Stream a chat completion from an inference endpoint
One step with Elastic Stack. We can help you get access.
Get something done
Stream a chat completion from an inference endpoint
with Elastic Stack · Artificial Intelligence Management
Use Elastic Stack: its Elasticsearch Request & Response Specification Inference API lets you stream a chat completion from an inference endpoint in a single step (POST /_inference/chat_completion/{inference_id}/_stream). capabilities.work can help you get signed up and connected.
- Can I stream a multi-turn chat conversation through an Elasticsearch chat_completion endpoint?
- Does the streaming chat API let me pass tools and a tool_choice to the model?
- What controls do I get over temperature and max completion tokens when streaming a chat reply?
Say it to your AI assistant
- Stream a chat reply from chat_completion endpoint {inference_id} for these messages: {messages}.
- Send {messages} to chat endpoint {inference_id} with temperature {temperature} and stream the answer back.
For your developer
POST /_inference/chat_completion/{inference_id}/_stream in Elasticsearch Request & Response Specification Inference API. Full spec on APIs.io.