Together Embedder

Generate 1024-dimensional embeddings with Together’s current multilingual E5 model through its OpenAI-compatible API.

Pass a current Together model and its matching dimensions explicitly. TogetherEmbedder reads TOGETHER_API_KEY and calls Together through the OpenAI SDK.

The Agno v2.7.2 default, togethercomputer/m2-bert-80M-32k-retrieval, was removed on February 6, 2026. Together’s current serverless catalog lists intfloat/multilingual-e5-large-instruct with 1024 dimensions. See Together deprecations and serverless models.

together_embedder.py

from agno.knowledge.embedder.together import TogetherEmbedder

embedder = TogetherEmbedder(
    id="intfloat/multilingual-e5-large-instruct",
    dimensions=1024,
)
embedding = embedder.get_embedding("The quick brown fox jumps over the lazy dog.")

print(embedding[:5])
print(len(embedding))

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Export the API key

   export TOGETHER_API_KEY=your_together_api_key_here
   
3. Install dependencies

   uv pip install -U agno openai
   
4. Run the example

   python together_embedder.py
   

Developer Resources

• TogetherEmbedder reference
• Together embeddings
• Embedders overview