From this release onwards, we ship only the slim edition (without embedding models) Docker image and no longer append the `-slim` suffix to the image tag.
:::
### New Features
- Dataset:
- Supports data synchronization from five online sources (AWS S3, Google Drive, Notion, Confluence, and Discord).
- RAPTOR can be built across an entire dataset or on individual documents.
- Ingestion pipeline: Supports [Docling document parsing](https://github.com/docling-project/docling) in the **Parser** component.
- Launches a new administrative Web UI dashboard for graphical user management and service status monitoring.
- Agent:
- Supports structured output.
- Supports metadata filtering in the **Retrieval** component.
- Introduces a **Variable aggregator** component with data operation and session variable definition capabilities.
### Improvements
- Agent: Supports visualizing previous components' outputs in the **Await Response** component.
- Revamps the model provider page.
- Upgrades RAGFlow's document engine Infinity to v0.6.5.
### Added Models
- Kimi-K2-Thinking
### New agent templates
- Interactive Agent, incorporates real-time user feedback to dynamically optimize Agent output.
- Orchestratable ingestion pipeline: Supports customized data ingestion and cleansing workflows, enabling users to flexibly design their data flows or directly apply the official data flow templates on the canvas.
- GraphRAG & RAPTOR write process optimized: Replaces the automatic incremental build process with manual batch building, significantly reducing construction overhead.
- Long-context RAG: Automatically generates document-level table of contents (TOC) structures to mitigate context loss caused by inaccurate or excessive chunking, substantially improving retrieval quality. This feature is now available via a TOC extraction template. See [here](./guides/dataset/extract_table_of_contents.md).
- Video file parsing: Expands the system's multimodal data processing capabilities by supporting video file parsing.
- Admin CLI: Introduces a new command-line tool for system administration, allowing users to manage and monitor RAGFlow's service status via command line.
### Improvements
- Redesigns RAGFlow's Login and Registration pages.
- Company Research Report Deep Dive Agent: Designed for financial institutions to help analysts quickly organize information, generate research reports, and make investment decisions.
- Orchestratable Ingestion Pipeline Template: Allows users to apply this template on the canvas to rapidly establish standardized data ingestion and cleansing processes.
- Four framework-level prompt blocks are available in the **System prompt** section, enabling customization and overriding of prompts at the framework level, thereby enhancing flexibility and control. See [here](./guides/agent/agent_component_reference/agent.mdx#system-prompt).
- **Execute SQL** component enhanced: Replaces the original variable reference component with a text input field, allowing users to write free-form SQL queries and reference variables. See [here](./guides/agent/agent_component_reference/execute_sql.md).
- An Agent in task mode still required a dialogue to trigger.
- Repeated answers in multi-turn dialogues.
- Duplicate summarization of parallel execution results.
### API changes
#### HTTP APIs
- Adds a body parameter `"metadata_condition"` to the [Retrieve chunks](./references/http_api_reference.md#retrieve-chunks) method, enabling metadata-based chunk filtering during retrieval. [#9877](https://github.com/infiniflow/ragflow/pull/9877)
#### Python APIs
- Adds a parameter `metadata_condition` to the [Retrieve chunks](./references/python_api_reference.md#retrieve-chunks) method, enabling metadata-based chunk filtering during retrieval. [#9877](https://github.com/infiniflow/ragflow/pull/9877)
Ecommerce Customer Service Workflow: A template designed to handle enquiries about product features and multi-product comparisons using the internal dataset, as well as to manage installation appointment bookings.
- Search: Supports creating search apps tailored to various business scenarios
- Chat: Supports comparing answer performance of up to three chat model settings on a single **Chat** page.
- Agent:
- Implements a toggle in the **Agent** component to enable or disable citation.
- Introduces a drag-and-drop method for creating components.
- Documentation: Corrects inaccuracies in the API reference.
### New Agent templates
- Report Agent: A template for generating summary reports in internal question-answering scenarios, supporting the display of tables and formulae. [#9427](https://github.com/infiniflow/ragflow/pull/9427)
- Choose Your Knowledge Base Workflow: Lets users select a dataset to query during conversations. [#9325](https://github.com/infiniflow/ragflow/pull/9325)
- Choose Your Knowledge Base Agent: Delivers higher-quality responses with extended reasoning time, suited for complex queries. [#9325](https://github.com/infiniflow/ragflow/pull/9325)
### Fixed Issues
- The **Agent** component was unable to invoke models installed via vLLM.
- Agents could not be shared with the team.
- Embedding an Agent into a webpage was not functioning properly.
From v0.20.0 onwards, Agents are no longer compatible with earlier versions, and all existing Agents from previous versions must be rebuilt following the upgrade.
### New features
- Unified orchestration of both Agents and Workflows.
- A comprehensive refactor of the Agent, greatly enhancing its capabilities and usability, with support for Multi-Agent configurations, planning and reflection, and visual functionalities.
- Fully implemented MCP functionality, allowing for MCP Server import, Agents functioning as MCP Clients, and RAGFlow itself operating as an MCP Server.
- Multi-Agent based Deep Research: Collaborative Agent teamwork led by a Lead Agent with multiple Subagents, distinct from traditional workflow orchestration.
- Added support for models installed via Ollama or VLLM when creating a dataset through the API. [#8069](https://github.com/infiniflow/ragflow/pull/8069)
- [Cross-language search](./references/glossary.mdx#cross-language-search) is supported in the Knowledge and Chat modules, enhancing search accuracy and user experience in multilingual environments, such as in Chinese-English datasets.
- Agent component: A new Code component supports Python and JavaScript scripts, enabling developers to handle more complex tasks like dynamic data processing.
- Enhanced image display: Images in Chat and Search now render directly within responses, rather than as external references. Knowledge retrieval testing can retrieve images directly, instead of texts extracted from images.
From this release onwards, built-in rerank models have been removed because they have minimal impact on retrieval rates but significantly increase retrieval time.
- DeepDoc supports adopting VLM model as a processing pipeline during document layout recognition, enabling in-depth analysis of images in PDF and DOCX files.
- AI chat: Implements Deep Research for agentic reasoning. To activate this, enable the **Reasoning** toggle under the **Prompt engine** tab of your chat assistant dialogue.
- AI chat: Leverages Tavily-based web search to enhance contexts in agentic reasoning. To activate this, enter the correct Tavily API key under the **Assistant settings** tab of your chat assistant dialogue.
- Dataset: Adds a **PDF parser**, aka **Document parser**, dropdown menu to dataset configurations. This includes a DeepDoc model option, which is time-consuming, a much faster **naive** option (plain text), which skips DLA (Document Layout Analysis), OCR (Optical Character Recognition), and TSR (Table Structure Recognition) tasks, and several currently *experimental* large model options. See [here](./guides/dataset/select_pdf_parser.md).
- Agent component: **(x)** or a forward slash `/` can be used to insert available keys (variables) in the system prompt field of the **Generate** or **Template** component.
- Object storage: Supports using Aliyun OSS (Object Storage Service) as a file storage option.
- GraphRAG refactor: Knowledge graph is dynamically built on an entire dataset rather than on an individual file, and automatically updated when a newly uploaded file starts parsing. See [here](https://ragflow.io/docs/dev/construct_knowledge_graph).
- Adds an **Iteration** agent component and a **Research report generator** agent template. See [here](./guides/agent/agent_component_reference/iteration.mdx).
Adds [Infinity's configuration file](https://github.com/infiniflow/ragflow/blob/main/docker/infinity_conf.toml) to facilitate integration and customization of [Infinity](https://github.com/infiniflow/infinity) as a document engine. From this release onwards, updates to Infinity's configuration can be made directly within RAGFlow and will take effect immediately after restarting RAGFlow using `docker compose`. [#3715](https://github.com/infiniflow/ragflow/pull/3715)
- Supports [Infinity](https://github.com/infiniflow/infinity) or Elasticsearch (default) as document engine for vector storage and full-text indexing. [#2894](https://github.com/infiniflow/ragflow/pull/2894)
From this release onwards, **service_config.yaml.template** replaces **service_config.yaml** for configuring backend services. Upon Docker container startup, the environment variables defined in this template file are automatically populated and a **service_config.yaml** is auto-generated from it. [#3341](https://github.com/infiniflow/ragflow/pull/3341)
This approach eliminates the need to manually update **service_config.yaml** after making changes to **.env**, facilitating dynamic environment configurations.
Ensure that you [upgrade **both** your code **and** Docker image to this release](https://ragflow.io/docs/dev/upgrade_ragflow#upgrade-ragflow-to-the-most-recent-officially-published-release) before trying this new approach.
- Implements an **Excel to HTML** toggle in the **General** chunking method, allowing users to parse a spreadsheet into either HTML tables or key-value pairs by row.
From this release onwards, RAGFlow offers slim editions of its Docker images to improve the experience for users with limited Internet access. A slim edition of RAGFlow's Docker image does not include built-in BGE/BCE embedding models and has a size of about 1GB; a full edition of RAGFlow is approximately 9GB and includes two built-in embedding models.
- Integrates reranker and embedding models: [BCE](https://github.com/netease-youdao/BCEmbedding), [BGE](https://github.com/FlagOpen/FlagEmbedding), and [Jina](https://jina.ai/embeddings/).
- Supports LLMs Baichuan and VolcanoArk.
- Implements [RAPTOR](https://arxiv.org/html/2401.18059v1) for improved text retrieval.
