AI Orchestration

Orkes Conductor provides features to build applications that use AI models and vector databases in workflows. These applications can range from simple AI-powered tasks to agentic workflows where decisions are made dynamically based on model output.

Key features include:

• AI Tasks: Use predefined system tasks to generate text, create embeddings, and retrieve results from vector databases.
• AI/LLM and Vector Database Integrations: Connect to multiple AI models and vector databases in a secure, governed way.
• AI Prompt Studio: Create, refine, test, and govern prompt templates for AI models.

You can use these features to build:

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

Orchestrating AI-powered tasks

Orkes Conductor provides a variety of AI tasks that can execute common logic without the need to write code. Unlike Worker tasks, AI tasks are system tasks that are executed directly by Orkes Conductor and do not require you to deploy or run a worker process. Depending on the task type, these tasks may require an AI/LLM integration, a vector database integration, or an AI prompt.

AI Task	Description	Prerequisites
LLM Text Complete	Generate text from an LLM based on a defined prompt.	Integrate an AI model Create an AI prompt
LLM Generate Embeddings	Generate text embeddings.	Integrate an AI model
LLM Store Embeddings	Store text embeddings in a vector database.	Integrate an AI model Integrate a vector database
LLM Get Embeddings	Retrieve data from a vector database.	Integrate a vector database
LLM Index Document	Chunk, generate, and store text embeddings in a vector database.	Integrate an AI model Integrate a vector database
LLM Get Document	Retrieve text or JSON content from a URL.	NA
LLM Index Text	Generate and store text embeddings in a vector database.	Integrate an AI model Integrate a vector database
LLM Search Index	Retrieve data from a vector database based on a search query.	Integrate an AI model Integrate a vector database
LLM Chat Complete	Generate text from an LLM based on a user query and additional system/assistant instructions.	Integrate an AI model Create an AI prompt (Optional)
Chunk Text	Divide text into smaller segments (chunks) based on the document type.	NA
List Files	Retrieve files from a specific storage location.	Integrate cloud providers for private files
Parse Document	Retrieves, parses, and chunk documents from various storage locations.	Integrate cloud providers for private files

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

Learn more

📄️ Using AI Models or LLMs

Learn how to integrate AI models and use LLM system tasks in workflows, including configuring models, prompt templates, and access control.

📄️ Using Vector Databases

Learn how to integrate vector databases and use them with AI tasks to store and retrieve embeddings in workflows.

📄️ Using AI Prompts

Learn how to create and manage prompt templates with variables and reuse them in AI tasks across workflows.