检索增强一代的终结？新兴的体系结构标志着一种转变
Retrieval Augmented Generation (RAG) has been a cornerstone in enhancing large language models (LLMs) for complex, knowledge-driven tasks. By pulling in relevant data from a vector database, RAG has empowered LLMs with factual grounding, significantly reducing instances of fabricated information. But is this the end of the road for RAG?
Devin，新的人工智能，能取代人类软件工程师吗？
A new AI named Devin claiming the title of the world’s first AI software engineer. From coding entire projects to fixing GitHub issues, Devin seems to be the new topic. And with such sensational capabilities, the rumor mill is working overtime, sparking fears that the era of human software engineers might be coming to an end. But before you join the panic parade, let’s take a look and see why, despite these advancements, we’re not heading for the job market exit anytime soon.
使用QLoRA在Google Colab中微调Mistral 7b（完整指南）
In this article, we are going to fine-tune Mistral 7b on the entire code base of a game called Enlighten, all for free in Google Colab(or Kaggle) with synthetic data. The resulting model will outperform Openai’s GPT-4 on our benchmark.
These are the steps:
RAG与微调——哪种工具是提升LLM应用程序的最佳工具？
高级RAG 05：探索语义块
After parsing the document, we can obtain structured or semi-structured data. The main task now is to break them down into smaller chunks to extract detailed features, and then embed these features to represent their semantics. Its position in RAG is shown in Figure 1.
构建自己的个人人工智能助手：构建文本和语音本地LLM的分步指南
In this tutorial we will create a personal local LLM assistant, that you can talk to. You will be able to record your voice using your microphone and send to the LLM. The LLM will return the answer with text AND speech.
高级RAG 02：揭开PDF解析的面纱
20240215 Additional content: Unveiling PDF Parsing: How to extract formulas from scientific pdf papers
如何在没有矢量数据库的情况下进行RAG
Introduction
When it comes to bestowing Large Language Models (LLMs) with long-term memory, the prevalent approach often involves a Retrieval Augmented Generation (RAG) solution, with vector databases acting as the storage mechanism for the long-term memory. This begs the question: Can we achieve the same results without vector databases?
2024年十大数据和人工智能趋势
从LLM将现代数据堆栈转换为矢量数据库的数据可观察性，以下是我对2024年顶级数据工程趋势的预测。
嵌入+知识图：RAG系统的终极工具
The advent of large language models (LLMs) , trained on vast amounts of text data, has been one of the most significant breakthroughs in natural language processing. The ability of these models to generate remarkably fluent and coherent text with just a short prompt has opened up new possibilities for conversational AI, creative writing, and a wide array of other applications.