Update app.py

app.py

@@ -271,24 +271,38 @@ def generate_chunked_response(prompt, model, max_tokens=10000, num_calls=3, temp
     print(f"Final clean response: {final_response[:100]}...")
     return final_response
 
-def duckduckgo_search(query):
-    with DDGS() as ddgs:
-        results = ddgs.text(query, max_results=5)
-    return results
+def duckduckgo_search(query, safe="on", region=None, language=None, time=None, filetype=None, site=None, inurl=None, intitle=None, intext=None, related=None, info=None, define=None):
+    params = {
+        "q": query,
+        "safe": safe,
+        "region": region,
+        "language": language,
+        "time": time,
+        "filetype": filetype,
+        "site": site,
+        "inurl": inurl,
+        "intitle": intitle,
+        "intext": intext,
+        "related": related,
+        "info": info,
+        "define": define
+   }
+   with DDGS() as ddgs:
+       results = ddgs.text(query, params=params, max_results=5)
+   return results
 
 class CitingSources(BaseModel):
     sources: List[str] = Field(
         ...,
         description="List of sources to cite. Should be an URL of the source."
     )
-def chatbot_interface(message, history, use_web_search, model, temperature, num_calls):
+
+def chatbot_interface(message, history, use_web_search, model, temperature, num_calls, safe, region, language, time, filetype, site, inurl, intitle, intext, related, info, define):
     if not message.strip():
         return "", history
-
     history = history + [(message, "")]
-
     try:
-        for response in respond(message, history, model, temperature, num_calls, use_web_search):
+        for response in respond(message, history, model, temperature, num_calls, use_web_search, safe, region, language, time, filetype, site, inurl, intitle, intext, related, info, define):
             history[-1] = (message, response)
             yield history
     except gr.CancelledError:
@@ -307,21 +321,19 @@ def retry_last_response(history, use_web_search, model, temperature, num_calls):
     
     return chatbot_interface(last_user_msg, history, use_web_search, model, temperature, num_calls)
 
-def respond(message, history, model, temperature, num_calls, use_web_search, selected_docs):
+def respond(message, history, model, temperature, num_calls, use_web_search, safe, region, language, time, filetype, site, inurl, intitle, intext, related, info, define):
     logging.info(f"User Query: {message}")
     logging.info(f"Model Used: {model}")
     logging.info(f"Search Type: {'Web Search' if use_web_search else 'PDF Search'}")
-
-    logging.info(f"Selected Documents: {selected_docs}")
-
+   
     try:
         if use_web_search:
-            for main_content, sources in get_response_with_search(message, model, num_calls=num_calls, temperature=temperature):
+            for main_content, sources in get_response_with_search(message, model, num_calls=num_calls, temperature=temperature, safe=safe, region=region, language=language, time=time, filetype=filetype, site=site, inurl=inurl, intitle=intitle, intext=intext, related=related, info=info, define=define):
                 response = f"{main_content}\n\n{sources}"
                 first_line = response.split('\n')[0] if response else ''
-#                logging.info(f"Generated Response (first line): {first_line}")
+                logging.info(f"Generated Response (first line): {first_line}")
                 yield response
-        else:
+       else:
             embed = get_embeddings()
             if os.path.exists("faiss_database"):
                 database = FAISS.load_local("faiss_database", embed, allow_dangerous_deserialization=True)
@@ -419,16 +431,20 @@ After writing the document, please provide a list of sources used in your respon
     if not full_response:
         yield "I apologize, but I couldn't generate a response at this time. Please try again later."
 
-def get_response_with_search(query, model, num_calls=3, temperature=0.2):
-    search_results = duckduckgo_search(query)
-    context = "\n".join(f"{result['title']}\n{result['body']}\nSource: {result['href']}\n" 
-                        for result in search_results if 'body' in result)
-    
-    prompt = f"""Using the following context:
+def get_response_with_search(query, model, num_calls=3, temperature=0.2, safe="on", region=None, language=None, time=None, filetype=None, site=None, inurl=None, intitle=None, intext=None, related=None, info=None, define=None):
+    search_results = duckduckgo_search(query, safe=safe, region=region, language=language, time=time, filetype=filetype, site=site, inurl=inurl, intitle=intitle, intext=intext, related=related, info=info, define=define)
+    web_search_database = create_web_search_vectors(search_results)
+    if not web_search_database:
+        yield "No web search results available. Please try again.", ""
+        return
+    retriever = web_search_database.as_retriever(search_kwargs={"k": 5})
+    relevant_docs = retriever.get_relevant_documents(query)
+    context = "\n".join([doc.page_content for doc in relevant_docs])
+    prompt = f"""Using the following context from web search results:
 {context}
 Write a detailed and complete research document that fulfills the following user request: '{query}'
 After writing the document, please provide a list of sources used in your response."""
-
+    
     if model == "@cf/meta/llama-3.1-8b-instruct":
         # Use Cloudflare API
         for response in get_response_from_cloudflare(prompt="", context=context, query=query, num_calls=num_calls, temperature=temperature, search_type="web"):
@@ -444,7 +460,7 @@ After writing the document, please provide a list of sources used in your respon
                 max_tokens=10000,
                 temperature=temperature,
                 stream=True,
-            ):
+           ):
                 if message.choices and message.choices[0].delta and message.choices[0].delta.content:
                     chunk = message.choices[0].delta.content
                     main_content += chunk
@@ -576,10 +592,23 @@ demo = gr.ChatInterface(
         gr.Slider(minimum=0.1, maximum=1.0, value=0.2, step=0.1, label="Temperature"),
         gr.Slider(minimum=1, maximum=5, value=1, step=1, label="Number of API Calls"),
         use_web_search,
-        document_selector
+        document_selector,
+        gr.Dropdown(choices=instruction_choices, label="Select Entity Type for Summary", value="None"),
+        gr.Checkbox(label="Safe Search", value=True),
+        gr.Textbox(label="Region", placeholder="US"),
+        gr.Textbox(label="Language", placeholder="en"),
+        gr.Textbox(label="Time", placeholder="d"),
+        gr.Textbox(label="Filetype", placeholder="pdf"),
+        gr.Textbox(label="Site", placeholder="github.com"),
+        gr.Textbox(label="Inurl", placeholder="github.com"),
+        gr.Textbox(label="Intitle", placeholder="github"),
+        gr.Textbox(label="Intext", placeholder="github"),
+        gr.Textbox(label="Related", placeholder="github.com"),
+        gr.Textbox(label="Info", placeholder="github.com"),
+        gr.Textbox(label="Define", placeholder="github")
     ],
     title="AI-powered Web Search and PDF Chat Assistant",
-    description="Chat with your PDFs or use web search to answer questions. Toggle between Web Search and PDF Chat in Additional Inputs below.",
+    description="Chat with your PDFs, use web search to answer questions, or generate summaries. Select an Entity Type for Summary to generate a specific summary.",
     theme=gr.themes.Soft(
         primary_hue="orange",
         secondary_hue="amber",
@@ -608,12 +637,12 @@ demo = gr.ChatInterface(
     analytics_enabled=False,
     textbox=gr.Textbox(placeholder=custom_placeholder, container=False, scale=7),
     chatbot = gr.Chatbot(  
-    show_copy_button=True,
-    likeable=True,
-    layout="bubble",
-    height=400,
-    value=initial_conversation()
-)
+        show_copy_button=True,
+        likeable=True,
+        layout="bubble",
+        height=400,
+        value=initial_conversation()
+    )
 )
 
 # Add file upload functionality