Abby Harrison

TextMemorySkill: Recall Can Return Many Memories, added Keyed Lookup Functions Retrieve() and Remove()

4

### Motivation and Context Currently, TextMemorySkill `Recall` only returns the most relevant memory despite being reliant on methods that support returning N relevant memories. Additionally, users should be able to...

Remove kernel builder pattern for Python: sk.kernel_create() -> sk.Kernel()

1

### Motivation and Context This PR makes creating a kernel instance more pythonic. The builder pattern is removed and the kernel is constructed using Kernel(...). Work originally started with #137...

### Motivation and Context This PR fixes the text that gets embedded for remembering planner functions and clarifies the parameters being passed to SaveInformationAsync() ### Description - text to embed...

### Motivation and Context It is confusing to have multiple skfunction invoke_* calls. This PR combines invoke and invoke_with_vars to enable calls with the input pattern: with SKContext, or with...

### Motivation and Context A previous PR enabled a `withEmbedding` for all memory get/search methods, but this did not bubble up the embedding through `SemanticTextMemory.` By default, `SemanticTextMemory` will not...

### Motivation and Context This PR is a consistency update between the Python and .NET Semantic Kernels. **This PR does not contain any feature enhancements or improvements!** ### Description -...

### Motivation and Context Users want to use ChatGPT as the service for their semantic functions. This feature exists with the C# SK. ChatGPT is perfectly capable of doing this....

### Motivation and Context This PR introduces native python support for Hugging Face models that can: complete text, generate new text, summarize, and that generate embeddings. Currently only supports downloading...

Default minrelevancescore to zero

3

### Motivation and Context A default minRelevanceThreshold of 0.7 works well with OpenAI's ada embeddings generation, but not necessarily with other models. It also is likely to return no results...

### Motivation and Context The separation of Kernel, KernelBase, and KernelExtensions is several layers of unnecessary abstraction. This PR does not change any API or kernel behavior - it just...