Update app.py

app.py

@@ -1,102 +1,67 @@
 import streamlit as st
-from bs4 import BeautifulSoup
 import requests
 import os
-import time
 from openai import OpenAI
 
-
 headers = {
     "User-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582"
 }
 
 proxies = {"http": os.getenv("HTTP_PROXY")}
 
-
-
 @st.cache_data(ttl=3600)
-def search_legal_cases(query, num_results=10):
-    url = "https://scholar.google.com/scholar?hl=en&as_sdt=6"
+def extract_text_from_api(query):
+    url = "https://fastapi-example-uqyy.onrender.com/extract_text"
     headers = {
         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.3"
     }
-
+    
     params = {
-        "q": query,
-        "hl": "en",
-        "num": num_results,
-        "as_sdt": "4",  # This parameter filters the search results to legal cases
-    }
-
-    response = requests.get(url, proxies=proxies, headers=headers, params=params)
-    soup = BeautifulSoup(response.text, "html.parser")
-
-    results = []
-    for result in soup.find_all("div", class_="gs_ri"):
-        title = result.find("h3", class_="gs_rt").text
-        base_url = "https://scholar.google.com"
-        link = base_url + result.find("a")["href"]
-        citation = result.find("div", class_="gs_a").text.replace(" - Google Scholar", "")
-        results.append((title, link, citation))
-
-    return results
-
-@st.cache_data(ttl=3600)
-def extract_text_from_link(url):
-    headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.3"
+        "query": query
     }
     
-    response = requests.get(url, headers=headers, proxies=proxies)
-    soup = BeautifulSoup(response.content, "html.parser")
+    response = requests.get(url, headers=headers, proxies=proxies, params=params)
     
-    text = soup.get_text(separator="\n")
-    return text
-
+    if response.status_code == 200:
+        return response.json().get("extracted_text", "")
+    else:
+        return ""
 
 @st.cache_data(ttl=3600)
 def get_summary(text):
-   client = OpenAI(api_key='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')
-
-   completion = client.chat.completions.create(
-     model="gpt-4o",
-     messages=[
-       {"role": "system", "content": f'''You are a law professor specialized in legal writing and legal research. 
-                   When presented with a case by a user please summarize it according to the following requirements:
-                   Name of the court.
-                   Facts (name of the parties, what happened factually).
-                   Procedural history (what happened in the past procedurally, what were prior judgements). 
-                   Issues (what is in dispute).
-                   Holding (the applied rule of law). 
-                   Rationale (reasons for the holding).
-                   Decision (what did the court decide, e.g. affirmed, overruled).
-                   Other opinions (if there are any dissenting or concurring opinions, summarize majority opinion, dissenting opinion and concurring opinion).
-                   Cases cited (which cases the court cited and how it treated them).'''},
-       {"role": "user", "content": f"Please summarize this case according to the instructions: {text}. "}
-     ]
-   )
-   
-   return completion.choices[0].message.content
+    client = OpenAI(api_key='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')
+
+    completion = client.chat.completions.create(
+        model="gpt-4o",
+        messages=[
+            {"role": "system", "content": '''You are a law professor specialized in legal writing and legal research. 
+                        When presented with a case by a user please summarize it according to the following requirements:
+                        Name of the court.
+                        Facts (name of the parties, what happened factually).
+                        Procedural history (what happened in the past procedurally, what were prior judgements). 
+                        Issues (what is in dispute).
+                        Holding (the applied rule of law). 
+                        Rationale (reasons for the holding).
+                        Decision (what did the court decide, e.g. affirmed, overruled).
+                        Other opinions (if there are any dissenting or concurring opinions, summarize majority opinion, dissenting opinion and concurring opinion).
+                        Cases cited (which cases the court cited and how it treated them).'''},
+            {"role": "user", "content": f"Please summarize this case according to the instructions: {text}. "}
+        ]
+    )
+    
+    return completion.choices[0].message.content
 
 
 st.write("\n")
 st.write("\n")
-search_query = st.text_input("case name, e.g. brown v board supreme, 372 US 335, google v oracle appeal")
+search_query = st.text_input("Enter the case query, e.g., 'brown v board supreme'")
 
 if search_query:
-    with st.spinner("Searching for cases..."):
-        results = search_legal_cases(search_query)
-    if results:
-        title, link, citation = results[0]
-        st.write("Title:\n", title)
-        #st.write("Link:\n", link)
-        st.write("Citation:\n", citation)
-        #with st.spinner("Extracting text from case / Generating summary"):
-        text = extract_text_from_link(link)
-        #st.write(text)  # Optionally display the extracted text
-        
-        summary = get_summary(text)
-        st.write(summary)
-        
+    with st.spinner("Extracting text from case..."):
+        text = extract_text_from_api(search_query)
+    if text:
+        with st.spinner("Generating summary..."):
+            summary = get_summary(text)
+            st.write(summary)
     else:
-        st.write("No results found.")
+        st.write("Failed to extract text from the external API.")