Loading content
The Chat Completions API exposes conversational endpoints for interacting with large language models and enables multi-turn dialogue, system/user roles and streaming responses. It simplifies integrating LLM-driven chat features into applications, but requires careful prompt design and safety controls.
Use this profile to understand the building block briefly, place it in the model, and open related building blocks.
Technical building block: can be automated, integrated, or operated.
Concrete cog in the system that works inside larger relationships.
The Chat Completions API is an interface for conversational LLM calls. It handles multi-turn dialogue with role control and can return responses as a stream.
The Chat Completions API is part of OpenAI's API surface and addresses the problem that LLM applications need a reliable way to represent conversation history, roles, and output control in a single request pattern. Instead of building dialog logic from scratch, developers can send an ordered message sequence and optionally process the reply as a stream.
Think of the API as a conversation record: for each turn, the application sends an ordered list of messages with roles. The model reads that history, produces the next reply, and can stream tokens incrementally. Context management, instructions, and safety boundaries remain the application's responsibility, not the model call alone.
A request consists of an ordered sequence of messages rather than a single prompt.
System, user, and assistant roles define what each message does in the dialogue.
Only a limited portion of the prior conversation can be considered at once by the model.
Responses can arrive incrementally so the application can display or process them early.
Instructions, filters, and validation help limit misbehavior, data leakage, and unwanted output.
The API is useful when chat features, assistants, or support dialogs need to be embedded into existing applications. It fits multi-step interactions and live output well. Trade-offs include context limits, rising cost as history grows, and the extra work needed for prompt design, validation, and safeguards.
Where this building block is located in the topic model.
No structure path available.
Explore how this building block connects to concepts, methods, technologies, and tools.
These sources establish the term and its professional meaning.
All direct connections of the current building block in a compact text view.
This classification shows where the building block typically matters, how demanding it is, and what kind of impact it has in the model.
The level within the organization (enterprise, domain, team) at which the AssetBlock is applied.