Skip to main content

AI Orchestration and Agentic Workflows

With the following suite of features, Orkes Conductor enables you to efficiently build AI-powered or agentic applications that leverage AI models and vector databases:

  • AI System Tasks—Use predefined tasks such as storing embeddings or generating chat completions.
  • AI/LLM and Vector Database Integrations—Connect to multiple AI models and vector databases in a secure, governed way.
  • AI Prompt Studio—Refine, test, and govern prompt templates for AI models.

Some common AI use cases include:

  • AI agents or agentic workflows
  • RAG (retrieval augmented generation) systems
  • LLM-powered chatbots
  • AI classifiers

Orchestrating AI-powered tasks

Orkes Conductor provides a variety of system AI tasks that can execute common logic without the need to write code. Depending on the type of task, using these tasks may require an AI/LLM integration, a vector database integration, or an AI prompt.

System AI TaskDescriptionPrerequisites
LLM Get DocumentRetrieve text or JSON content from a URL.NA
LLM Generate EmbeddingsGenerate text embeddings.
  • Integrate an AI model
LLM Store EmbeddingsStore text embeddings in a vector database.
  • Integrate an AI model
  • Integrate a vector database
LLM Index TextGenerate and store text embeddings in a vector database.
  • Integrate an AI model
  • Integrate a vector database
LLM Index DocumentChunk, generate, and store text embeddings in a vector database.
  • Integrate an AI model
  • Integrate a vector database
LLM Get EmbeddingsRetrieve data from a vector database.
  • Integrate a vector database
LLM Search IndexRetrieve data from a vector database based on a search query.
  • Integrate an AI model
  • Integrate a vector database
LLM Text CompleteGenerate text from an LLM based on a defined prompt.
  • Integrate an AI model
  • Create an AI prompt
LLM Chat CompleteGenerate text from an LLM based on a user query and additional system/assistant instructions.
  • Integrate an AI model
  • Create an AI prompt

If custom logic is required, you can create an external worker instead of using the system AI tasks. For more details, refer to the guide on Writing Workers.

Once you have decided which task to use, check out the following guides to begin building AI-powered or agentic applications.

Learn more