From 6a7e74e71b15ce585aea06a35674da01ff81d84c Mon Sep 17 00:00:00 2001 From: Yaohui Liu Date: Sat, 4 Nov 2023 22:38:06 +0800 Subject: [PATCH 1/3] build: add package for kernel-memory integration. --- .../LLamaSharp.KernelMemory.csproj | 23 ++++++++++++++++++- .../LLamaSharp.SemanticKernel.csproj | 6 ++--- README.md | 9 +++++++- 3 files changed, 33 insertions(+), 5 deletions(-) diff --git a/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj b/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj index 54766b02..de5f42a5 100644 --- a/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj +++ b/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj @@ -1,9 +1,30 @@ - net6.0 + netstandard2.0;net6.0;net7.0 enable enable + + 0.7.1 + Xbotter + SciSharp STACK + true + MIT, SciSharp STACK $([System.DateTime]::UtcNow.ToString(yyyy)) + https://github.com/SciSharp/LLamaSharp + git + https://avatars3.githubusercontent.com/u/44989469?s=200&v=4 + LLama, LLM, GPT, ChatGPT, kernel-memory, vector search, SciSharp + + The integration of LLamaSharp and Microsoft kernel-memory. It could make it easy to support document search for LLamaSharp model inference. + + + Support integration with kernel-memory + + MIT + packages + AnyCPU;x64;Arm64 + LLamaSharp.kernel-memory + Debug;Release;GPU diff --git a/LLama.SemanticKernel/LLamaSharp.SemanticKernel.csproj b/LLama.SemanticKernel/LLamaSharp.SemanticKernel.csproj index 77596d57..c6ece4e7 100644 --- a/LLama.SemanticKernel/LLamaSharp.SemanticKernel.csproj +++ b/LLama.SemanticKernel/LLamaSharp.SemanticKernel.csproj @@ -10,8 +10,8 @@ enable enable - 0.6.2-beta1 - Tim Miller + 0.7.1 + Tim Miller, Xbotter SciSharp STACK true MIT, SciSharp STACK $([System.DateTime]::UtcNow.ToString(yyyy)) @@ -20,7 +20,7 @@ https://avatars3.githubusercontent.com/u/44989469?s=200&v=4 LLama, LLM, GPT, ChatGPT, semantic-kernel, SciSharp - The integration of LLamaSharp ans semantic-kernel. + The integration of LLamaSharp and Microsoft semantic-kernel. Support integration with semantic-kernel diff --git a/README.md b/README.md index c3b73f8c..d116d1a4 100644 --- a/README.md +++ b/README.md @@ -54,6 +54,13 @@ For [microsoft semantic-kernel](https://github.com/microsoft/semantic-kernel) in LLamaSharp.semantic-kernel ``` +For [microsoft kernel-memory](https://github.com/microsoft/kernel-memory) integration, please search and install the following package: + +``` +LLamaSharp.kernel-memory +``` + + ### Tips for choosing a version In general, there may be some break changes between two minor releases, for example 0.5.1 and 0.6.0. On the contrary, we don't introduce API break changes in patch release. Therefore it's recommended to keep the highest patch version of a minor release. For example, keep 0.5.6 instead of 0.5.3. @@ -196,7 +203,7 @@ Another choice is generate gguf format file yourself with a pytorch weight (or a 🔳 Fine-tune -⚠️ Local document search (enabled by kernel-memory now) +✅ Local document search (enabled by kernel-memory now) 🔳 MAUI Integration From 0f12566f654f430f50480128ae65e5f588f6dc45 Mon Sep 17 00:00:00 2001 From: Yaohui Liu Date: Sun, 5 Nov 2023 02:55:41 +0800 Subject: [PATCH 2/3] build: use only net6.0 with kernel-memory. --- LLama.KernelMemory/LLamaSharp.KernelMemory.csproj | 2 +- README.md | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj b/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj index de5f42a5..7fd99e2c 100644 --- a/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj +++ b/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj @@ -1,7 +1,7 @@ - netstandard2.0;net6.0;net7.0 + net6.0 enable enable diff --git a/README.md b/README.md index d116d1a4..96c9883a 100644 --- a/README.md +++ b/README.md @@ -54,13 +54,12 @@ For [microsoft semantic-kernel](https://github.com/microsoft/semantic-kernel) in LLamaSharp.semantic-kernel ``` -For [microsoft kernel-memory](https://github.com/microsoft/kernel-memory) integration, please search and install the following package: +For [microsoft kernel-memory](https://github.com/microsoft/kernel-memory) integration, please search and install the following package (currently kernel-memory only supports net6.0): ``` LLamaSharp.kernel-memory ``` - ### Tips for choosing a version In general, there may be some break changes between two minor releases, for example 0.5.1 and 0.6.0. On the contrary, we don't introduce API break changes in patch release. Therefore it's recommended to keep the highest patch version of a minor release. For example, keep 0.5.6 instead of 0.5.3. From 457958435b07603e9f41dad62af2ca60e621bae1 Mon Sep 17 00:00:00 2001 From: Yaohui Liu Date: Sun, 5 Nov 2023 02:59:41 +0800 Subject: [PATCH 3/3] build: use semantic-kernel beta1 in examples. --- LLama.Examples/LLama.Examples.csproj | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/LLama.Examples/LLama.Examples.csproj b/LLama.Examples/LLama.Examples.csproj index 3ecacdfe..c1761829 100644 --- a/LLama.Examples/LLama.Examples.csproj +++ b/LLama.Examples/LLama.Examples.csproj @@ -29,7 +29,7 @@ - +