fixed bug with websocket and added quality improvements to ux ui and …

…research report output

README.md

@@ -44,7 +44,7 @@ https://github.com/assafelovic/gpt-researcher/assets/13554167/dd6cf08f-b31e-40c6
 
 ## 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 /> 
-The agents leverage both `gpt3.5-turbo` and `gpt-4o` (128K context) to complete a research task. We optimize for costs using each only when necessary. **The average research task takes around 3 minutes to complete, and costs ~$0.1.**
+The agents leverage both `gpt3.5-turbo` and `gpt-4o` (128K context) to complete a research task. We optimize for costs using each only when necessary. **The average research task takes around 3 minutes to complete, and costs ~$0.005.**
 
 <div align="center">
 <img align="center" height="600" src="https://github.com/assafelovic/gpt-researcher/assets/13554167/4ac896fd-63ab-4b77-9688-ff62aafcc527">
@@ -104,8 +104,8 @@ export TAVILY_API_KEY={Your Tavily API Key here}
 
 For a more permanent setup, create a `.env` file in the current `gpt-researcher` directory and input the env vars (without `export`).
 
-- For LLM provider, we recommend **[OpenAI GPT](https://platform.openai.com/docs/guides/gpt)**, but you can use any other LLM model (including open sources). To learn how to change the LLM model, please refer to the [documentation](https://docs.gptr.dev/docs/gpt-researcher/llms) page. 
-- For web search API, we recommend **[Tavily Search API](https://app.tavily.com)**, but you can also refer to other search APIs of your choice by changing the search provider in config/config.py to `duckduckgo`, `google`, `bing`, `serper`, `searx` and more. Then add the corresponding env API key.
+- For LLM, we recommend **[OpenAI GPT](https://platform.openai.com/docs/guides/gpt)**, but you can use other LLMs such as `claude`, `ollama3`, `gemini`, `mistral` and more. To learn how to change the LLM provider, see the [LLMs documentation](https://docs.gptr.dev/docs/gpt-researcher/llms) page. 
+- The default retriever is **[Tavily](https://app.tavily.com)**, but you can refer to other retrievers such as `duckduckgo`, `google`, `bing`, `serper`, `searx`, `arxiv`, `exa` and more. To learn how to change the search provider, see the [retrievers documentation](https://docs.gptr.dev/docs/gpt-researcher/retrievers) page.
 
 ### Quickstart
 

backend/report_type/basic_report/basic_report.py

@@ -12,7 +12,8 @@ def __init__(self, query: str, report_type: str, report_source:str, source_urls,
 
     async def run(self):
         # Initialize researcher
-        researcher = GPTResearcher(self.query, self.report_type, self.report_source, self.source_urls, self.config_path, self.websocket)
+        researcher = GPTResearcher(query=self.query, report_type=self.report_type, report_source=self.report_source,
+                                   source_urls=self.source_urls, config_path=self.config_path, websocket=self.websocket)
 
         # Run research
         await researcher.conduct_research()

backend/report_type/detailed_report/detailed_report.py

@@ -18,7 +18,9 @@ def __init__(self, query: str, report_type: str, report_source: str, source_urls
         self.subtopics = subtopics
 
         # A parent task assistant. Adding research_report as default
-        self.main_task_assistant = GPTResearcher(self.query, "research_report", self.report_source, self.source_urls, self.config_path, self.websocket)
+        self.main_task_assistant = GPTResearcher(query=self.query, report_type="research_report",
+                                                 report_source=self.report_source, source_urls=self.source_urls,
+                                                 config_path=self.config_path, websocket=self.websocket)
         self.existing_headers = []
         # This is a global variable to store the entire context accumulated at any point through searching and scraping
         self.global_context = []
@@ -81,13 +83,6 @@ async def fetch_report(subtopic):
         # and passed to the next subtopic report generation.
         # This is only possible to do sequentially
 
-        # tasks = [fetch_report(subtopic) for subtopic in subtopics]
-        # results = await asyncio.gather(*tasks)
-
-        # for result in filter(lambda r: r["report"], results):
-        #     subtopic_reports.append(result)
-        #     subtopics_report_body += "\n\n\n" + result["report"]
-
         for subtopic in subtopics:
             result = await fetch_report(subtopic)
             if result["report"]:
@@ -96,7 +91,7 @@ async def fetch_report(subtopic):
 
         return subtopic_reports, subtopics_report_body
 
-    async def _get_subtopic_report(self, subtopic: dict) -> tuple:
+    async def _get_subtopic_report(self, subtopic: dict) -> str:
         current_subtopic_task = subtopic.get("task")
         subtopic_assistant = GPTResearcher(
             query=current_subtopic_task,

frontend/styles.css

@@ -40,7 +40,6 @@ body {
 }
 
 .container {
-    max-width: 900px;
     margin: auto;
     padding: 20px;
     background-color: rgba(255, 255, 255, 0.1);
@@ -107,7 +106,7 @@ footer {
 .margin-div {
     margin-top: 20px;
     margin-bottom: 20px;
-    padding: 10px;
+    padding: 25px;
 }
 
 .agent_response {
@@ -124,13 +123,14 @@ footer {
     padding: 10px;
     margin-bottom: 10px;
     margin-top: 10px;
+    border-radius: 12px;
 }
 
 #reportContainer {
     background-color: rgba(255,255,255,0.1);
     border: none;
     color: #fff;
     transition: all .3s ease-in-out;
-    padding: 10px;
+    padding: 25px;
     border-radius: 12px;
 }