POST/v1/embeddings

Embeddings

Create vector embeddings for semantic search, similarity detection, and RAG applications. Returns dense vectors that capture the semantic meaning of your text.

Request

Example Request

curl https://api.assisters.dev/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bge-large-en",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Parameters

modelrequiredstring

ID of the embedding model to use.

Available models:

bge-large-en - High quality English embeddings (1024 dimensions)
bge-base-en - Balanced performance/speed (768 dimensions)
all-minilm-l6 - Fast, lightweight (384 dimensions)
multilingual-e5 - 100+ languages support (768 dimensions)

inputrequiredstring | array

Text to embed. Can be a single string or array of strings for batch processing. Maximum 8192 tokens per input string.

encoding_formatoptionalstringdefault: float

Format for the embeddings. float for full precision, base64 for compressed.

Response

Example Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.0023, -0.0094, 0.0152, ...],
      "index": 0
    }
  ],
  "model": "bge-large-en",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

Use Cases

Semantic Search

Find documents with similar meaning, not just matching keywords.

RAG Applications

Retrieve relevant context for LLM responses from your knowledge base.

Recommendations

Find similar products, articles, or content based on embeddings.

Duplicate Detection

Identify near-duplicate content even with different wording.

Code Examples

Python

embeddings.py

from assisters import Assisters

client = Assisters(api_key="YOUR_API_KEY")

# Single embedding
response = client.embeddings.create(
    model="bge-large-en",
    input="What is machine learning?"
)

embedding = response.data[0].embedding
print(f"Embedding dimension: {len(embedding)}")

# Batch embeddings
texts = ["First document", "Second document", "Third document"]
response = client.embeddings.create(
    model="bge-large-en",
    input=texts
)

for i, data in enumerate(response.data):
    print(f"Document {i}: {len(data.embedding)} dimensions")