This article explores how to implement a retriever over a knowledge graph containing structured information to power RAG (Retrieval-Augmented Generation) applications.
IncarnaMind enables chatting with personal documents (PDF, TXT) using Large Language Models (LLMs) like GPT. It uses a Sliding Window Chunking mechanism and Ensemble Retriever for efficient querying.
This page lists various tools that can be integrated with LangChain, categorized by their functionalities. These tools range from search engines and code interpreters to API connectors and data manipulation tools.
This article provides an overview of LangChain, a tool that facilitates the integration of AI, particularly LLMs, into your code or project. It explains the concept of 'chains' in LangChain, which are sequences of operations that involve processing inputs, interacting with an AI, and handling outputs. The article also mentions the need for API keys for the AI you plan to use.
Mariya Mansurova explores using CrewAI's multi-agent framework to create a solution for writing documentation based on tables and answering related questions.
This article introduces Langchain, a platform for productionizing large language model (LLM) applications, and discusses the first principles of building LLM agents. The author explains the difference between simple LLM usage and techniques such as 'chain of thought' and 'tree of thoughts'. The article also provides examples of how to use Langchain's built-in tools and custom tools for planning, memory, and tools in LLM agents.
LangChain's ElasticsearchRetriever enables full flexibility in defining retrieval strategies, allowing users to experiment with different approaches.
This article discusses how to overcome limitations of retrieval-augmented generation (RAG) models by creating an AI assistant using advanced SQL vector queries. The author uses tools such as MyScaleDB, OpenAI, LangChain, Hugging Face and the HackerNews API to develop an application that enhances the accuracy and efficiency of data retrieval process.
This article guides you through the process of building a simple agent in LangChain using Tools and Toolkits. It explains the basics of Agents, their components, and how to build a Mathematics Agent that can perform simple mathematical operations.
The article argues that instead of developing numerous tools for LLM, giving it direct access to a terminal is more efficient and future-proof. It references Rich Sutton's "The Bitter Lesson" and discusses how the terminal's existing command-line tools can be utilized by LLM for various tasks, highlighting the importance of general methods over specialized tools.
