NextJS moved to root

README-ja_JP.md

@@ -10,6 +10,9 @@
 -  [中文](README-zh_CN.md)
 -  [日本語](README-ja_JP.md)
 
+**デモ**
+https://github.com/user-attachments/assets/7809de76-3b7d-4f89-b94e-da01b0c83723
+
 **GPT Researcher は、さまざまなタスクに対する包括的なオンラインリサーチのために設計された自律エージェントです。**
 
 このエージェントは、詳細で事実に基づいた偏りのない研究レポートを生成することができ、関連するリソース、アウトライン、およびレッスンに焦点を当てるためのカスタマイズオプションを提供します。最近の [Plan-and-Solve](https://arxiv.org/abs/2305.04091) および [RAG](https://arxiv.org/abs/2005.11401) 論文に触発され、GPT Researcher は速度、決定論、および信頼性の問題に対処し、同期操作ではなく並列化されたエージェント作業を通じてより安定したパフォーマンスと高速化を提供します。

README-zh_CN.md

@@ -10,6 +10,8 @@
 -  [中文](README-zh_CN.md)
 -  [日本語](README-ja_JP.md)
 
+**演示**
+https://github.com/user-attachments/assets/7809de76-3b7d-4f89-b94e-da01b0c83723
 
 **GPT Researcher 是一个智能体代理，专为各种任务的综合在线研究而设计。**
 

README.md

@@ -41,7 +41,7 @@ The agent can produce detailed, factual and unbiased research reports, with cust
 - Using only a selection of web sources can create bias in determining the right conclusions for research tasks.
 
 ## Demo
-https://github.com/assafelovic/gpt-researcher/assets/13554167/dd6cf08f-b31e-40c6-9907-1915f52a7110
+https://github.com/user-attachments/assets/7809de76-3b7d-4f89-b94e-da01b0c83723
 
 ## Architecture
 The main idea is to run "planner" and "execution" agents, whereas the planner generates questions to research, and the execution agents seek the most related information based on each generated research question. Finally, the planner filters and aggregates all related information and creates a research report. <br /> <br /> 

multi_agents/frontend/app/globals.css → application/app/globals.css

@@ -89,3 +89,34 @@ body {
 body {
   margin: 0px !important;
 }
+
+/* Styles for code blocks */
+pre {
+  white-space: pre-wrap;       /* CSS 3 */
+  white-space: -moz-pre-wrap;  /* Mozilla, since 1999 */
+  white-space: -pre-wrap;      /* Opera 4-6 */
+  white-space: -o-pre-wrap;    /* Opera 7 */
+  word-wrap: break-word;       /* Internet Explorer 5.5+ */
+  overflow-x: auto;
+  padding: 1rem;
+  border-radius: 4px;
+}
+
+/* Styles for inline code */
+code {
+  padding: 0.2rem 0.4rem;
+  border-radius: 3px;
+  font-family: 'Courier New', Courier, monospace;
+}
+
+/* Ensure long words don't overflow */
+p, div, span {
+  overflow-wrap: break-word;
+  word-wrap: break-word;
+  -ms-word-break: break-all;
+  word-break: break-word;
+  -ms-hyphens: auto;
+  -moz-hyphens: auto;
+  -webkit-hyphens: auto;
+  hyphens: auto;
+}

docker-compose.yml

@@ -19,10 +19,10 @@ services:
       - CHOKIDAR_USEPOLLING=true
     build:
       dockerfile: Dockerfile.dev
-      context: multi_agents/frontend
+      context: application
     volumes:
       - /app/node_modules
-      - ./multi_agents/frontend:/app
+      - ./application:/app
     restart: always
     ports:
       - 3000:3000

multi_agents/agents/human.py

@@ -14,7 +14,12 @@ async def review_plan(self, research_state: dict):
         :return:
         """
         layout = research_state.get("sections")
-        user_feedback = input(f"Any feedback on this plan? {layout}? If not, please reply with 'no'.\n>> ")
+        user_feedback = 'no'
+
+        if not self.websocket:
+            user_feedback = input(f"Any feedback on this plan? {layout}? If not, please reply with 'no'.\n>> ")
+
         if "no" in user_feedback:
             user_feedback = None
+
         return {"human_feedback": user_feedback}