Update app.py

app.py

@@ -31,7 +31,7 @@ def augment_prompt(query, vectordb):
     source_knowledge = "\n".join([x.page_content for x in results])
     augmented_prompt = f"""
     You are an AI assistant. Use the context provided below to answer the question as comprehensively as possible. 
-    If the answer is not contained within the context, respond with "I don't know".
+    If the answer is not contained within the context, respond politely that you cannot provide that information.
 
     Context:
     {source_knowledge}
@@ -41,9 +41,9 @@ def augment_prompt(query, vectordb):
     return augmented_prompt
 
 # Function to handle chat with OpenAI
-def chat_with_openai(query, vectordb, openai_api_key):
-    chat = ChatOpenAI(model_name="gpt-3.5-turbo", openai_api_key=openai_api_key)
-    augmented_query = augment_prompt(query, vectordb)
+def chat_with_openai(query, vectordb, openai_api_key, search_results):
+    chat = ChatOpenAI(model_name="gpt-3.5-turbo", openai_api_key=openai_api_key, timeout=30)  # Increased timeout
+    augmented_query = augment_prompt(query, vectordb, search_results)
     prompt = HumanMessage(content=augmented_query)
     messages = [
         SystemMessage(content="You are a helpful assistant."),
@@ -52,6 +52,37 @@ def chat_with_openai(query, vectordb, openai_api_key):
     res = chat(messages)
     return res.content
 
+# Function to perform web search
+def perform_web_search(query):
+    headers = {
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"}
+    search_results = ""
+
+    # Glassdoor search
+    glassdoor_url = f"https://www.glassdoor.com/Search/results.htm?keyword={query}"
+    response = requests.get(glassdoor_url, headers=headers)
+    if response.status_code == 200:
+        soup = BeautifulSoup(response.text, 'html.parser')
+        glassdoor_results = soup.find_all('div', {'class': 'jobContainer'})
+        for result in glassdoor_results[:5]:  # limiting to first 3 results
+            title = result.find('a', {'class': 'jobInfoItem jobTitle'}).text.strip() if result.find('a', {'class': 'jobInfoItem jobTitle'}) else 'N/A'
+            company = result.find('div', {'class': 'jobInfoItem jobEmpolyerName'}).text.strip() if result.find('div', {'class': 'jobInfoItem jobEmpolyerName'}) else 'N/A'
+            location = result.find('span', {'class': 'subtle loc'}).text.strip() if result.find('span', {'class': 'subtle loc'}) else 'N/A'
+            search_results += f"Glassdoor Result: {title} at {company}, {location}\n"
+
+    # Indeed search
+    indeed_url = f"https://www.indeed.com/jobs?q={query}&limit=10"
+    response = requests.get(indeed_url, headers=headers)
+    if response.status_code == 200:
+        soup = BeautifulSoup(response.text, 'html.parser')
+        indeed_results = soup.find_all('div', {'class': 'jobsearch-SerpJobCard'})
+        for result in indeed_results[:5]:  # limiting to first 3 results
+            title = result.find('h2', {'class': 'title'}).text.strip() if result.find('h2', {'class': 'title'}) else 'N/A'
+            company = result.find('span', {'class': 'company'}).text.strip() if result.find('span', {'class': 'company'}) else 'N/A'
+            location = result.find('span', {'class': 'location'}).text.strip() if result.find('span', {'class': 'location'}) else 'N/A'
+            search_results += f"Indeed Result: {title} at {company}, {location}\n"
+    
+    return search_results
 
 # Streamlit UI
 st.title("Data Roles Company Finder Chatbot")
@@ -71,19 +102,69 @@ for message in st.session_state.messages:
     with st.chat_message(message["role"]):
         st.markdown(message["content"])
 
-
 # User input
 if prompt := st.chat_input("Enter your query"):
     st.session_state.messages.append({"role": "user", "content": prompt})
     with st.chat_message("user"):
         st.markdown(prompt)
 
+    # Perform web search
+    search_results = perform_web_search(prompt)
+
+    # Chat with OpenAI
+    openai_api_key = st.secrets["OPENAI_API_KEY"]
+    response = chat_with_openai(prompt, vectordb, openai_api_key, search_results)
+    
+    # Display assistant response
     with st.chat_message("assistant"):
-        openai_api_key = st.secrets["OPENAI_API_KEY"]
-        response = chat_with_openai(prompt, vectordb, openai_api_key)
         st.markdown(response)
         
     st.session_state.messages.append({"role": "assistant", "content": response})
+    
+# # Function to handle chat with OpenAI
+# def chat_with_openai(query, vectordb, openai_api_key):
+#     chat = ChatOpenAI(model_name="gpt-3.5-turbo", openai_api_key=openai_api_key)
+#     augmented_query = augment_prompt(query, vectordb)
+#     prompt = HumanMessage(content=augmented_query)
+#     messages = [
+#         SystemMessage(content="You are a helpful assistant."),
+#         prompt
+#     ]
+#     res = chat(messages)
+#     return res.content
+
+
+# # Streamlit UI
+# st.title("Data Roles Company Finder Chatbot")
+# st.write("This app helps users find companies hiring for data roles, providing information such as job title, salary estimate, job description, company rating, and more.")
+
+# # Load vector database
+# zip_file_path = "chroma_db_compressed_.zip"
+# extract_path = "./chroma_db_extracted"
+# vectordb = load_vector_db(zip_file_path, extract_path)
+
+# # Initialize session state for chat history
+# if "messages" not in st.session_state:
+#     st.session_state.messages = []
+
+# # Display chat history
+# for message in st.session_state.messages:
+#     with st.chat_message(message["role"]):
+#         st.markdown(message["content"])
+
+
+# # User input
+# if prompt := st.chat_input("Enter your query"):
+#     st.session_state.messages.append({"role": "user", "content": prompt})
+#     with st.chat_message("user"):
+#         st.markdown(prompt)
+
+#     with st.chat_message("assistant"):
+#         openai_api_key = st.secrets["OPENAI_API_KEY"]
+#         response = chat_with_openai(prompt, vectordb, openai_api_key)
+#         st.markdown(response)
+        
+#     st.session_state.messages.append({"role": "assistant", "content": response})
         
 # # Query input
 # query = st.text_input("Enter your query", "")