- DATA
- SEARCH
- INDEX
- HUMAN
Short answer
How can I turn text into vectors using my AI?
Your AI uses the Together AI MCP to transform text into high-dimensional numerical arrays. This prepares your data for vector databases and semantic search. You'll get the exact arrays you need for indexing.
The outcomes
Where your data lands.
This process converts plain text into a format your database can actually use.
DATA
Numerical arrays
The AI converts your text into dense vectors. You get the specific arrays required for your vector store.
SEARCH
Semantic readiness
The embeddings capture the meaning of your text. This makes your content ready for similarity-based retrieval.
INDEX
Database preparation
The AI formats the vectors for easy insertion. You'll have the math ready to push into your database.
HUMAN
Content selection
You decide which specific text chunks are worth vectorizing. The AI won't choose the data for you.
The workflow
What your AI does when text arrives.
The AI handles the heavy math so you don't have to run local embedding models.
Input text
Your agent takes the raw text or documents you provide and prepares them for processing.
generate_embeddingsVectorize
The AI calls the embedding model to turn those text chunks into numerical arrays.
generate_embeddingsFormat
The resulting vectors are structured to be compatible with standard vector databases.
generate_embeddingsOutput
The AI hands the numerical arrays back to you for storage in your vector store.
generate_embeddings
Try it
Copy these to start.
Use these prompts to trigger the embedding process.
Starting points
Replace the bracketed text with your actual content or file names.
Together AI Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_uwxFbBTrWtpKdtNP0Ee38Zmxxir6fie6FBKXtn0o/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Together AI capabilities are ready to use.
{
"mcpServers": {
"together-ai-mcp": {
"url": "https://edge.vinkius.com/vk_preview_uwxFbBTrWtpKdtNP0Ee38Zmxxir6fie6FBKXtn0o/mcp"
}
}
}Generate embeddings for this paragraph: [paste text here]
Convert the contents of my 'customer_feedback.txt' file into vectors.
Create embeddings for these three product descriptions: [list descriptions]
Turn this list of user queries into numerical arrays for my database.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Together AI once, then ask.
Link your account once and your credentials stay encrypted on our side. You can then start embedding text through your preferred AI client.
Connect Together AI to your AIFAQ
How this task behaves
- 01
Can the AI embed an entire website at once?
No. You need to provide the specific text or document chunks you want to vectorize.
- 02
Will the AI automatically update my vector database?
No. The AI generates the embeddings, but you are responsible for inserting them into your database.
- 03
What kind of data can I embed?
Any raw text you provide can be turned into a vector.
- 04
Does the AI choose the embedding model?
The AI uses the models provided by Together AI to perform the task.
- 05
Can I delete existing embeddings using this tool?
No. This tool is only for generating new embeddings from text.
More questions about Together AI? The Connector page answers them. See everything the Together AI Connector can do
Connect Together AI to Claude, Cursor, ChatGPT & more
