Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -1,7 +1,9 @@
|
|
1 |
import nest_asyncio
|
2 |
import json
|
|
|
|
|
|
|
3 |
from scrapegraphai.graphs import SearchGraph
|
4 |
-
import streamlit as st # This import is necessary to access secrets in Streamlit
|
5 |
|
6 |
# Apply necessary settings for asyncio compatibility in Jupyter/Streamlit environments
|
7 |
nest_asyncio.apply()
|
@@ -9,28 +11,51 @@ nest_asyncio.apply()
|
|
9 |
# Access your API keys securely
|
10 |
OPENAI_API_KEY = st.secrets["OPENAI_API_KEY"]
|
11 |
|
12 |
-
#
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
import nest_asyncio
|
2 |
import json
|
3 |
+
import streamlit as st # This import is necessary to access secrets and for the web interface
|
4 |
+
from selenium import webdriver
|
5 |
+
from chromedriver_binary import add_chromedriver_to_path
|
6 |
from scrapegraphai.graphs import SearchGraph
|
|
|
7 |
|
8 |
# Apply necessary settings for asyncio compatibility in Jupyter/Streamlit environments
|
9 |
nest_asyncio.apply()
|
|
|
11 |
# Access your API keys securely
|
12 |
OPENAI_API_KEY = st.secrets["OPENAI_API_KEY"]
|
13 |
|
14 |
+
# Selenium setup function
|
15 |
+
def setup_selenium():
|
16 |
+
add_chromedriver_to_path()
|
17 |
+
options = webdriver.ChromeOptions()
|
18 |
+
options.add_argument("--headless")
|
19 |
+
options.add_argument("--no-sandbox")
|
20 |
+
options.add_argument("--disable-dev-shm-usage")
|
21 |
+
driver = webdriver.Chrome(options=options)
|
22 |
+
return driver
|
23 |
+
|
24 |
+
def get_web_page_title(url):
|
25 |
+
driver = setup_selenium()
|
26 |
+
driver.get(url)
|
27 |
+
title = driver.title
|
28 |
+
driver.quit()
|
29 |
+
return title
|
30 |
+
|
31 |
+
st.title("Hybrid AI and Web Scraping Application")
|
32 |
+
url = st.text_input("Enter the URL to scrape for title")
|
33 |
+
|
34 |
+
if st.button("Scrape for Title"):
|
35 |
+
title = get_web_page_title(url)
|
36 |
+
st.write(f"The title of the page is: {title}")
|
37 |
+
|
38 |
+
query_prompt = st.text_input("Enter your AI query", value="List me all the attributes of 'cannabis strain'.")
|
39 |
+
|
40 |
+
if st.button("Fetch Data from AI"):
|
41 |
+
# Define the configuration for the graph based on user input
|
42 |
+
graph_config = {
|
43 |
+
"llm": {
|
44 |
+
"api_key": OPENAI_API_KEY,
|
45 |
+
"model": "gpt-3.5-turbo",
|
46 |
+
"temperature": 0,
|
47 |
+
},
|
48 |
+
}
|
49 |
+
|
50 |
+
# Create the SearchGraph instance dynamically
|
51 |
+
search_graph = SearchGraph(prompt=query_prompt, config=graph_config)
|
52 |
+
|
53 |
+
try:
|
54 |
+
# Run the graph to fetch results
|
55 |
+
result = search_graph.run()
|
56 |
+
# Convert the result to a JSON string with indentation for better readability
|
57 |
+
output = json.dumps(result, indent=2)
|
58 |
+
# Display each line of the JSON output
|
59 |
+
st.text_area("Result", value=output, height=300)
|
60 |
+
except Exception as e:
|
61 |
+
st.error(f"An error occurred: {e}")
|