Integrating RAGFlow API as a Plugin into ChatGPT-on-WeChat

intergrations/chatgpt-on-wechat/plugins/README.md

@@ -0,0 +1,57 @@
+RAGFlow Chat Plugin for ChatGPT-on-WeChat
+=========================================
+
+This folder contains the source code for the `ragflow_chat` plugin, which extends the core functionality of the RAGFlow API to support conversational interactions using Retrieval-Augmented Generation (RAG). This plugin integrates seamlessly with the [ChatGPT-on-WeChat](https://github.com/zhayujie/chatgpt-on-wechat) project, enabling WeChat and other platforms to leverage the knowledge retrieval capabilities provided by RAGFlow in chat interactions.
+
+### Features
+* **Conversational Interactions**: Combine WeChat's conversational interface with powerful RAG (Retrieval-Augmented Generation) capabilities.
+* **Knowledge-Based Responses**: Enrich conversations by retrieving relevant data from external knowledge sources and incorporating them into chat responses.
+* **Multi-Platform Support**: Works across WeChat, WeCom, and various other platforms supported by the ChatGPT-on-WeChat framework.
+
+### Plugin vs. ChatGPT-on-WeChat Configurations
+**Note**: There are two distinct configuration files used in this setup—one for the ChatGPT-on-WeChat core project and another specific to the `ragflow_chat` plugin. It is important to configure both correctly to ensure smooth integration.
+
+#### ChatGPT-on-WeChat Root Configuration (`config.json`)
+This file is located in the root directory of the [ChatGPT-on-WeChat](https://github.com/zhayujie/chatgpt-on-wechat) project and is responsible for defining the communication channels and overall behavior. For example, it handles the configuration for WeChat, WeCom, and other services like Feishu and DingTalk.
+
+Example `config.json` (for WeChat channel):
+```json
+{
+  "channel_type": "wechatmp",
+  "wechatmp_app_id": "YOUR_APP_ID",
+  "wechatmp_app_secret": "YOUR_APP_SECRET",
+  "wechatmp_token": "YOUR_TOKEN",
+  "wechatmp_port": 80,
+  ...
+}
+```
+
+This file can also be modified to support other communication platforms, such as:
+- **Personal WeChat** (`channel_type: wx`)
+- **WeChat Public Account** (`wechatmp` or `wechatmp_service`)
+- **WeChat Work (WeCom)** (`wechatcom_app`)
+- **Feishu** (`feishu`)
+- **DingTalk** (`dingtalk`)
+
+For detailed configuration options, see the official [LinkAI documentation](https://docs.link-ai.tech/cow/multi-platform/wechat-mp).
+
+#### RAGFlow Chat Plugin Configuration (`plugins/ragflow_chat/config.json`)
+This configuration is specific to the `ragflow_chat` plugin and is used to set up communication with the RAGFlow server. Ensure that your RAGFlow server is running, and update the plugin's `config.json` file with your server details:
+
+Example `config.json` (for `ragflow_chat`):
+```json
+{
+  "ragflow_api_key": "YOUR_API_KEY",
+  "ragflow_host": "127.0.0.1:80"
+}
+```
+
+This file must be configured to point to your RAGFlow instance, with the `ragflow_api_key` and `ragflow_host` fields set appropriately. The `ragflow_host` is typically your server's address and port number, and the `ragflow_api_key` is obtained from your RAGFlow API setup.
+
+### Requirements
+Before you can use this plugin, ensure the following are in place:
+
+1. You have installed and configured [ChatGPT-on-WeChat](https://github.com/zhayujie/chatgpt-on-wechat).
+2. You have deployed and are running the [RAGFlow](https://github.com/jina-ai/ragflow) server.
+
+Make sure both `config.json` files (ChatGPT-on-WeChat and RAGFlow Chat Plugin) are correctly set up as per the examples above.

intergrations/chatgpt-on-wechat/plugins/__init__.py

@@ -0,0 +1 @@
+from .ragflow_chat import *

intergrations/chatgpt-on-wechat/plugins/config.json

@@ -0,0 +1,4 @@
+{
+    "api_key": "ragflow-***",
+    "host_address": "127.0.0.1:80"
+}

intergrations/chatgpt-on-wechat/plugins/ragflow_chat.py

@@ -0,0 +1,114 @@
+import requests
+import json
+from bridge.context import Context, ContextType  # Import Context, ContextType
+from bridge.reply import Reply, ReplyType  # Import Reply, ReplyType
+from bridge import *
+from common.log import logger
+from config import conf
+from plugins import Plugin, register  # Import Plugin and register
+from plugins.event import Event, EventContext, EventAction  # Import event-related classes
+
+@register(name="RAGFlowChat", desc="Use RAGFlow API to chat", version="1.0", author="Your Name")
+class RAGFlowChat(Plugin):
+    def __init__(self):
+        super().__init__()
+        # Load plugin configuration
+        self.cfg = self.load_config()
+        # Bind event handling function
+        self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
+        # Store conversation_id for each user
+        self.conversations = {}
+        logger.info("[RAGFlowChat] Plugin initialized")
+
+    def on_handle_context(self, e_context: EventContext):
+        context = e_context['context']
+        if context.type != ContextType.TEXT:
+            return  # Only process text messages
+
+        user_input = context.content.strip()
+        session_id = context['session_id']
+
+        # Call RAGFlow API to get a reply
+        reply_text = self.get_ragflow_reply(user_input, session_id)
+        if reply_text:
+            reply = Reply()
+            reply.type = ReplyType.TEXT
+            reply.content = reply_text
+            e_context['reply'] = reply
+            e_context.action = EventAction.BREAK_PASS  # Skip the default processing logic
+        else:
+            # If no reply is received, pass to the next plugin or default logic
+            e_context.action = EventAction.CONTINUE
+
+    def get_ragflow_reply(self, user_input, session_id):
+        # Get API_KEY and host address from the configuration
+        api_key = self.cfg.get("api_key")
+        host_address = self.cfg.get("host_address")
+        user_id = session_id  # Use session_id as user_id
+
+        if not api_key or not host_address:
+            logger.error("[RAGFlowChat] Missing configuration")
+            return "The plugin configuration is incomplete. Please check the configuration."
+
+        headers = {
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json"
+        }
+
+        # Step 1: Get or create conversation_id
+        conversation_id = self.conversations.get(user_id)
+        if not conversation_id:
+            # Create a new conversation
+            url_new_conversation = f"http://{host_address}/v1/api/new_conversation"
+            params_new_conversation = {
+                "user_id": user_id
+            }
+            try:
+                response = requests.get(url_new_conversation, headers=headers, params=params_new_conversation)
+                logger.debug(f"[RAGFlowChat] New conversation response: {response.text}")
+                if response.status_code == 200:
+                    data = response.json()
+                    if data.get("retcode") == 0:
+                        conversation_id = data["data"]["id"]
+                        self.conversations[user_id] = conversation_id
+                    else:
+                        logger.error(f"[RAGFlowChat] Failed to create conversation: {data.get('retmsg')}")
+                        return f"Sorry, unable to create a conversation: {data.get('retmsg')}"
+                else:
+                    logger.error(f"[RAGFlowChat] HTTP error when creating conversation: {response.status_code}")
+                    return f"Sorry, unable to connect to RAGFlow API (create conversation). HTTP status code: {response.status_code}"
+            except Exception as e:
+                logger.exception(f"[RAGFlowChat] Exception when creating conversation: {e}")
+                return f"Sorry, an internal error occurred: {str(e)}"
+
+        # Step 2: Send the message and get a reply
+        url_completion = f"http://{host_address}/v1/api/completion"
+        payload_completion = {
+            "conversation_id": conversation_id,
+            "messages": [
+                {
+                    "role": "user",
+                    "content": user_input
+                }
+            ],
+            "quote": False,
+            "stream": False
+        }
+
+        try:
+            response = requests.post(url_completion, headers=headers, json=payload_completion)
+            logger.debug(f"[RAGFlowChat] Completion response: {response.text}")
+            if response.status_code == 200:
+                data = response.json()
+                if data.get("retcode") == 0:
+                    answer = data["data"]["answer"]
+                    return answer
+                else:
+                    logger.error(f"[RAGFlowChat] Failed to get answer: {data.get('retmsg')}")
+                    return f"Sorry, unable to get a reply: {data.get('retmsg')}"
+            else:
+                logger.error(f"[RAGFlowChat] HTTP error when getting answer: {response.status_code}")
+                return f"Sorry, unable to connect to RAGFlow API (get reply). HTTP status code: {response.status_code}"
+        except Exception as e:
+            logger.exception(f"[RAGFlowChat] Exception when getting answer: {e}")
+            return f"Sorry, an internal error occurred: {str(e)}"

intergrations/chatgpt-on-wechat/plugins/requirements.txt

@@ -0,0 +1 @@
+requests