Skip to main content

/embeddings

Quick Start​

Python​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.embeddings.create(
    model="openai/text-embedding-ada-002",
    input=["good morning from haimaker"]
)

print(response.data[0].embedding)

cURL​

curl https://api.haimaker.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/text-embedding-ada-002",
    "input": ["good morning from haimaker"]
  }'

Async Usage​

from openai import AsyncOpenAI
import asyncio

client = AsyncOpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

async def get_embedding():
    response = await client.embeddings.create(
        model="openai/text-embedding-ada-002",
        input=["good morning from haimaker"]
    )
    return response

response = asyncio.run(get_embedding())
print(response.data[0].embedding)

Supported Models​

OpenAI Embedding Models​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

# text-embedding-3-small
response = client.embeddings.create(
    model="openai/text-embedding-3-small",
    input=["good morning from haimaker"],
    dimensions=256  # Optional: specify dimensions for text-embedding-3 models
)

# text-embedding-3-large
response = client.embeddings.create(
    model="openai/text-embedding-3-large",
    input=["good morning from haimaker"]
)

# text-embedding-ada-002
response = client.embeddings.create(
    model="openai/text-embedding-ada-002",
    input=["good morning from haimaker"]
)
Model NameModel ID
text-embedding-3-smallopenai/text-embedding-3-small
text-embedding-3-largeopenai/text-embedding-3-large
text-embedding-ada-002openai/text-embedding-ada-002

Cohere Embedding Models​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.embeddings.create(
    model="cohere/embed-english-v3.0",
    input=["good morning from haimaker"]
)
Model NameModel ID
embed-english-v3.0cohere/embed-english-v3.0
embed-english-light-v3.0cohere/embed-english-light-v3.0
embed-multilingual-v3.0cohere/embed-multilingual-v3.0
embed-multilingual-light-v3.0cohere/embed-multilingual-light-v3.0
embed-english-v2.0cohere/embed-english-v2.0
embed-english-light-v2.0cohere/embed-english-light-v2.0
embed-multilingual-v2.0cohere/embed-multilingual-v2.0

Voyage AI Embedding Models​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.embeddings.create(
    model="voyage/voyage-01",
    input=["good morning from haimaker"]
)
Model NameModel ID
voyage-01voyage/voyage-01
voyage-lite-01voyage/voyage-lite-01
voyage-lite-01-instructvoyage/voyage-lite-01-instruct

Mistral AI Embedding Models​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.embeddings.create(
    model="mistral/mistral-embed",
    input=["good morning from haimaker"]
)
Model NameModel ID
mistral-embedmistral/mistral-embed

Google Gemini Embedding Models​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.embeddings.create(
    model="gemini/text-embedding-004",
    input=["good morning from haimaker"]
)
Model NameModel ID
text-embedding-004gemini/text-embedding-004

Vertex AI Embedding Models​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.embeddings.create(
    model="vertex_ai/textembedding-gecko",
    input=["good morning from haimaker"]
)
Model NameModel ID
textembedding-geckovertex_ai/textembedding-gecko
textembedding-gecko-multilingualvertex_ai/textembedding-gecko-multilingual
textembedding-gecko-multilingual@001vertex_ai/textembedding-gecko-multilingual@001
textembedding-gecko@001vertex_ai/textembedding-gecko@001
textembedding-gecko@003vertex_ai/textembedding-gecko@003
text-embedding-preview-0409vertex_ai/text-embedding-preview-0409
text-multilingual-embedding-preview-0409vertex_ai/text-multilingual-embedding-preview-0409

AWS Bedrock Embedding Models​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.embeddings.create(
    model="bedrock/amazon.titan-embed-text-v1",
    input=["good morning from haimaker"]
)
Model NameModel ID
Titan Embeddings - G1bedrock/amazon.titan-embed-text-v1
Cohere Embeddings - Englishbedrock/cohere.embed-english-v3
Cohere Embeddings - Multilingualbedrock/cohere.embed-multilingual-v3

HuggingFace Embedding Models​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.embeddings.create(
    model="huggingface/microsoft/codebert-base",
    input=["good morning from haimaker"]
)
Model NameModel ID
microsoft/codebert-basehuggingface/microsoft/codebert-base
BAAI/bge-large-zhhuggingface/BAAI/bge-large-zh

Input Parameters​

Required Fields​

  • model: string - ID of the model to use (e.g., openai/text-embedding-ada-002)
  • input: string or array - Input text to embed, encoded as a string or array of strings

Optional Fields​

  • dimensions: integer - The number of dimensions for the output embeddings. Only supported in text-embedding-3 and later models.
  • encoding_format: string - The format to return the embeddings in. Can be "float" or "base64". Defaults to "float".
  • user: string - A unique identifier representing your end-user.

Output Format​

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        -0.0022326677571982145,
        0.010749882087111473,
        ...
      ]
    }
  ],
  "model": "text-embedding-ada-002-v2",
  "usage": {
    "prompt_tokens": 10,
    "total_tokens": 10
  }
}