Update app.py

app.py

@@ -255,9 +255,63 @@ chain_neo4j = (
 )
 
 # Define a function to select between Pinecone and Neo4j
+# def generate_answer(message, choice, retrieval_mode):
+#     logging.debug(f"generate_answer called with choice: {choice} and retrieval_mode: {retrieval_mode}")
+
+#     prompt_template = QA_CHAIN_PROMPT_1 if choice == "Details" else QA_CHAIN_PROMPT_2
+
+#     if retrieval_mode == "VDB":
+#         qa_chain = RetrievalQA.from_chain_type(
+#             llm=chat_model,
+#             chain_type="stuff",
+#             retriever=retriever,
+#             chain_type_kwargs={"prompt": prompt_template}
+#         )
+#         response = qa_chain({"query": message})
+#         logging.debug(f"Vector response: {response}")
+#         return response['result'], extract_addresses(response['result'])
+#     elif retrieval_mode == "KGF":
+#         response = chain_neo4j.invoke({"question": message})
+#         logging.debug(f"Knowledge-Graph response: {response}")
+#         return response, extract_addresses(response)
+#     else:
+#         return "Invalid retrieval mode selected.", []
+
+# def bot(history, choice, tts_choice, retrieval_mode):
+#     if not history:
+#         return history
+    
+#     response, addresses = generate_answer(history[-1][0], choice, retrieval_mode)
+#     history[-1][1] = ""
+
+#     with concurrent.futures.ThreadPoolExecutor() as executor:
+#         if tts_choice == "Alpha":
+#             audio_future = executor.submit(generate_audio_elevenlabs, response)
+#         elif tts_choice == "Beta":
+#             audio_future = executor.submit(generate_audio_parler_tts, response)
+#         elif tts_choice == "Gamma":
+#             audio_future = executor.submit(generate_audio_mars5, response)
+
+#         for character in response:
+#             history[-1][1] += character
+#             time.sleep(0.05)
+#             yield history, None
+
+#         audio_path = audio_future.result()
+#         yield history, audio_path
+
+#     history.append([response, None])  # Ensure the response is added in the correct format
+
+
+
 def generate_answer(message, choice, retrieval_mode):
     logging.debug(f"generate_answer called with choice: {choice} and retrieval_mode: {retrieval_mode}")
 
+    # Check if the question is about restaurants
+    if "restaurant" in message.lower() and "birmingham" in message.lower():
+        response = fetch_yelp_restaurants()
+        return response, extract_addresses(response)
+
     prompt_template = QA_CHAIN_PROMPT_1 if choice == "Details" else QA_CHAIN_PROMPT_2
 
     if retrieval_mode == "VDB":
@@ -277,6 +331,7 @@ def generate_answer(message, choice, retrieval_mode):
     else:
         return "Invalid retrieval mode selected.", []
 
+
 def bot(history, choice, tts_choice, retrieval_mode):
     if not history:
         return history
@@ -284,6 +339,14 @@ def bot(history, choice, tts_choice, retrieval_mode):
     response, addresses = generate_answer(history[-1][0], choice, retrieval_mode)
     history[-1][1] = ""
 
+    # Detect if the response is from Yelp (i.e., HTML formatted response)
+    if "<table>" in response:
+        for chunk in response.splitlines():
+            history[-1][1] += chunk + "\n"
+            time.sleep(0.1)  # Adjust the delay as needed
+            yield history, None
+        return
+
     with concurrent.futures.ThreadPoolExecutor() as executor:
         if tts_choice == "Alpha":
             audio_future = executor.submit(generate_audio_elevenlabs, response)
@@ -302,6 +365,9 @@ def bot(history, choice, tts_choice, retrieval_mode):
 
     history.append([response, None])  # Ensure the response is added in the correct format
 
+
+
+
 def add_message(history, message):
     history.append((message, None))
     return history, gr.Textbox(value="", interactive=True, placeholder="Enter message or upload file...", show_label=False)
@@ -351,70 +417,6 @@ def generate_map(location_names):
     
     map_html = m._repr_html_()
     return map_html
-#------------------------------------
-from langchain import OpenAI, LLMMathChain, SerpAPIWrapper
-from langchain.agents import initialize_agent, Tool, AgentExecutor
-from langchain.chat_models import ChatOpenAI
-import os
-
-# Step 1: Define the Yelp Search Tool
-class YelpSearchTool:
-    name = "YelpSearch"
-    description = "A tool to search for restaurants in Birmingham, AL using Yelp."
-
-    def _run(self, query: str) -> str:
-        params = {
-            "engine": "yelp",
-            "find_desc": "Restaurant",
-            "find_loc": "Birmingham, AL, USA",
-            "api_key": os.getenv("SERP_API")
-        }
-
-        response = requests.get("https://serpapi.com/search.json", params=params)
-        if response.status_code == 200:
-            results = response.json().get("organic_results", [])
-            if not results:
-                return "No results found."
-            
-            result_str = "Top Restaurants:\n"
-            for result in results[:5]:  # Limit to top 5 results
-                name = result.get("title", "No name")
-                rating = result.get("rating", "No rating")
-                reviews = result.get("reviews", "No reviews")
-                address = result.get("address", "No address available")
-                result_str += f"Name: {name}\nRating: {rating}\nReviews: {reviews}\nAddress: {address}\n\n"
-
-            return result_str
-        else:
-            return f"Failed to fetch data from Yelp. Status code: {response.status_code}"
-
-# Initialize the LLM and the Tool
-yelp_tool = YelpSearchTool()
-tools = [
-    Tool(
-        name="YelpSearch",
-        func=yelp_tool._run,
-        description="Search for restaurants in Birmingham using Yelp."
-    )
-]
-
-# Initialize the agent
-agent = initialize_agent(
-    tools=tools,
-    llm=chat_model,
-    agent="zero-shot-react-description",
-    verbose=True
-)
-
-memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
-conversational_agent = ConversationalRetrievalChain.from_llm(
-    llm=llm,
-    retriever=agent,
-    memory=memory
-)
-
-
-#--------------------------------------------------------
 
 
 def fetch_local_news():