{"id":10738910,"url":"https://github.com/gpt-open/rag-gpt","last_synced_at":"2025-11-17T03:28:44.340Z","repository":{"id":232317259,"uuid":"784026037","full_name":"gpt-open/rag-gpt","owner":"gpt-open","description":"RAG-GPT, leveraging LLM and RAG technology, learns from user-customized knowledge bases to provide contextually relevant answers for a wide range of queries, ensuring rapid and accurate information retrieval.","archived":false,"fork":false,"pushed_at":"2024-07-19T02:00:39.000Z","size":32577,"stargazers_count":429,"open_issues_count":15,"forks_count":71,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-03-29T02:03:48.917Z","etag":null,"topics":["claude","deepseek","gpt","gpt-4o","gpt-4o-mini","liama","llamaparse","llm","moonshot","nextjs","ollama","openai","python","qwen","rag","zhipuai"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gpt-open.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-04-09T03:19:04.000Z","updated_at":"2025-03-27T05:05:37.000Z","dependencies_parsed_at":"2024-12-08T06:13:20.776Z","dependency_job_id":null,"html_url":"https://github.com/gpt-open/rag-gpt","commit_stats":{"total_commits":114,"total_committers":5,"mean_commits":22.8,"dds":0.1842105263157895,"last_synced_commit":"da1548e22ab05a7619cf6a3a6777d58893f61da8"},"previous_names":["open-kf/smart-qa-service","open-kf/rag-gpt","gpt-open/rag-gpt"],"tags_count":4,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gpt-open%2Frag-gpt","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gpt-open%2Frag-gpt/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gpt-open%2Frag-gpt/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gpt-open%2Frag-gpt/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gpt-open","download_url":"https://codeload.github.com/gpt-open/rag-gpt/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247280262,"owners_count":20912967,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["claude","deepseek","gpt","gpt-4o","gpt-4o-mini","liama","llamaparse","llm","moonshot","nextjs","ollama","openai","python","qwen","rag","zhipuai"],"created_at":"2024-06-04T23:04:31.662Z","updated_at":"2025-11-17T03:28:39.319Z","avatar_url":"https://github.com/gpt-open.png","language":"Python","funding_links":[],"categories":["Python","A01_文本生成_文本对话","NLP"],"sub_categories":["大语言对话模型及数据"],"readme":"\u003cdiv align=\"center\"\u003e\n\u003ch1 align=\"center\"\u003eRAG-GPT\u003c/h1\u003e\nQuickly launch an intelligent customer service system with Flask, LLM, RAG, including frontend, backend, and admin console.\n\u003cbr/\u003e\n\u003ca href=\"https://langchain-bot.open-sora.ai/\" target=\"_blank\"\u003e Live Demo \u003c/a\u003e\n\u003cbr/\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/rag_overview.jpg\"\u003e\n\u003c/div\u003e\n\n\n# Contents\n\n- [Features](#features)\n- [Online Retrieval Architecture](#online-retrieval-architecture)\n- [Deploy the RAG-GPT Service](#deploy-the-rag-gpt-service)\n  - [Step 1: Download repository code](#step-1-download-repository-code)\n  - [Step 2: Configure variables of .env](#step-2-configure-variables-of-env)\n    - [Using OpenAI as the LLM base](#using-openai-as-the-llm-base)\n    - [Using ZhipuAI as the LLM base](#using-zhipuai-as-the-llm-base)\n    - [Using DeepSeek as the LLM base](#using-deepseek-as-the-llm-base)\n    - [Using Moonshot as the LLM base](#using-moonshot-as-the-llm-base)\n    - [Using local LLMs](#using-local-llms)\n  - [Step 3: Deploy RAG-GPT](#step-3-deploy-rag-gpt)\n    - [Deploy RAG-GPT using Docker](#deploy-rag-gpt-using-docker)\n    - [Deploy RAG-GPT from source code](#deploy-rag-gpt-from-source-code)\n      - [Set up the Python running environment](#set-up-the-python-running-environment)\n        - [Create and activate a virtual environment](#create-and-activate-a-virtual-environment)\n        - [Install dependencies with pip](#install-dependencies-with-pip)\n      - [Create SQLite Database](#create-sqlite-database)\n      - [Start the service](#start-the-service)\n- [Configure the admin console](#configure-the-admin-console)\n  - [Login to the admin console](#login-to-the-admin-console)\n  - [Import your data](#import-your-data)\n    - [import websites](#import-websites)\n    - [import isolated urls](#import-isolated-urls)\n    - [import local files](#import-local-files)\n  - [Test the chatbot](#test-the-chatbot)\n  - [Embed on your website](#embed-on-your-website)\n  - [Dashboard of user's historical request](#dashboard-of-users-historical-request)\n- [The frontend of admin console and chatbot](#the-frontend-of-admin-console-and-chatbot)\n  - [admin console](#admin-console)\n  - [chatbot](#chatbot)\n\n\n## Features\n- **Built-in LLM Support**: Support cloud-based LLMs and local LLMs.\n- **Quick Setup**: Enables deployment of production-level conversational service robots within just five minutes.\n- **Diverse Knowledge Base Integration**: Supports multiple types of knowledge bases, including websites, isolated URLs, and local files.\n- **Flexible Configuration**: Offers a user-friendly backend equipped with customizable settings for streamlined management.\n- **Attractive UI**: Features a customizable and visually appealing user interface.\n\n\n## Online Retrieval Architecture\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 100%;\" src=\"./doc/online_retrieve.jpg\"\u003e\n\u003c/div\u003e\n\n\n## Deploy the RAG-GPT Service\n\n### Step 1: Download repository code\n\nClone the repository:\n\n```shell\ngit clone https://github.com/open-kf/rag-gpt.git \u0026\u0026 cd rag-gpt\n```\n\n### Step 2: Configure variables of .env\n\nBefore starting the RAG-GPT service, you need to modify the related configurations for the program to initialize correctly. \n\n#### Using OpenAI as the LLM base\n\n```shell\ncp env_of_openai .env\n```\n\nThe variables in .env\n\n```shell\nLLM_NAME=\"OpenAI\"\nOPENAI_API_KEY=\"xxxx\"\nGPT_MODEL_NAME=\"gpt-4o-mini\"\nMIN_RELEVANCE_SCORE=0.4\nBOT_TOPIC=\"xxxx\"\nURL_PREFIX=\"http://127.0.0.1:7000/\"\nUSE_PREPROCESS_QUERY=1\nUSE_RERANKING=1\nUSE_DEBUG=0\nUSE_LLAMA_PARSE=0\nLLAMA_CLOUD_API_KEY=\"xxxx\"\nUSE_GPT4O=0\n```\n\n- Don't modify **`LLM_NAME`**\n- Modify the **`OPENAI_API_KEY`** with your own key. Please log in to the [OpenAI website](https://platform.openai.com/api-keys) to view your API Key.\n- Update the **`GPT_MODEL_NAME`** setting, replacing `gpt-4o-mini` with `gpt-4-turbo` or `gpt-4o` if you want to use GPT-4.\n- Change **`BOT_TOPIC`** to reflect your Bot's name. This is very important, as it will be used in `Prompt Construction`. Please try to use a concise and clear word, such as `OpenIM`, `LangChain`.\n- Adjust **`URL_PREFIX`** to match your website's domain. This is mainly for generating accessible URL links for uploaded local files. Such as `http://127.0.0.1:7000/web/download_dir/2024_05_20/d3a01d6a-90cd-4c2a-b926-9cda12466caf/openssl-cookbook.pdf`.\n- Set **`USE_LLAMA_PARSE`** to 1 if you want to use `LlamaParse`.\n- Modify the **`LLAMA_CLOUD_API_KEY `** with your own key. Please log in to the [LLamaCloud website](https://cloud.llamaindex.ai/api-key) to view your API Key.\n- Set **`USE_GPT4O`** to 1 if you want to use `GPT-4o` mode.\n- For more information about the meanings and usages of constants, you can check under the `server/constant` directory.\n\n#### Using ZhipuAI as the LLM base\n\nIf you cannot use OpenAI's API services, consider using ZhipuAI as an alternative. \n\n\n```shell\ncp env_of_zhipuai .env\n```\n\nThe variables in .env\n\n```shell\nLLM_NAME=\"ZhipuAI\"\nZHIPUAI_API_KEY=\"xxxx\"\nGLM_MODEL_NAME=\"glm-4-air\"\nMIN_RELEVANCE_SCORE=0.4\nBOT_TOPIC=\"xxxx\"\nURL_PREFIX=\"http://127.0.0.1:7000/\"\nUSE_PREPROCESS_QUERY=1\nUSE_RERANKING=1\nUSE_DEBUG=0\nUSE_LLAMA_PARSE=0\nLLAMA_CLOUD_API_KEY=\"xxxx\"\n```\n\n- Don't modify **`LLM_NAME`**\n- Modify the **`ZHIPUAI_API_KEY`** with your own key. Please log in to the [ZhipuAI website](https://open.bigmodel.cn/usercenter/apikeys) to view your API Key.\n- Update the **`GLM_MODEL_NAME`** setting, the model list is `['glm-3-turbo', 'glm-4', 'glm-4-0520', 'glm-4-air', 'glm-4-airx', 'glm-4-flash']`.\n- Change **`BOT_TOPIC`** to reflect your Bot's name. This is very important, as it will be used in `Prompt Construction`. Please try to use a concise and clear word, such as `OpenIM`, `LangChain`.\n- Adjust **`URL_PREFIX`** to match your website's domain. This is mainly for generating accessible URL links for uploaded local files. Such as `http://127.0.0.1:7000/web/download_dir/2024_05_20/d3a01d6a-90cd-4c2a-b926-9cda12466caf/openssl-cookbook.pdf`.\n- Set **`USE_LLAMA_PARSE`** to 1 if you want to use `LlamaParse`.\n- Modify the **`LLAMA_CLOUD_API_KEY `** with your own key. Please log in to the [LLamaCloud website](https://cloud.llamaindex.ai/api-key) to view your API Key.\n- For more information about the meanings and usages of constants, you can check under the `server/constant` directory.\n\n#### Using DeepSeek as the LLM base\n\nIf you cannot use OpenAI's API services, consider using DeepSeek as an alternative.\n\n\u003e [!NOTE]\n\u003e DeepSeek does not provide an `Embedding API`, so here we use ZhipuAI's `Embedding API`.\n\n\n```shell\ncp env_of_deepseek .env\n```\n\nThe variables in .env\n\n```shell\nLLM_NAME=\"DeepSeek\"\nZHIPUAI_API_KEY=\"xxxx\"\nDEEPSEEK_API_KEY=\"xxxx\"\nDEEPSEEK_MODEL_NAME=\"deepseek-chat\"\nMIN_RELEVANCE_SCORE=0.4\nBOT_TOPIC=\"xxxx\"\nURL_PREFIX=\"http://127.0.0.1:7000/\"\nUSE_PREPROCESS_QUERY=1\nUSE_RERANKING=1\nUSE_DEBUG=0\nUSE_LLAMA_PARSE=0\nLLAMA_CLOUD_API_KEY=\"xxxx\"\n```\n\n- Don't modify **`LLM_NAME`**\n- Modify the **`ZHIPUAI_API_KEY`** with your own key. Please log in to the [ZhipuAI website](https://open.bigmodel.cn/usercenter/apikeys) to view your API Key.\n- Modify the **`DEEPKSEEK_API_KEY`** with your own key. Please log in to the [DeepSeek website](https://platform.deepseek.com/api_keys) to view your API Key.\n- Update the **`DEEPSEEK_MODEL_NAME `** setting if you want to use other models of DeepSeek.\n- Change **`BOT_TOPIC`** to reflect your Bot's name. This is very important, as it will be used in `Prompt Construction`. Please try to use a concise and clear word, such as `OpenIM`, `LangChain`.\n- Adjust **`URL_PREFIX`** to match your website's domain. This is mainly for generating accessible URL links for uploaded local files. Such as `http://127.0.0.1:7000/web/download_dir/2024_05_20/d3a01d6a-90cd-4c2a-b926-9cda12466caf/openssl-cookbook.pdf`.\n- Set **`USE_LLAMA_PARSE`** to 1 if you want to use `LlamaParse`.\n- Modify the **`LLAMA_CLOUD_API_KEY `** with your own key. Please log in to the [LLamaCloud website](https://cloud.llamaindex.ai/api-key) to view your API Key.\n- For more information about the meanings and usages of constants, you can check under the `server/constant` directory.\n\n\n#### Using Moonshot as the LLM base\n\nIf you cannot use OpenAI's API services, consider using Moonshot as an alternative.\n\n\u003e [!NOTE]\n\u003e Moonshot does not provide an `Embedding API`, so here we use ZhipuAI's `Embedding API`.\n\n\n```shell\ncp env_of_moonshot .env\n```\n\nThe variables in .env\n\n```shell\nLLM_NAME=\"Moonshot\"\nZHIPUAI_API_KEY=\"xxxx\"\nMOONSHOT_API_KEY=\"xxxx\"\nMOONSHOT_MODEL_NAME=\"moonshot-v1-8k\"\nMIN_RELEVANCE_SCORE=0.4\nBOT_TOPIC=\"xxxx\"\nURL_PREFIX=\"http://127.0.0.1:7000/\"\nUSE_PREPROCESS_QUERY=1\nUSE_RERANKING=1\nUSE_DEBUG=0\nUSE_LLAMA_PARSE=0\nLLAMA_CLOUD_API_KEY=\"xxxx\"\n```\n\n- Don't modify **`LLM_NAME`**\n- Modify the **`ZHIPUAI_API_KEY`** with your own key. Please log in to the [ZhipuAI website](https://open.bigmodel.cn/usercenter/apikeys) to view your API Key.\n- Modify the **`MOONSHOT_API_KEY`** with your own key. Please log in to the [Moonshot website](https://platform.moonshot.cn/console/api-keys) to view your API Key.\n- Update the **`MOONSHOT_MODEL_NAME `** setting if you want to use other models of Moonshot.\n- Change **`BOT_TOPIC`** to reflect your Bot's name. This is very important, as it will be used in `Prompt Construction`. Please try to use a concise and clear word, such as `OpenIM`, `LangChain`.\n- Adjust **`URL_PREFIX`** to match your website's domain. This is mainly for generating accessible URL links for uploaded local files. Such as `http://127.0.0.1:7000/web/download_dir/2024_05_20/d3a01d6a-90cd-4c2a-b926-9cda12466caf/openssl-cookbook.pdf`.\n- Set **`USE_LLAMA_PARSE`** to 1 if you want to use `LlamaParse`.\n- Modify the **`LLAMA_CLOUD_API_KEY `** with your own key. Please log in to the [LLamaCloud website](https://cloud.llamaindex.ai/api-key) to view your API Key.\n- For more information about the meanings and usages of constants, you can check under the `server/constant` directory.\n\n\n#### Using local LLMs\n\nIf your knowledge base involves **sensitive information** and you prefer not to use cloud-based LLMs, consider using `Ollama` to deploy large models locally.\n\n\n\u003e [!NOTE]\n\u003e First, refer to [ollama](https://github.com/ollama/ollama) to **Install Ollama**, and download the embedding model `mxbai-embed-large` and the LLM model such as `llama3`.\n\n\n```shell\ncp env_of_ollama .env\n```\n\nThe variables in .env\n\n```shell\nLLM_NAME=\"Ollama\"\nOLLAMA_MODEL_NAME=\"xxxx\"\nOLLAMA_BASE_URL=\"http://127.0.0.1:11434\"\nMIN_RELEVANCE_SCORE=0.4\nBOT_TOPIC=\"xxxx\"\nURL_PREFIX=\"http://127.0.0.1:7000/\"\nUSE_PREPROCESS_QUERY=1\nUSE_RERANKING=1\nUSE_DEBUG=0\nUSE_LLAMA_PARSE=0\nLLAMA_CLOUD_API_KEY=\"xxxx\"\n```\n\n- Don't modify **`LLM_NAME`**\n- Update the **`OLLAMA_MODEL_NAME `** setting, select an appropriate model from [ollama library](https://ollama.com/library).\n- If you have changed the default `IP:PORT` when starting `Ollama`, please update **`OLLAMA_BASE_URL`**. Please pay special attention, only enter the IP (domain) and PORT here, without appending a URI.\n- Change **`BOT_TOPIC`** to reflect your Bot's name. This is very important, as it will be used in `Prompt Construction`. Please try to use a concise and clear word, such as `OpenIM`, `LangChain`.\n- Adjust **`URL_PREFIX`** to match your website's domain. This is mainly for generating accessible URL links for uploaded local files. Such as `http://127.0.0.1:7000/web/download_dir/2024_05_20/d3a01d6a-90cd-4c2a-b926-9cda12466caf/openssl-cookbook.pdf`.\n- Set **`USE_LLAMA_PARSE`** to 1 if you want to use `LlamaParse`.\n- Modify the **`LLAMA_CLOUD_API_KEY `** with your own key. Please log in to the [LLamaCloud website](https://cloud.llamaindex.ai/api-key) to view your API Key.\n- For more information about the meanings and usages of constants, you can check under the `server/constant` directory.\n\n\n### Step 3: Deploy RAG-GPT\n#### Deploy RAG-GPT using Docker\n\n\u003e [!NOTE]\n\u003e When deploying with Docker, pay special attention to the host of **URL_PREFIX** in the `.env` file. If using `Ollama`, also pay special attention to the host of **OLLAMA_BASE_URL** in the `.env` file. They need to use the actual IP address of the host machine.\n\n\n```shell\ndocker-compose up --build\n```\n\n#### Deploy RAG-GPT from source code\n\n\u003e [!NOTE]\n\u003e Please use Python version 3.10.x or above.\n\n##### Set up the Python running environment\n\nIt is recommended to install Python-related dependencies in a Python virtual environment to avoid affecting dependencies of other projects.\n\n###### Create and activate a virtual environment\n\nIf you have not yet created a virtual environment, you can create one with the following command:\n\n```shell\npython3 -m venv myenv\n```\n\nAfter creation, activate the virtual environment:\n\n```shell\nsource myenv/bin/activate\n```\n\n###### Install dependencies with pip\n\nOnce the virtual environment is activated, you can use `pip` to install the required dependencies. \n\n```shell\npip install -r requirements.txt\n```\n\n##### Create SQLite Database\n\nThe RAG-GPT service uses SQLite as its storage DB. Before starting the RAG-GPT service, you need to execute the following command to initialize the database and add the default configuration for admin console.\n\n```shell\npython3 create_sqlite_db.py\n```\n\n##### Start the service\n\nIf you have completed the steps above, you can try to start the RAG-GPT service by executing the following command.\n\n- **Start single process:**\n\n```shell\npython3 rag_gpt_app.py\n```\n\n- **Start multiple processes:**\n\n```shell\nsh start.sh\n```\n\n\u003e [!NOTE]\n\u003e - The service port for RAG-GPT is **`7000`**. During the first test, please try not to change the port so that you can quickly experience the entire product process.\n\u003e - We recommend starting the RAG-GPT service using **`start.sh`** in multi-process mode for a smoother user experience.\n\n\n\n## Configure the admin console\n\n### Login to the admin console\n\nAccess the admin console through the link **`http://your-server-ip:7000/open-kf-admin/`** to reach the login page. The default username and password are **`admin`** and **`open_kf_AIGC@2024`** (can be checked in `create_sqlite_db.py`).\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-2.jpg\"\u003e\n\u003c/div\u003e\n\nAfter logging in successfully, you will be able to see the configuration page of the admin console.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-3.jpg\"\u003e\n\u003c/div\u003e\n\nOn the page **`http://your-server-ip:7000/open-kf-admin/#/`**, you can set the following configurations:\n- Choose the LLM base, currently only the `gpt-3.5-turbo` option is available, which will be gradually expanded.\n- Initial Messages\n- Suggested Messages\n- Message Placeholder\n- Profile Picture (upload a picture)\n- Display name\n- Chat icon (upload a picture)\n\n### Import your data\n\n#### Import websites\n\nAfter submitting the website URL, once the server retrieves the list of all web page URLs via crawling, you can select the web page URLs you need as the knowledge base (all selected by default). The initial `Status` is **`Recorded`**.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-12.jpg\"\u003e\n\u003c/div\u003e\n\nYou can actively refresh the page **`http://your-server-ip:7000/open-kf-admin/#/source`** in your browser to get the progress of web page URL processing. After the content of the web page URL has been crawled, and the Embedding calculation and storage are completed, you can see the corresponding `Size` in the admin console, and the `Status` will also be updated to **`Trained`**.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-13.jpg\"\u003e\n\u003c/div\u003e\n\nClicking on a webpage's URL reveals how many sub-pages the webpage is divided into, and the text size of each sub-page.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-10.jpg\"\u003e\n\u003c/div\u003e\n\nClicking on a sub-page allows you to view its full text content. This will be very helpful for verifying the effects during the experience testing process.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-11.jpg\"\u003e\n\u003c/div\u003e\n\n#### Import isolated urls\n\nCollect the URLs of the required web pages. You can submit up to `10` web page URLs at a time, and these pages can be from different domains.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-14.jpg\"\u003e\n\u003c/div\u003e\n\n#### Import local files\n\nUpload the required local files. You can upload up to `10` files at a time, and each file cannot exceed `30MB`. The following file types are currently supported: `[\".txt\", \".md\", \".pdf\", \".epub\", \".mobi\", \".html\", \".docx\", \".pptx\", \".xlsx\", \".csv\"]`.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-15.jpg\"\u003e\n\u003c/div\u003e\n\n\n### Test the chatbot\n\nAfter importing website data in the admin console, you can experience the chatbot service through the link **`http://your-server-ip:7000/open-kf-chatbot/`**.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-6.jpg\"\u003e\n\u003c/div\u003e\n\n### Embed on your website\n\nThrough the admin console link **`http://your-server-ip:7000/open-kf-admin/#/embed`**, you can see the detailed tutorial for configuring the iframe in your website.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-7.jpg\"\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n\u003cbr/\u003e\n\u003ca href=\"https://docs.openim.io/\" target=\"_blank\"\u003e OpenIM chatbot \u003c/a\u003e\n\u003cbr/\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-8.jpg\"\u003e\n\u003c/div\u003e\n\n### Dashboard of user's historical request\n\nThrough the admin console link **`http://your-server-ip:7000/open-kf-admin/#/dashboard`**, you can view the historical request records of all users within a specified time range.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg style=\"display: block; margin: auto; width: 70%;\" src=\"./doc/screenshot-9.jpg\"\u003e\n\u003c/div\u003e\n\n\n## The frontend of admin console and chatbot\nThe RAG-GPT service integrates 2 frontend modules, and their source code information is as follows:\n\n### admin console\n\u003e [Code Repository](https://github.com/open-kf/smart-qa-admin)\n\nAn intuitive web-based admin interface for Smart QA Service, offering comprehensive control over content, configuration, and user interactions. Enables effortless management of the knowledge base, real-time monitoring of queries and feedback, and continuous improvement based on user insights.\n\n### chatbot\n\u003e [Code Repository](https://github.com/open-kf/smart-qa-h5)\n\nAn HTML5 interface for Smart QA Service designed for easy integration into websites via iframe, providing users direct access to a tailored knowledge base without leaving the site, enhancing functionality and immediate query resolution.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgpt-open%2Frag-gpt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgpt-open%2Frag-gpt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgpt-open%2Frag-gpt/lists"}