# Ragflow

> slug: /what-is-agent-context-engine

## Pages

- [What is Agent context engine?](basics-agent-context-engine.md): From 2025, a silent revolution began beneath the dazzling surface of AI Agents. While the world marveled at agents th...
- [What is Retreival-Augmented-Generation (RAG)？](basics-rag.md): Since large language models (LLMs) became the focus of technology, their ability to handle general knowledge has been...
- [Configuration](configurations.md): Configurations for deploying RAGFlow via Docker.
- [Contribution guidelines](contribution-contributing.md): General guidelines for RAGFlow's community contributors.
- [Acquire RAGFlow API key](develop-acquire-ragflow-api-key.md): An API key is required for the RAGFlow server to authenticate your HTTP/Python or MCP requests. This documents provid...
- [Launch service from source](develop-launch-ragflow-from-source.md): A guide explaining how to set up a RAGFlow service from its source code. By following this guide, you'll be able to d...
- [Launch RAGFlow MCP server](develop-mcp-launch-mcp-server.md): Launch an MCP server from source or via Docker.
- [RAGFlow MCP client examples](develop-mcp-mcp-client-example.md): Python and curl MCP client examples.
- [RAGFlow MCP tools](develop-mcp-mcp-tools.md): The MCP server currently offers a specialized tool to assist users in searching for relevant information powered by R...
- [Migrate from multi-Bucket to single-bucket mode](develop-migrate-to-single-bucket-mode.md): By default, RAGFlow creates one bucket per Knowledge Base (dataset) and one bucket per user folder. This can be probl...
- [Switch document engine](develop-switch-doc-engine.md): Switch your doc engine from Elasticsearch to Infinity.
- [Admin CLI](guides-admin-admin-cli.md): The RAGFlow Admin CLI is a command-line-based system administration tool that offers administrators an efficient and ...
- [Admin Service](guides-admin-admin-service.md): The Admin Service is the core backend management service of the RAGFlow system, providing comprehensive system admini...
- [Admin UI](guides-admin-admin-ui.md): The RAGFlow Admin UI is a web-based interface that provides comprehensive system status monitoring and user managemen...
- [Title chunker component](guides-agent-agent-component-reference-chunker-title.md): A component that splits texts into chunks by heading level.
- [Token chunker component](guides-agent-agent-component-reference-chunker-token.md): A component that splits texts into chunks, respecting a maximum token limit and using delimiters to find optimal brea...
- [Docs Generator component](guides-agent-agent-component-reference-docs-generator.md): A component that generates downloadable PDF, DOCX, or TXT documents from markdown-style content with full Unicode sup...
- [Execute SQL tool](guides-agent-agent-component-reference-execute-sql.md): A tool that execute SQL queries on a specified relational database.
- [HTTP request component](guides-agent-agent-component-reference-http.md): A component that calls remote services.
- [Indexer component](guides-agent-agent-component-reference-indexer.md): A component that defines how chunks are indexed.
- [Parser component](guides-agent-agent-component-reference-parser.md): A component that sets the parsing rules for your dataset.
- [Transformer component](guides-agent-agent-component-reference-transformer.md): A component that uses an LLM to extract insights from the chunks.
- [Introduction to agents](guides-agent-agent-introduction.md): Key concepts, basic operations, a quick view of the agent editor.
- [Accelerate answering](guides-agent-best-practices-accelerate-agent-question-answering.md): A checklist to speed up question answering.
- [Embed agent into webpage](guides-agent-embed-agent-into-webpage.md): You can use iframe to embed an agent into a third-party webpage.
- [Sandbox quickstart](guides-agent-sandbox-quickstart.md): A secure, pluggable code execution backend designed for RAGFlow and other applications requiring isolated code execut...
- [Search](guides-ai-search.md): Conduct an AI search.
- [Implement deep research](guides-chat-implement-deep-research.md): Implements deep research for agentic reasoning.
- [Set variables](guides-chat-set-chat-variables.md): Set variables to be used together with the system prompt for your LLM.
- [Start AI chat](guides-chat-start-chat.md): Initiate an AI-powered chat with a configured chat assistant.
- [Add Google Drive](guides-dataset-add-data-source-add-google-drive.md): You can either create a dedicated project for RAGFlow or use an existing
- [Auto-extract metadata](guides-dataset-auto-metadata.md): Automatically extract metadata from uploaded files.
- [Configure child chunking strategy](guides-dataset-configure-child-chunking-strategy.md): Set parent-child chunking strategy to improve retrieval.
- [Configure dataset](guides-dataset-configure-knowledge-base.md): Most of RAGFlow's chat assistants and Agents are based on datasets. Each of RAGFlow's datasets serves as a knowledge ...
- [Construct knowledge graph](guides-dataset-construct-knowledge-graph.md): Generate a knowledge graph for your dataset.
- [Enable Excel2HTML](guides-dataset-enable-excel2html.md): Convert complex Excel spreadsheets into HTML tables.
- [Enable RAPTOR](guides-dataset-enable-raptor.md): A recursive abstractive method used in long-context knowledge retrieval and summarization, balancing broad semantic u...
- [Extract table of contents](guides-dataset-extract-table-of-contents.md): Extract table of contents (TOC) from documents to provide long context RAG and improve retrieval.
- [Manage metadata](guides-dataset-manage-metadata.md): Manage metadata for your dataset and for your individual documents.
- [Run retrieval test](guides-dataset-run-retrieval-test.md): Conduct a retrieval test on your dataset to check whether the intended chunks can be retrieved.
- [Select PDF parser](guides-dataset-select-pdf-parser.md): Select a visual model for parsing your PDFs.
- [Set context window size](guides-dataset-set-context-window.md): Set context window size for images and tables to improve long-context RAG performances.
- [Set metadata](guides-dataset-set-metadata.md): Manually add metadata to an uploaded file
- [Set page rank](guides-dataset-set-page-rank.md): Create a step-retrieval strategy using page rank.
- [Use tag set](guides-dataset-use-tag-sets.md): Use a tag set to auto-tag chunks in your datasets.
- [Files](guides-manage-files.md): RAGFlow's file management allows you to upload files individually or in bulk. You can then link an uploaded file to m...
- [Data Migration Guide](guides-migration-migrate-from-docker-compose.md): A common scenario is processing large datasets on a powerful instance (e.g., with a GPU) and then migrating the entir...
- [Configure model API key](guides-models-llm-api-key-setup.md): An API key is required for RAGFlow to interact with an online AI model. This guide provides information about setting...
- [Join or leave a team](guides-team-join-or-leave-team.md): Accept an invitation to join a team, decline an invitation, or leave a team.
- [Manage team members](guides-team-manage-team-members.md): Invite or remove team members.
- [Share Agent](guides-team-share-agents.md): Share an Agent with your team members.
- [Share chat assistant](guides-team-share-chat-assistant.md): Sharing chat assistant is currently exclusive to RAGFlow Enterprise, but will be made available in due course.
- [Share dataset](guides-team-share-knowledge-bases.md): Share a dataset with team members.
- [Share models](guides-team-share-model.md): Sharing models is currently exclusive to RAGFlow Enterprise.
- [HTTP API](references-http-api-reference.md): A complete reference for RAGFlow's RESTful API. Before proceeding, please ensure you [have your RAGFlow API key ready...
- [Python API](references-python-api-reference.md): A complete reference for RAGFlow's Python APIs. Before proceeding, please ensure you [have your RAGFlow API key ready...
- [Releases](release-notes.md): Key features, improvements and bug fixes in the latest releases.
- [Build RAGFlow Docker image](develop-build-docker-image.md): import Tabs from '@theme/Tabs';
- [FAQs](faq.md): Answers to questions about general features, troubleshooting, usage, and more.
- [Agent component](guides-agent-agent-component-reference-agent.md): The component equipped with reasoning, tool usage, and multi-agent collaboration capabilities.
- [Await response component](guides-agent-agent-component-reference-await-response.md): A component that halts the workflow and awaits user input.
- [Begin component](guides-agent-agent-component-reference-begin.md): The starting component in a workflow.
- [Categorize component](guides-agent-agent-component-reference-categorize.md): A component that classifies user inputs and applies strategies accordingly.
- [Code component](guides-agent-agent-component-reference-code.md): A component that enables users to integrate Python or JavaScript codes into their Agent for dynamic data processing.
- [Iteration component](guides-agent-agent-component-reference-iteration.md): A component that splits text input into text segments and iterates a predefined workflow for each one.
- [Message component](guides-agent-agent-component-reference-message.md): A component that sends out a static or dynamic message.
- [Retrieval component](guides-agent-agent-component-reference-retrieval.md): A component that retrieves information from specified datasets.
- [Switch component](guides-agent-agent-component-reference-switch.md): A component that evaluates whether specified conditions are met and directs the follow of execution accordingly.
- [Text processing component](guides-agent-agent-component-reference-text-processing.md): A component that merges or splits texts.
- [Accelerate answering](guides-chat-best-practices-accelerate-question-answering.md): import APITable from '@site/src/components/APITable';
- [Auto-keyword Auto-question](guides-dataset-autokeyword-autoquestion.md): import APITable from '@site/src/components/APITable';
- [Accelerate indexing](guides-dataset-best-practices-accelerate-doc-indexing.md): import APITable from '@site/src/components/APITable';
- [Deploy local models](guides-models-deploy-local-llm.md): import Tabs from '@theme/Tabs';
- [Tracing](guides-tracing.md): Observability & Tracing with Langfuse.
- [Upgrading](guides-upgrade-ragflow.md): import Tabs from '@theme/Tabs';
- [Get started](quickstart.md): import Tabs from '@theme/Tabs';
- [Glossary](references-glossary.md): Definitions of key terms and basic concepts related to RAGFlow.
- [Supported models](references-supported-models.md): import APITable from '@site/src/components/APITable';