string/array | required | Text(s) to embed |
model | string | required | Model ID (assisters-embed-v1) |
encoding_format | string | "float" | Output format: "float" or "base64" |
Use Cases
Best Practices
Batch Requests
Embed multiple texts in one request for better throughput
Cache Embeddings
Store embeddings to avoid recomputing for the same text
Normalize Vectors
Our model outputs normalized vectors; verify for your use case
Match Query/Doc Models
Always use the same model for queries and documents
Vector Databases
Store and search embeddings efficiently:
| Database | Type | Features |
|---|---|---|
| Pinecone | Managed | Fast, scalable, serverless |
| Weaviate | Self-hosted | Open-source, hybrid search |
| Qdrant | Self-hosted | Rust-based, efficient |
| Milvus | Self-hosted | Distributed, GPU support |
| pgvector | Extension | PostgreSQL integration |
| Supabase | Managed | PostgreSQL with pgvector built-in |