Merge pull request assafelovic#21 from assafelovic/agent_logs

added additional agent task logs for better progress visibility

actions/web_scrape.py

@@ -18,6 +18,7 @@
 from selenium.webdriver.safari.options import Options as SafariOptions
 from selenium.webdriver.support import expected_conditions as EC
 from selenium.webdriver.support.wait import WebDriverWait
+from fastapi import WebSocket
 
 import processing.text as summary
 
@@ -32,25 +33,32 @@
 CFG = Config()
 
 
-async def async_browse(url: str, question: str) -> str:
+async def async_browse(url: str, question: str, websocket: WebSocket) -> str:
     """Browse a website and return the answer and links to the user
 
     Args:
         url (str): The url of the website to browse
         question (str): The question asked by the user
+        websocket (WebSocketManager): The websocket manager
 
     Returns:
         str: The answer and links to the user
     """
     loop = asyncio.get_event_loop()
     executor = ThreadPoolExecutor(max_workers=8)
+
     print(f"Scraping url {url} with question {question}")
+    await websocket.send_json(
+        {"type": "logs", "output": f"🔎 Browsing the {url} for relevant about: {question}..."})
 
     try:
         driver, text = await loop.run_in_executor(executor, scrape_text_with_selenium, url)
         await loop.run_in_executor(executor, add_header, driver)
         summary_text = await loop.run_in_executor(executor, summary.summarize_text, url, text, question, driver)
 
+        await websocket.send_json(
+            {"type": "logs", "output": f"📝 Information gathered from url {url}: {summary_text}"})
+
         return f"Information gathered from url {url}: {summary_text}"
     except Exception as e:
         print(f"An error occurred while processing the url {url}: {e}")

agent/research_agent.py

@@ -62,7 +62,6 @@ async def get_new_urls(self, url_set_input):
                 self.visited_urls.add(url)
                 new_urls.append(url)
 
-        await self.websocket.send_json({"type": "logs", "output": f"📝 Summarizing sources..."})
         return new_urls
 
     async def call_agent(self, action, stream=False, websocket=None):
@@ -99,8 +98,11 @@ async def async_search(self, query):
         search_results = json.loads(web_search(query))
         new_search_urls = self.get_new_urls([url.get("href") for url in search_results])
 
+        await self.websocket.send_json(
+            {"type": "logs", "output": f"🌐 Browsing the following sites for relevant information: {new_search_urls}..."})
+
         # Create a list to hold the coroutine objects
-        tasks = [async_browse(url, query,) for url in await new_search_urls]
+        tasks = [async_browse(url, query, self.websocket) for url in await new_search_urls]
 
         # Gather the results as they become available
         responses = await asyncio.gather(*tasks, return_exceptions=True)