POST
https://api.morphllm.com
/
v1
/
embeddings
curl --request POST \
  --url https://api.morphllm.com/v1/embeddings \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "morph-embedding-v2",
  "input": "function calculateSum(a, b) { return a + b; }",
  "encoding_format": "float"
}'
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.0023064255,
        -0.009327292,
        0.01183665
      ],
      "index": 0
    }
  ],
  "model": "morph-embedding-v2",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

​
Overview

Morph provides an OpenAI-compatible API for generating embeddings from code and text. Morph embeddings are optimized to be state of the art for code, and are specifically made to be used on functional units like Syntax Tree Nodes (functions, classes, etc.) - not every N tokens. Use this in the Morph SDK to detect when files change, Syntax Tree parse, and re-embed automatically.

​
API Endpoint

POST https://api.morphllm.com/v1/embeddings

​
Example Request

import { OpenAI } from 'openai';

const client = new OpenAI({
  apiKey: 'your-morph-api-key',
  baseURL: 'https://api.morphllm.com/v1'
});

async function generateEmbeddings() {
  const response = await client.embeddings.create({
    model: "morph-embedding-v2",
    input: "function calculateSum(a, b) { return a + b; }"
  });
  
  return response.data[0].embedding;
}

​
Input Format

The request accepts the following parameters:

ParameterTypeRequiredDescription
modelstringYesThe model ID to use for embedding generation. Use morph-embedding-v2.
inputstring or arrayYesThe text to generate embeddings for. Can be a string or an array of strings.
encoding_formatstringNoThe format in which the embeddings are returned. Options are float and base64. Default is float.

​
Batch Processing Example

from openai import OpenAI

client = OpenAI(
    api_key="your-morph-api-key",
    base_url="https://api.morphllm.com/v1"
)

# Example with batch inputs
code_snippets = [
    "function add(a, b) { return a + b; }",
    "class User { constructor(name) { this.name = name; } }",
    "import pandas as pd\ndf = pd.read_csv('data.csv')"
]

response = client.embeddings.create(
    model="morph-embedding-v2",
    input=code_snippets
)

# Access embeddings for each input
for i, embedding_data in enumerate(response.data):
    embedding = embedding_data.embedding
    print(f"Embedding for snippet {i+1}: {len(embedding)} dimensions")

​
cURL Example

curl --request POST \
  --url https://api.morphllm.com/v1/embeddings \
  --header 'Authorization: Bearer your-morph-api-key' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "morph-embedding-v2",
    "input": "function calculateSum(a, b) { return a + b; }"
  }'

​
Response Format

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.0023064255, -0.009327292, ...],
      "index": 0
    }
  ],
  "model": "morph-embedding-v2",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

When multiple inputs are provided, the response includes embeddings for each input:

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.0023064255, -0.009327292, ...],
      "index": 0
    },
    {
      "object": "embedding",
      "embedding": [0.0103662554, -0.007650322, ...],
      "index": 1
    },
    {
      "object": "embedding",
      "embedding": [0.0183664255, -0.002327742, ...],
      "index": 2
    }
  ],
  "model": "morph-embedding-v2",
  "usage": {
    "prompt_tokens": 24,
    "total_tokens": 24
  }
}

​
Usage with Vector Databases

Embeddings can be stored in vector databases for efficient similarity searching:

# Example with Pinecone
import pinecone
from openai import OpenAI

# Initialize clients
openai_client = OpenAI(
    api_key="your-morph-api-key",
    base_url="https://api.morphllm.com/v1"
)
pinecone.init(api_key="your-pinecone-api-key", environment="your-environment")
index = pinecone.Index("code-embeddings")

# Generate embedding for a code snippet
code_snippet = "def calculate_factorial(n):\n    if n == 0:\n        return 1\n    else:\n        return n * calculate_factorial(n-1)"
response = openai_client.embeddings.create(
    model="morph-embedding-v2",
    input=code_snippet
)
embedding = response.data[0].embedding

# Store in Pinecone
index.upsert([
    ("snippet-1", embedding, {"snippet": code_snippet})
])

# Search for similar code
results = index.query(
    vector=embedding,
    top_k=5,
    include_metadata=True
)

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Embedding generation request

The body is of type object.

Response

200
application/json

Embedding response

The response is of type object.