LLM Embeddings

Convert text into a vector embedding for search, similarity, or retrieval workflows.

Audience

Creators building workflows and buyers checking provider requirements.

Overview#

LLM Embeddings turns text into a numeric vector using OpenAI embedding models. The output is infrastructure data, not something customers read directly.

Use it inside larger workflows for semantic search, memory, indexing, or comparing how similar two pieces of text are.

LLM Embeddings

Ports#

Input: Text: The string to embed, from connected upstream content or fallback text in the inspector.
Output: Embedding: An array-like vector for downstream similarity or storage steps.

Inspector#

Text (fallback): Used when the Text input is not connected.
Model: Default small model is cheap and strong for most retrieval jobs; large model suits premium memory workflows.

Tips#

Feed clean, meaningful text; low-quality input produces weak vectors.
Keep this block inside the graph; pair it with Workflow Output only if customers need to see raw vectors.
Do not confuse embeddings with visible copy from LLM Chat.
Credential requirements come from the listing mode: Edgaze-hosted uses no buyer key, creator-connected uses the creator's Vault key, and buyer-BYOK requires the buyer's OpenAI Vault key and Plus.

Workflow Studio

Was this useful?

Your response helps us improve the documentation.

More blocks

Workflow Input

Ask the customer one clear question and turn their answer into data your workflow can use.

Workflow Form

Collect several run-modal fields in one grouped form, each with a stable key for downstream steps.

Workflow Output

Define what the customer receives when the workflow finishes.

Block reference

LLM Embeddings

Convert text into a vector embedding for search, similarity, or retrieval workflows.

Audience

Creators building workflows and buyers checking provider requirements.

Overview#

LLM Embeddings turns text into a numeric vector using OpenAI embedding models. The output is infrastructure data, not something customers read directly.

Use it inside larger workflows for semantic search, memory, indexing, or comparing how similar two pieces of text are.

LLM Embeddings

Ports#

Input: Text: The string to embed, from connected upstream content or fallback text in the inspector.
Output: Embedding: An array-like vector for downstream similarity or storage steps.

Inspector#

Text (fallback): Used when the Text input is not connected.
Model: Default small model is cheap and strong for most retrieval jobs; large model suits premium memory workflows.

Tips#

Feed clean, meaningful text; low-quality input produces weak vectors.
Keep this block inside the graph; pair it with Workflow Output only if customers need to see raw vectors.
Do not confuse embeddings with visible copy from LLM Chat.
Credential requirements come from the listing mode: Edgaze-hosted uses no buyer key, creator-connected uses the creator's Vault key, and buyer-BYOK requires the buyer's OpenAI Vault key and Plus.