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 Hello, We are having issues with SQL, most likely with the table **[dbo].[KMMemories]**. It's hard to perform any operations on it. Retrieving a large number of...
### Context / Scenario Every time I upload a new file with ImportDocumentAsync, the collection is recreated and everything in it is cleared out, making it kind of useless. I've...
### Context / Scenario In my application, I have provided users a web page to upload and delete documents. For delete functionality, I calling KM's DeleteDocumentAsync() method by passing it...
### Context / Scenario When calling `MemoryWebClient.SearchSummariesAsync` with `PipelineOnlySummary`, the value of `results[0].partitions[0].relevance` in the `answer` object becomes `-Infinity`. The relevance value is: -1.7976931348623157E+308 ### Error Message ``` [15:45:16.251] trce:...
### Context / Scenario This is where the NormalizeNewlines() call is needed. https://github.com/microsoft/kernel-memory/blob/508ac0b1236a6f4700c093909282e8c83a385c97/service/Core/DataFormats/Text/TextDecoder.cs#L46 https://github.com/microsoft/kernel-memory/blob/508ac0b1236a6f4700c093909282e8c83a385c97/service/Core/DataFormats/Text/TextDecoder.cs#L60 https://github.com/microsoft/kernel-memory/blob/508ac0b1236a6f4700c093909282e8c83a385c97/service/Core/DataFormats/Text/MarkDownDecoder.cs#L43 https://github.com/microsoft/kernel-memory/blob/508ac0b1236a6f4700c093909282e8c83a385c97/service/Core/DataFormats/Text/MarkDownDecoder.cs#L57
### Context / Scenario **Steps to reproduce:** 1. Set-up Kernel Memory locally with Swagger 2. Configure it to use AI Search 3. Import a larger file (size >200 kb -...
### Context / Scenario When using Chinese markdown file, GetTokens function returns incorrectly. CL100KTokenizer cL100KTokenizer=new CL100KTokenizer(); var result= cL100KTokenizer.GetTokens("交通运输部关于发布《公路桥涵设计通用规范》的公告\r\n现发布《公路桥涵设计通用规范》（JTG D60-2015），作为公路工程行业标准，自 2015 年 12 月 1 日起施行，原《公路桥涵设计通用规范》（JTG D60-2004）同时废止。"); ### What happened?...
There is no need to remove spaces here, they are needed if they remain after the decoder. https://github.com/microsoft/kernel-memory/blob/1c424ed35738342ea2b3f8cae4091cb649071c49/service/Core/Handlers/TextExtractionHandler.cs#L220 It can be a PDF where the sentence goes to the next...
## Motivation and Context (Why the change? What's the scenario?) * Include page number information in Text Partition. ## High level description (Approach, Design) * Implement by the simple way...
### Context / Scenario When processing a large Chinese document (in Markdown format, around 100 KB), the Chunker introduced in version 0.97.250211.1 starts duplicating certain Chinese characters right after a...
