spring-ai

spring-ai copied to clipboard

Investigate Streaming support across all currently supported model providers

1

Implement streaming support where possible for all supported model providers.

markpollack

ResourceReader to get list of documents from a resource

3

Fix #221

Omkar-Shetkar

[#208](https://github.com/spring-projects/spring-ai/issues/208) Review capitalization of enumeration names

Abhishake63

Provide prompt options on a call by call basis

3

Our local OpenAI endpoint has a very small default max_tokens against the chat completion. We like to make it adjustable **Expected Behavior** Hoping this code. https://github.com/spring-projects-experimental/spring-ai/blob/main/spring-ai-openai/src/main/java/org/springframework/ai/openai/client/OpenAiClient.java Looks something like this...

mhoshi-vm

This will facilitate loading a list of `Resource`s into a vector database inside a loop. Currently this requires recreating `TextReader` instances.

markpollack

also look into adding a model package. Then move messages package should move to beneath model package.

markpollack

markpollack

https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/customization_guide/inference_protocols.html

markpollack

Currently at beta6, should aim for including GA release for a 1.0.0 release

markpollack

See https://github.com/milvus-io/milvus-sdk-java/issues/704

markpollack