Title: P2: Indexing techniques and RAG best practices [2024-08-01 Thu]
publicly avaliable models converted to ONNX format.
😶 #dailyreport #rag #grag #indexing #retriving #onnx #ncnn

Title: P1: Indexing techniques and RAG best practices [2024-08-01 Thu]
I compiled from sources PyTorch.

ONNX quantized models have boost up to 3X in speed and
memory and can be run on cheepest CPU, that is what I am
going to achieve - create approachable and presonalized
AI.

I found open source runtime for ONNX without hell of
dependencies: https://github.com/Tencent/ncnn/

I faced lack of examples and hell of dependencies for #dailyreport #rag #grag #indexing #retriving #onnx #ncnn

GitHub - Tencent/ncnn: ncnn is a high-performance neural network inference framework optimized for the mobile platform

ncnn is a high-performance neural network inference framework optimized for the mobile platform - Tencent/ncnn

GitHub
Title: P2: P0: Indexing techniques and RAG best practices [2024-08-01 Thu]
- 2019 pretrained language models - semantic of data
- 2020 improvement of negative sampling with constrasting
learning
- 2021 exploitation of knowledge distillation
- 2024 graphRetrival, multi-agents #dailyreport #rag #grag #indexing #retriving #onnx #ncnn

Title: P1: P0: Indexing techniques and RAG best practices [2024-08-01 Thu]
I have been reading original papars at arxiv and articles
about indexing techniques and RAG best practices such as
Graph-based RAG, SubGraph GRAG.

Modern history of neural retrival: #dailyreport #rag #grag #indexing #retriving #onnx #ncnn

Title: P2: Indexing techniques and RAG best practices [2024-08-01 Thu]
publicly avaliable models converted to ONNX format.
😶 #dailyreport #rag #grag #indexing #retriving #onnx #ncnn

Title: P1: Indexing techniques and RAG best practices [2024-08-01 Thu]
I compiled from sources PyTorch.

ONNX quantized models have boost up to 3X in speed and
memory and can be run on cheepest CPU, that is what I am
going to achieve - create approachable and presonalized
AI.

I found open source runtime for ONNX without hell of
dependencies: https://github.com/Tencent/ncnn/

I faced lack of examples and hell of dependencies for #dailyreport #rag #grag #indexing #retriving #onnx #ncnn

GitHub - Tencent/ncnn: ncnn is a high-performance neural network inference framework optimized for the mobile platform

ncnn is a high-performance neural network inference framework optimized for the mobile platform - Tencent/ncnn

GitHub
Title: P2: P0: Indexing techniques and RAG best practices [2024-08-01 Thu]
- 2019 pretrained language models - semantic of data
- 2020 improvement of negative sampling with constrasting
learning
- 2021 exploitation of knowledge distillation
- 2024 graphRetrival, multi-agents #dailyreport #rag #grag #indexing #retriving #onnx #ncnn

Title: P1: P0: Indexing techniques and RAG best practices [2024-08-01 Thu]
I have been reading original papars at arxiv and articles
about indexing techniques and RAG best practices such as
Graph-based RAG, SubGraph GRAG.

Modern history of neural retrival: #dailyreport #rag #grag #indexing #retriving #onnx #ncnn

Title: P0: Onnx, jupyter [2024-07-25 Thu]
I have been enhancing my Jupyter to Org mode
converter j2o written in Python.

I studying ONNX framework now and I want to build RAG and
memory for personalized AI.

I have found cool looking underrated game "Darksiders:
Wrath of War" 2010. Didn't played.
😶 #dailyreport #jupyter #onnx

Title: P0: Onnx, jupyter [2024-07-25 Thu]
I have been enhancing my Jupyter to Org mode
converter j2o written in Python.

I studying ONNX framework now and I want to build RAG and
memory for personalized AI.

I have found cool looking underrated game "Darksiders:
Wrath of War" 2010. Didn't played.
😶 #dailyreport #jupyter #onnx