Octen AI
AI-native web search and retrieval API for LLM agents: real-time search, URL extract, embeddings, web-augmented chat, and deep research
Three ways to use Octen AI
Ask your specialist
Pull data, take actions, or answer questions with this integration, right in a conversation.
Build a workflow
Create automated workflows that trigger on events, run on a schedule, or chain multiple tools together.
Power an app
Use this integration as a data source or action layer behind a dashboard, form, or internal tool.
Supported tools
Actions your AI agents can perform with Octen AI.
Broad Search
Decompose a question into sub-queries, run them in parallel, and synthesize a unified answer
Create Multimodal (VL) Embeddings
Embed mixed text, image, and video inputs into a unified vector space; optionally fuse multiple elements into one vector
Create Text Embeddings
Embed a batch of text inputs into dense vectors using an Octen embedding model
Deep Research
Multi-round adaptive research pipeline that produces a structured report; supports a two-phase plan-confirmation flow
Extract
Batch-fetch up to 20 URLs and return clean markdown content with optional highlights, page structure, and media
Search
Run a ranked web search with optional domain/text/time filters, highlights, and full-page content extraction