@tiger16601/n8n-nodes-fastgpt

Overview

Integrates with FastGPT, an AI knowledge base and Q&A platform that helps teams build custom AI assistants. This package connects n8n workflows to FastGPT for conversational AI, knowledge base management, and analytics.

Nodes & Operations

FastGPT

Connects to the FastGPT platform to manage conversations, chat history, knowledge bases, and application analytics.

• 对话 · 多模态对话 — Sends a chat request to a FastGPT app via POST /v1/chat/completions (OpenAI-compatible), building the messages array from text, image URLs and document URLs, and returns the API response.
• 对话 · 请求插件 — Calls a FastGPT plugin-type app by POSTing to /v1/chat/completions with stream disabled, passing plugin inputs as variables.
• 对话 · 获取历史记录列表 — Fetches a paginated list of chat history entries for a FastGPT app via POST /core/chat/history/getHistories, optionally filtered by conversation source.
• 对话 · 修改历史记录标题 — Renames an existing FastGPT chat history by sending a PUT to /core/chat/history/updateHistory with the app ID, chat ID and a new custom title.
• 对话 · 修改历史记录置顶状态 — Pins or unpins a FastGPT chat history by sending a PUT request to /core/chat/history/updateHistory with the app ID, chat ID and a top flag.
• 对话 · 删除单个历史记录 — Deletes a single chat history (conversation) of a FastGPT app by sending a DELETE request to /core/chat/history/delHistory with the app ID and chat ID as query parameters.
• 对话 · 清空应用历史记录 — Deletes all chat history records for a given FastGPT app by sending a DELETE request to /core/chat/history/clearHistories with the app ID as a query parameter.
• 对话 · 获取会话框基本信息 — Fetches the chat-box initialization info for a FastGPT app (such as welcome text and variables) via a GET request to /core/chat/init, optionally loading an existing chat session.
• 对话 · 获取对话记录列表 — Fetches a paginated list of individual message records within a specific FastGPT chat (conversation), optionally including user custom feedback, by POSTing to /core/chat/getPaginationRecords.
• 对话 · 获取单个对话记录运行详情 — Fetches the detailed runtime data (such as per-node outputs) for a single chat record in a FastGPT app. It sends a GET request to /core/chat/getResData with the app, chat and record IDs.
• 对话 · 删除对话记录 — Deletes a single message record from a FastGPT chat conversation by sending a DELETE request to /core/chat/record/delete with the app ID, chat ID, and record (content) ID as query parameters.
• 对话 · 点赞/取消点赞 — Sets or clears a "like" (thumbs-up) on a specific FastGPT chat record by POSTing to /core/chat/feedback/updateUserFeedback. Providing a value in the like field adds the like; leaving it empty removes it.
• 对话 · 点踩/取消点踩 — Marks a FastGPT chat record as disliked, or clears an existing dislike, by POSTing to /core/chat/feedback/updateUserFeedback. Sending a value in the dislike field sets the dislike, and leaving it empty clears it.
• 对话 · 猜你想问 — Generates suggested follow-up questions ("猜你想问") for an existing FastGPT conversation by POSTing to /core/ai/agent/v2/createQuestionGuide. The model and prompt can be overridden, or the app's latest published config is used.
• 知识库 · 获取知识库列表 — Lists the knowledge bases (datasets) and folders in FastGPT under a given parent folder, or at the root if none is given, by calling POST /core/dataset/list.
• 知识库 · 获取知识库详情 — Fetches the details of a single FastGPT knowledge base (dataset) by ID by sending a GET request to /core/dataset/detail.
• 知识库 · 删除一个知识库 — Deletes a FastGPT knowledge base (dataset) by ID by sending a DELETE request to /core/dataset/delete.
• 知识库 · 创建一个知识库 — Creates a FastGPT knowledge base or folder by sending a POST to /core/dataset/create with a name, optional intro and avatar, and optional model settings.
• 知识库 · 知识库检索 — Runs a test search against a chosen FastGPT knowledge base (POST /core/dataset/searchTest) and returns the recall results for the query text. Supports semantic, full-text, or hybrid search with optional ReRank and query rewriting.
• 知识库 · 创建训练订单 — Creates a FastGPT knowledge base training order (billing usage record) by POSTing to /support/wallet/usage/createTrainingUsage. The response carries a billId that you can pass to the "推送数据到训练队列" operation so that training data is aggregated under a single bill.
• 集合 · 创建一个空的集合 — Creates an empty collection in a FastGPT knowledge base, either as a folder or as a virtual (manual) collection, by POSTing to /core/dataset/collection/create.
• 集合 · 创建一个纯文本集合 — Creates a FastGPT dataset collection from pasted plain text by POSTing to /core/dataset/collection/create/text; FastGPT splits the text into chunks or QA pairs for training.
• 集合 · 创建一个链接集合 — Creates a FastGPT knowledge-base collection from a web URL by POSTing to /core/dataset/collection/create/link. FastGPT fetches the page, extracts its text and splits it into chunks or QA pairs for training.
• 集合 · 创建一个文件集合 — Uploads a binary file from the incoming n8n item to FastGPT and creates a dataset collection from it. FastGPT reads the file and splits it into chunks, via POST /core/dataset/collection/create/localFile.
• 集合 · 通过API数据集创建集合(V1) — Creates a FastGPT knowledge-base collection from a file already present in a FastGPT API dataset, by POSTing the file ID to /core/dataset/collection/create/apiCollection with chunking or QA-split training settings.
• 集合 · 创建一个外部文件库集合（商业版） — Creates a FastGPT dataset collection from an external file URL (commercial-edition feature) by POSTing to /proApi/core/dataset/collection/create/externalFileUrl. FastGPT downloads the file and splits it according to the chosen training settings.
• 集合 · 获取集合列表 — Lists collections (files and folders) inside a FastGPT knowledge base via POST /core/dataset/collection/listV2, with offset pagination and optional fuzzy search.
• 集合 · 获取集合详情 — Fetches the details of a single FastGPT knowledge-base collection by ID via GET /core/dataset/collection/detail, and throws a node error if the API reports a failure.
• 集合 · 删除一个集合 — Deletes one or more collections from a FastGPT knowledge base by sending a DELETE request to /core/dataset/collection/delete with a comma-separated list of collection IDs.
• 集合 · 更新集合信息 — Updates a FastGPT dataset collection's metadata (name, tags, parent folder, disabled flag, creation time) by POSTing to /core/dataset/collection/update. The collection is identified either by collection ID or by dataset ID plus external file ID.
• 数据 · 获取数据列表 — Fetches a paginated list of data entries (q/a records) in a FastGPT knowledge-base collection, with optional fuzzy keyword search, by calling POST /core/dataset/data/v2/list.
• 数据 · 获取单条数据详情 — Fetches the full details of a single FastGPT knowledge-base data entry by its data ID, via a GET request to /core/dataset/data/detail.
• 数据 · 删除单条数据 — Deletes a single data entry from a FastGPT knowledge-base collection by sending a DELETE request to /core/dataset/data/delete with the data ID as a query parameter.
• 数据 · 更新单条数据 — Updates a single data entry in a FastGPT knowledge-base collection by sending a PUT request to /core/dataset/data/update with the new content, indexes and metadata.
• 数据 · 推送数据到训练队列 — Pushes a batch of up to 200 q/a records into a FastGPT knowledge-base collection's training queue for vectorization, via POST /core/dataset/data/pushData.
• 应用 · 获取应用总体数据统计 — Fetches overall statistics for a single FastGPT app by sending a GET request to the commercial-edition endpoint /proApi/core/app/logs/getTotalData with the app ID as a query parameter.
• 应用 · 获取应用图表数据 — Fetches chart/time-series statistics for a FastGPT app by POSTing to the commercial-edition endpoint /proApi/core/app/logs/getChartData, filtered by date range, log sources, and per-metric time granularity.

Installation

Install as an n8n community node: in n8n, open Settings → Community nodes → Install and enter @tiger16601/n8n-nodes-fastgpt.

Links

• n8n community nodes installation guide