​
Overview

The Embedding API converts code and text into high-dimensional vectors that capture semantic meaning. These embeddings enable powerful search, clustering, and similarity operations for code-related applications.

​
Endpoint Reference

from openai import OpenAI

# Initialize the OpenAI client with Morph's API endpoint
client = OpenAI(
    api_key="your-morph-api-key",
    base_url="https://api.morphllm.com/v1"
)

def get_embeddings(text: str) -> list[float]:
    response = client.embeddings.create(
        model="morph-embedding-v2",
        input=text
    )
    return response.data[0].embedding

# Example: Get embeddings for code chunks
def embed_code_chunks(code_chunks: list[str]) -> list[dict]:
    results = []

    for chunk in code_chunks:
        embedding = get_embeddings(chunk)
        results.append({
            "text": chunk,
            "embedding": embedding
        })

    return results

# Store these embeddings in a vector database of your choice

​
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.

​
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
  }
}

​
Features

  • Code Optimized: Specially trained to understand programming languages and code semantics
  • High Dimensionality: Creates rich embeddings that capture nuanced relationships between code concepts
  • Language Support: Works with all major programming languages including Python, JavaScript, Java, Go, and more
  • Contextual Understanding: Captures semantic meanings rather than just syntactic similarities
  • Batch Processing: Efficiently processes multiple inputs in a single API call

​
Common Use Cases

  • Semantic Code Search: Create powerful code search systems that understand intent
  • Similar Code Detection: Find similar implementations or potential code duplications
  • Code Clustering: Group related code snippets for organization or analysis
  • Relevance Ranking: Rank code snippets by relevance to a query
  • Concept Tagging: Automatically tag code with relevant concepts or categories