diff --git a/docs/administrator/configurations.md b/docs/administrator/configurations.md index 770426962..213c6d8a3 100644 --- a/docs/administrator/configurations.md +++ b/docs/administrator/configurations.md @@ -2,7 +2,7 @@ sidebar_position: 0 slug: /configurations sidebar_custom_props: { - sidebarIcon: LucideCog + categoryIcon: LucideCog } --- # Configuration diff --git a/docs/guides/agent/agent_component_reference/retrieval.mdx b/docs/guides/agent/agent_component_reference/retrieval.mdx index 5295092ed..2cf791d4d 100644 --- a/docs/guides/agent/agent_component_reference/retrieval.mdx +++ b/docs/guides/agent/agent_component_reference/retrieval.mdx @@ -128,7 +128,7 @@ Select one or more languages for cross‑language search. If no language is sele ### Use knowledge graph :::caution IMPORTANT -Before enabling this feature, ensure you have properly [constructed a knowledge graph from each target dataset](../../dataset/construct_knowledge_graph.md). +Before enabling this feature, ensure you have properly [constructed a knowledge graph from each target dataset](../../dataset/advanced/construct_knowledge_graph.md). ::: Whether to use knowledge graph(s) in the specified dataset(s) during retrieval for multi-hop question answering. When enabled, this would involve iterative searches across entity, relationship, and community report chunks, greatly increasing retrieval time. diff --git a/docs/guides/dataset/advanced/_category_.json b/docs/guides/dataset/advanced/_category_.json new file mode 100644 index 000000000..59b612304 --- /dev/null +++ b/docs/guides/dataset/advanced/_category_.json @@ -0,0 +1,11 @@ +{ + "label": "Advanced enrichment", + "position": 8, + "link": { + "type": "generated-index", + "description": "Advanced enrichment." + }, + "customProps": { + "categoryIcon": "LucideFlower" + } +} diff --git a/docs/guides/dataset/auto_metadata.md b/docs/guides/dataset/advanced/auto_metadata.md similarity index 99% rename from docs/guides/dataset/auto_metadata.md rename to docs/guides/dataset/advanced/auto_metadata.md index 7a7b08636..7814489d8 100644 --- a/docs/guides/dataset/auto_metadata.md +++ b/docs/guides/dataset/advanced/auto_metadata.md @@ -1,5 +1,5 @@ --- -sidebar_position: -6 +sidebar_position: 4 slug: /auto_metadata sidebar_custom_props: { categoryIcon: LucideFileCodeCorner diff --git a/docs/guides/dataset/autokeyword_autoquestion.mdx b/docs/guides/dataset/advanced/autokeyword_autoquestion.mdx similarity index 99% rename from docs/guides/dataset/autokeyword_autoquestion.mdx rename to docs/guides/dataset/advanced/autokeyword_autoquestion.mdx index 3165a6a6b..ae06006f1 100644 --- a/docs/guides/dataset/autokeyword_autoquestion.mdx +++ b/docs/guides/dataset/advanced/autokeyword_autoquestion.mdx @@ -1,5 +1,5 @@ --- -sidebar_position: 3 +sidebar_position: 0 slug: /autokeyword_autoquestion sidebar_custom_props: { categoryIcon: LucideSlidersHorizontal diff --git a/docs/guides/dataset/construct_knowledge_graph.md b/docs/guides/dataset/advanced/construct_knowledge_graph.md similarity index 99% rename from docs/guides/dataset/construct_knowledge_graph.md rename to docs/guides/dataset/advanced/construct_knowledge_graph.md index b4eba1fd6..5b5f21984 100644 --- a/docs/guides/dataset/construct_knowledge_graph.md +++ b/docs/guides/dataset/advanced/construct_knowledge_graph.md @@ -1,5 +1,5 @@ --- -sidebar_position: 8 +sidebar_position: 1 slug: /construct_knowledge_graph sidebar_custom_props: { categoryIcon: LucideWandSparkles diff --git a/docs/guides/dataset/enable_raptor.md b/docs/guides/dataset/advanced/enable_raptor.md similarity index 95% rename from docs/guides/dataset/enable_raptor.md rename to docs/guides/dataset/advanced/enable_raptor.md index 54e36d2bf..b312d7c94 100644 --- a/docs/guides/dataset/enable_raptor.md +++ b/docs/guides/dataset/advanced/enable_raptor.md @@ -1,5 +1,5 @@ --- -sidebar_position: 7 +sidebar_position: 2 slug: /enable_raptor sidebar_custom_props: { categoryIcon: LucideNetwork @@ -34,7 +34,7 @@ The recursive clustering and summarization capture a broad understanding (by the For multi-hop question-answering tasks involving complex, multistep reasoning, a semantic gap often exists between the question and its answer. As a result, searching with the question often fails to retrieve the relevant chunks that contribute to the correct answer. RAPTOR addresses this challenge by providing the chat model with richer and more context-aware and relevant chunks to summarize, enabling a holistic understanding without losing granular details. :::tip NOTE -Knowledge graphs can also be used for multi-hop question-answering tasks. See [Construct knowledge graph](./construct_knowledge_graph.md) for details. You may use either approach or both, but ensure you understand the memory, computational, and token costs involved. +Knowledge graphs can also be used for multi-hop question-answering tasks. See [Construct knowledge graph](../advanced/construct_knowledge_graph.md) for details. You may use either approach or both, but ensure you understand the memory, computational, and token costs involved. ::: ## Prerequisites diff --git a/docs/guides/dataset/extract_table_of_contents.md b/docs/guides/dataset/advanced/extract_table_of_contents.md similarity index 98% rename from docs/guides/dataset/extract_table_of_contents.md rename to docs/guides/dataset/advanced/extract_table_of_contents.md index fc86f78f4..8835d68dd 100644 --- a/docs/guides/dataset/extract_table_of_contents.md +++ b/docs/guides/dataset/advanced/extract_table_of_contents.md @@ -1,5 +1,5 @@ --- -sidebar_position: 4 +sidebar_position: 3 slug: /enable_table_of_contents sidebar_custom_props: { categoryIcon: LucideTableOfContents diff --git a/docs/guides/dataset/set_metadata.md b/docs/guides/dataset/set_metadata.md index 082fc70b5..6931281c2 100644 --- a/docs/guides/dataset/set_metadata.md +++ b/docs/guides/dataset/set_metadata.md @@ -31,4 +31,4 @@ Ensure that your metadata is in JSON format; otherwise, your updates will not be ### Can I set metadata for multiple documents at once? -From v0.23.0 onwards, you can set metadata for each document individually or have the LLM auto-generate metadata for multiple files. See [Extract metadata](./auto_metadata.md) for details. \ No newline at end of file +From v0.23.0 onwards, you can set metadata for each document individually or have the LLM auto-generate metadata for multiple files. See [Extract metadata](./advanced/auto_metadata.md) for details. \ No newline at end of file diff --git a/docs/references/http_api_reference.md b/docs/references/http_api_reference.md index 87c2d9316..5cc930f57 100644 --- a/docs/references/http_api_reference.md +++ b/docs/references/http_api_reference.md @@ -2436,7 +2436,7 @@ curl --request POST \ - `"top_k"`: (*Body parameter*), `integer` The number of chunks engaged in vector cosine computation. Defaults to `1024`. - `"use_kg"`: (*Body parameter*), `boolean` - Whether to search chunks related to the generated knowledge graph for multi-hop queries. Defaults to `False`. Before enabling this, ensure you have successfully constructed a knowledge graph for the specified datasets. See [here](https://ragflow.io/docs/dev/construct_knowledge_graph) for details. + Whether to search chunks related to the generated knowledge graph for multi-hop queries. Defaults to `False`. Before enabling this, ensure you have successfully constructed a knowledge graph for the specified datasets. See [here](../guides/dataset/advanced/construct_knowledge_graph.md) for details. - `"toc_enhance"`: (*Body parameter*), `boolean` Whether to search chunks with extracted table of content. Defaults to `False`. Before enabling this, ensure you have enabled `TOC_Enhance` and successfully extracted table of contents for the specified datasets. See [here](https://ragflow.io/docs/dev/enable_table_of_contents) for details. - `"rerank_id"`: (*Body parameter*), `integer` diff --git a/docs/release_notes.md b/docs/release_notes.md index fb889add2..973bb5bdb 100644 --- a/docs/release_notes.md +++ b/docs/release_notes.md @@ -20,7 +20,7 @@ Released on February 10, 2026. - Outputs Memory extraction log to the console. - Dataset - Supports batch metadata management. - - Renames "ToC (Table of Contents)" to "PageIndex". See [here](./guides/dataset/extract_table_of_contents.md). + - Renames "ToC (Table of Contents)" to "PageIndex". See [here](./guides/dataset/advanced/extract_table_of_contents.md). - Agent - Launches a new Chat-like Agent conversation management interface that retains sessions and dialogue history. - Introduces a multi-Sandbox mechanism supporting local gVisor and Alibaba Cloud, with compatibility for mainstream Sandbox APIs (configurable in the Admin page). @@ -225,7 +225,7 @@ Released on October 15, 2025. - 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). +- 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/advanced/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. @@ -480,7 +480,7 @@ From this release onwards, built-in rerank models have been removed because they #### Added documents - [Set page rank](./guides/dataset/set_page_rank.md) -- [Enable RAPTOR](./guides/dataset/enable_raptor.md) +- [Enable RAPTOR](./guides/dataset/advanced/enable_raptor.md) - [Set variables for your chat assistant](./guides/chat/set_chat_variables.md) - [Launch RAGFlow MCP server](./develop/mcp/launch_mcp_server.md) @@ -592,7 +592,7 @@ Released on February 6, 2025. ### New features - Supports DeepSeek R1 and DeepSeek V3. -- 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). +- 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](./guides/dataset/advanced/construct_knowledge_graph.md). - Adds an **Iteration** agent component and a **Research report generator** agent template. See [here](./guides/agent/agent_component_reference/iteration.mdx). - New UI language: Portuguese. - Allows setting metadata for a specific file in a dataset to enhance AI-powered chats. See [here](./guides/dataset/set_metadata.md). @@ -608,7 +608,7 @@ The **Tag dataset** feature is *unavailable* on the [Infinity](https://github.co #### Added documents -- [Construct knowledge graph](./guides/dataset/construct_knowledge_graph.md) +- [Construct knowledge graph](./guides/dataset/advanced/construct_knowledge_graph.md) - [Set metadata](./guides/dataset/set_metadata.md) - [Begin component](./guides/agent/agent_component_reference/begin.mdx) - [Generate component](./guides/agent/agent_component_reference/generate.mdx)