kernel-memory
kernel-memory copied to clipboard
microsoft
RAG architecture: index and query any data using LLM and natural language, track sources, show citations, asynchronous memory patterns.
### Context / Scenario The ability to configure KernelMemory using appsettings.json is great, but I think it could be improved. ### The problem Currently, the `FromAppSettings` extension method is available...
### Context / Scenario I am running the service directly from VS Code. I have created an appsettings.Developmnet.json file with the desired configuration. When I upload a document the pipeline...
I'd like to be able to opt-in enable OCRing PDF documents. I understand that tesseract doesn't support this, but Form Recognizer does.
### Context / Scenario The `MemoryWebClient` class is _mostly_ a wrapper around `HttpClient` in .NET, but it doesn't follow the pattern of a [Typed HttpClient](https://learn.microsoft.com/dotnet/core/extensions/httpclient-factory#typed-clients), which means that it's difficult...
### Context / Scenario When I was using Kernel Memory, I found that there was no interface to retrieve the document collection based on the index, which made it impossible...
### Context / Scenario I have a scenario where my entry point is **FunctionCallingStepwisePlanner**. I added some plugins with native functions for mathematic calculates and the plugin **TextMemoryPlugin**. My memory...
### Context / Scenario When using Kernel Memory, whether it is Import or Ask, I hope to increase the consumption of returning tokens, so that I can analyze the cost...
### Context / Scenario We are building a chat bot and would like to use Kernel Memory to allow users to ask questions. How can we implement a short term...
SQL Server works fine as a memory source to store vector embeddings. It is the most cost effective method. See: [Azure OpenAI RAG Pattern using a SQL Vector Database](https://blazorhelpwebsite.com/ViewBlogPost/10067)
### Context / Scenario Using Azure AI Search for our embeddings. I'm storing custom tags for uploaded documents, and they appear properly in the Azure AI Search Index. ### Question...