Mark Pollack

Remove README.md in pinecone source tree

1

It has already been moved into the reference docs.

Revisit package structure in light of multiple model data types

1

Currently we have the structure ``` org.sf.ai.chat org.sf.ai.prompt org.sf.ai.prompt.messages ``` This doesn't feel right for several reasons. First is that `message` package should not be under `prompt` as it is...

Create GenerativeTextTemplate that streamlines usage of AiClient, Prompts, and OutputParsers

1

There is an analogy to make between GenerationTemplate and JdbcTemplate that will help simplify the use of the lower level classes such as AiClient, Prompts, and OutputParsers. Note: AiClient should...

The prefix for these properties should be `spring.ai.openai.chat`, currently it is `spring.ai.openai` `OpenAIProperties` has options only for `temperature` and is missing options * frequency_penalty * logit_bias * logprobs * top_logprobs...

Investigate Streaming support across all currently supported model providers

1

Implement streaming support where possible for all supported model providers.

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

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

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

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