In this blog post, we introduce a brand new data structure in LlamaIndex: the Document Summary Index. We describe how it helps provide better retrieval performance compared to traditional semantic search, along with an example. https://github.com/jerryjliu/llama_index 1 Background One of the core scenarios for large language models (LLM) is question answering on user data. To … Read more
LlamaIndex is a simple and flexible data framework that connects custom data sources with large language models. LlamaIndex provides comprehensive support for RAG. Advanced RAG (Retrieval-Augmented Generation) techniques can be modeled using a composable hierarchical abstraction. The retrieved text can be linked to the following elements: Retriever Text Pipeline Query Engine The retrieval of RAG … Read more
Overview The ContextChatEngine class is a contextual chat engine designed to provide a smooth chat experience by retrieving contextual information from the chat and using a language model (LLM) to generate responses based on system prompts. It is a simple chat mode built on top of a data retriever. For each chat interaction: First, retrieve … Read more
Overview ReAct is an agent-based chat mode built on top of a data query engine. For each chat interaction, the agent enters a ReAct loop: First, decide whether to use the query engine tool and propose appropriate input (Optional) Use the query engine tool and observe its output Decide whether to repeat or give a … Read more
Abstract Large language models (LLMs) have demonstrated impressive capabilities. However, this does not mean they are error-free; anyone who has experienced ChatGPT’s “hallucinations” can attest to that. Retrieval Augmented Generation (RAG) is a framework designed to make LLMs more reliable by extracting relevant, up-to-date data directly related to user queries. In this article, I analyze … Read more
Overview The Query Engine is a generic interface that allows you to query data. It accepts natural language queries and returns rich responses. It is typically (but not always) built on one or more indexes through a retriever. You can combine multiple query engines to achieve more advanced functionality. Note: If you want to have … Read more
Overview This article introduces how to use LlamaIndex to write your own Agent handling functions. Note that this article uses a locally deployed LLM supported by Ollama for practical implementation, rather than remotely calling the OpenAI API. The goal of this article is to save the output content to a PDF file and then stop … Read more
In the previous article “The Future of Application Orchestration is Pipeline, LlamaIndex Releases Query Pipeline in Preview to Enhance Application Development Flexibility” we mentioned that LlamaIndex has released a new experimental feature that supports defining a Query Pipeline in a declarative manner to create personalized application workflows, along with a case study for RAG applications. … Read more
Project Introduction Project: There are various types of agents (projects), each with its own functionality. (rag, ragsql, inference, vision) User: Users represent the system’s users. It is used for authentication and authorization (basic authentication). Each user can access multiple projects. LLMs: Supports any public or local LLM supported by LlamaIndex or Ollama. VRAM: Automatic VRAM … Read more
Overview This article implements a simple intelligent Agent that first queries data from a database and then processes the data using utility functions. This is a very common scenario that can be extended to multiple practical situations. Similarly, all experiments in this article are conducted on a local machine with 16C32G Linux (CPU). Data Preparation … Read more