Shreyas094 commited on
Commit
69ddd17
1 Parent(s): 90e8b4f

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -8
app.py CHANGED
@@ -22,6 +22,8 @@ from dotenv import load_dotenv
22
  import certifi
23
  from bs4 import BeautifulSoup
24
  import requests
 
 
25
 
26
  # Load environment variables from a .env file
27
  load_dotenv()
@@ -253,7 +255,7 @@ Remember to focus on financial aspects and implications in your assessment and s
253
  logger.error(f"Error assessing relevance and summarizing with LLM: {e}")
254
  return "Error: Unable to assess relevance and summarize"
255
 
256
- def scrape_full_content(url, scraper="trafilatura", max_chars=3000, timeout=5):
257
  try:
258
  logger.info(f"Scraping full content from: {url}")
259
 
@@ -319,12 +321,7 @@ Your response should be detailed, informative, accurate, and directly relevant t
319
  logger.error(f"Error in LLM summarization: {e}")
320
  return "Error: Unable to generate a summary. Please try again."
321
 
322
- import requests
323
- from trafilatura import extract
324
- from trafilatura.settings import use_config
325
- from urllib.request import urlopen, Request
326
-
327
- def search_and_scrape(query, chat_history, num_results=5, scraper="trafilatura", max_chars=3000, time_range="", language="all", category="",
328
  engines=[], safesearch=2, method="GET", llm_temperature=0.2, timeout=5):
329
  try:
330
  # Step 1: Rephrase the Query
@@ -561,7 +558,7 @@ iface = gr.ChatInterface(
561
  description="Enter your query, and I'll search the web for the most recent and relevant financial news, scrape content, and provide summarized results.",
562
  additional_inputs=[
563
  gr.Slider(5, 20, value=10, step=1, label="Number of initial results"),
564
- gr.Dropdown(["bs4", "trafilatura"], value="trafilatura", label="Scraping Method"),
565
  gr.Slider(500, 10000, value=1500, step=100, label="Max characters to retrieve"),
566
  gr.Dropdown(["", "day", "week", "month", "year"], value="year", label="Time Range"),
567
  gr.Dropdown(["all", "en", "fr", "de", "es", "it", "nl", "pt", "pl", "ru", "zh"], value="en", label="Language"),
 
22
  import certifi
23
  from bs4 import BeautifulSoup
24
  import requests
25
+ from trafilatura.settings import use_config
26
+ from urllib.request import urlopen, Request
27
 
28
  # Load environment variables from a .env file
29
  load_dotenv()
 
255
  logger.error(f"Error assessing relevance and summarizing with LLM: {e}")
256
  return "Error: Unable to assess relevance and summarize"
257
 
258
+ def scrape_full_content(url, scraper="bs4", max_chars=3000, timeout=5):
259
  try:
260
  logger.info(f"Scraping full content from: {url}")
261
 
 
321
  logger.error(f"Error in LLM summarization: {e}")
322
  return "Error: Unable to generate a summary. Please try again."
323
 
324
+ def search_and_scrape(query, chat_history, num_results=5, scraper="bs4", max_chars=3000, time_range="", language="all", category="",
 
 
 
 
 
325
  engines=[], safesearch=2, method="GET", llm_temperature=0.2, timeout=5):
326
  try:
327
  # Step 1: Rephrase the Query
 
558
  description="Enter your query, and I'll search the web for the most recent and relevant financial news, scrape content, and provide summarized results.",
559
  additional_inputs=[
560
  gr.Slider(5, 20, value=10, step=1, label="Number of initial results"),
561
+ gr.Dropdown(["bs4", "trafilatura"], value="bs4", label="Scraping Method"),
562
  gr.Slider(500, 10000, value=1500, step=100, label="Max characters to retrieve"),
563
  gr.Dropdown(["", "day", "week", "month", "year"], value="year", label="Time Range"),
564
  gr.Dropdown(["all", "en", "fr", "de", "es", "it", "nl", "pt", "pl", "ru", "zh"], value="en", label="Language"),