GoPenAI·2yLab #3: Implementing RAG to build a “Chat with Multiple PDFs” app
This post explains how to build a 'Chat with Multiple PDFs' app using Retrieval-Augmented Generation (RAG), and covers its benefits, such as reducing model hallucination and enhancing reliability. It details phases for pre-processing and inference, including loading, chunking, and embedding data into a vector database, and setting up a retrieval chain using Langchain and OpenAI integration.
LangChain·2yWhat is a "cognitive architecture"?
Cognitive architecture refers to the way a system processes user input to generate a response or perform actions, utilizing levels of autonomy from simple code to complex autonomous agents. Different architectures like single LLM calls, chains of LLM calls, routers, state machines, and fully autonomous agents are explored. Choosing a cognitive architecture depends on the task, with more flexibility and customization available through LangChain and LangGraph frameworks. Python and JavaScript are recommended for implementing these systems.
Community Picks·2yDeploy Mistral Large to Azure and create a conversation with Python and LangChain
Neon, a cloud-native serverless Postgres solution, introduces a guide for deploying Mistral Large, an advanced Large Language Model by Mistral AI, on Azure. The guide covers the deployment process in Azure AI Studio and using Mistral Large with LangChain for creating conversations. Highlights include Mistral Large’s high performance in reasoning, coding, and mathematics, making it ideal for Retrieval Augmented Generation applications.
Towards Data Science·2yIntegrating Microsoft GraphRAG into Neo4j
Learn how to integrate Microsoft GraphRAG with Neo4j to store and analyze data, along with implementing local and global retrievers using LangChain and LlamaIndex. Steps include configuration of knowledge graph extraction, importing data into Neo4j, and setting up retrievers. Uses dataset 'A Christmas Carol' to demonstrate the process. Code available on GitHub.