Upload folder using huggingface_hub

app.py

@@ -11,12 +11,10 @@ from collections import defaultdict
 import fastapi
 from gradio.context import Context
 import logging
-from rag_utils import RAGSystem
 
-# Set up logging
-logging.basicConfig(level=logging.INFO, 
-                   format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
 logger = logging.getLogger(__name__)
+logger.setLevel(logging.DEBUG)
+
 
 load_dotenv(override=True)
 
@@ -134,85 +132,39 @@ class Me:
         self.openai = OpenAI(api_key=os.getenv("GOOGLE_API_KEY"), base_url="https://generativelanguage.googleapis.com/v1beta/openai/")
         self.name = "Sagarnil Das"
         self.rate_limiter = RateLimiter(max_requests=5, time_window=60)  # 5 messages per minute
-        
-        # Initialize RAG system
-        self.rag = RAGSystem()
-        
-        # Try to load the RAG index
-        try:
-            rag_index_path = "me/rag_index"
-            if os.path.exists(rag_index_path):
-                logger.info(f"Loading RAG index from {rag_index_path}")
-                self.rag.load_index(rag_index_path)
-                logger.info(f"Loaded {len(self.rag.chunks)} chunks from index")
-                self.rag_loaded = True
-            else:
-                logger.warning(f"RAG index not found at {rag_index_path}. Falling back to full document loading.")
-                self.rag_loaded = False
-                # Fall back to loading full documents
-                self._load_full_documents()
-        except Exception as e:
-            logger.error(f"Error loading RAG index: {e}")
-            logger.warning("Falling back to full document loading")
-            self.rag_loaded = False
-            # Fall back to loading full documents
-            self._load_full_documents()
+        reader = PdfReader("me/linkedin.pdf")
+        self.linkedin = ""
+        for page in reader.pages:
+            text = page.extract_text()
+            if text:
+                self.linkedin += text
+        with open("me/summary.txt", "r", encoding="utf-8") as f:
+            self.summary = f.read()
 
-    def _load_full_documents(self):
-        """Legacy method to load full documents if RAG fails"""
-        logger.info("Loading full documents as fallback...")
-        try:
-            reader = PdfReader("me/linkedin.pdf")
-            self.linkedin = ""
-            for page in reader.pages:
-                text = page.extract_text()
-                if text:
-                    self.linkedin += text
-            with open("me/summary.txt", "r", encoding="utf-8") as f:
-                self.summary = f.read()
-            logger.info("Full documents loaded successfully")
-        except Exception as e:
-            logger.error(f"Error loading full documents: {e}")
-            self.linkedin = "LinkedIn profile not available."
-            self.summary = "Professional summary not available."
 
     def handle_tool_call(self, tool_calls):
         results = []
         for tool_call in tool_calls:
             tool_name = tool_call.function.name
             arguments = json.loads(tool_call.function.arguments)
-            logger.info(f"Tool called: {tool_name}")
+            print(f"Tool called: {tool_name}", flush=True)
             tool = globals().get(tool_name)
             result = tool(**arguments) if tool else {}
             results.append({"role": "tool","content": json.dumps(result),"tool_call_id": tool_call.id})
         return results
     
-    def system_prompt(self, query=None):
-        """Dynamic system prompt that includes RAG context if RAG is loaded and query is provided"""
+    def system_prompt(self):
         system_prompt = f"You are acting as {self.name}. You are answering questions on {self.name}'s website, \
 particularly questions related to {self.name}'s career, background, skills and experience. \
 Your responsibility is to represent {self.name} for interactions on the website as faithfully as possible. \
+You are given a summary of {self.name}'s background and LinkedIn profile which you can use to answer questions. \
 Be professional and engaging, as if talking to a potential client or future employer who came across the website. \
 If you don't know the answer to any question, use your record_unknown_question tool to record the question that you couldn't answer, even if it's about something trivial or unrelated to career. \
 If the user is engaging in discussion, try to steer them towards getting in touch via email; ask for their email and record it using your record_user_details tool. \
 When a user provides their email, both a push notification and an email notification will be sent. If the user does not provide any note in the message \
 in which they provide their email, then give a summary of the conversation so far as the notes."
 
-        # If we have a query and RAG is loaded, use RAG to retrieve relevant context
-        if query and self.rag_loaded:
-            try:
-                context = self.rag.get_context_for_query(query, top_k=3)
-                system_prompt += f"\n\n## Relevant Background Information:\n{context}\n\n"
-            except Exception as e:
-                logger.error(f"Error retrieving RAG context: {e}")
-                # Fall back to full documents if RAG retrieval fails
-                if hasattr(self, 'summary') and hasattr(self, 'linkedin'):
-                    system_prompt += f"\n\n## Summary:\n{self.summary}\n\n## LinkedIn Profile:\n{self.linkedin}\n\n"
-        else:
-            # Fall back to full documents if RAG is not loaded
-            if hasattr(self, 'summary') and hasattr(self, 'linkedin'):
-                system_prompt += f"\n\n## Summary:\n{self.summary}\n\n## LinkedIn Profile:\n{self.linkedin}\n\n"
-        
+        system_prompt += f"\n\n## Summary:\n{self.summary}\n\n## LinkedIn Profile:\n{self.linkedin}\n\n"
         system_prompt += f"With this context, please chat with the user, always staying in character as {self.name}."
         return system_prompt
     
@@ -241,49 +193,35 @@ in which they provide their email, then give a summary of the conversation so fa
         if self.rate_limiter.is_rate_limited(user_id):
             return "You're sending messages too quickly. Please wait a moment before sending another message."
         
-        try:
-            # First message includes base system prompt (without query-specific context)
-            messages = [{"role": "system", "content": self.system_prompt()}]
+        messages = [{"role": "system", "content": self.system_prompt()}]
 
-            # Check if history is a list of dicts (Gradio "messages" format)
-            if isinstance(history, list) and all(isinstance(h, dict) for h in history):
-                messages.extend(history)
+        # Check if history is a list of dicts (Gradio "messages" format)
+        if isinstance(history, list) and all(isinstance(h, dict) for h in history):
+            messages.extend(history)
+        else:
+            # Assume it's a list of [user_msg, assistant_msg] pairs
+            for user_msg, assistant_msg in history:
+                messages.append({"role": "user", "content": user_msg})
+                messages.append({"role": "assistant", "content": assistant_msg})
+
+        messages.append({"role": "user", "content": message})
+
+        done = False
+        while not done:
+            response = self.openai.chat.completions.create(
+                model="gemini-2.0-flash",
+                messages=messages,
+                tools=tools
+            )
+            if response.choices[0].finish_reason == "tool_calls":
+                tool_calls = response.choices[0].message.tool_calls
+                tool_result = self.handle_tool_call(tool_calls)
+                messages.append(response.choices[0].message)
+                messages.extend(tool_result)
             else:
-                # Assume it's a list of [user_msg, assistant_msg] pairs
-                for user_msg, assistant_msg in history:
-                    messages.append({"role": "user", "content": user_msg})
-                    messages.append({"role": "assistant", "content": assistant_msg})
+                done = True
 
-            # Add the user's message
-            messages.append({"role": "user", "content": message})
-            
-            # Update the system message with query-specific context
-            try:
-                messages[0] = {"role": "system", "content": self.system_prompt(query=message)}
-            except Exception as e:
-                logger.error(f"Error updating system prompt with RAG context: {e}")
-                # Keep original system prompt if there's an error
-
-            done = False
-            while not done:
-                response = self.openai.chat.completions.create(
-                    model="gemini-2.0-flash",
-                    messages=messages,
-                    tools=tools
-                )
-                if response.choices[0].finish_reason == "tool_calls":
-                    tool_calls = response.choices[0].message.tool_calls
-                    tool_result = self.handle_tool_call(tool_calls)
-                    messages.append(response.choices[0].message)
-                    messages.extend(tool_result)
-                else:
-                    done = True
-
-            return response.choices[0].message.content
-            
-        except Exception as e:
-            logger.error(f"Error in chat method: {e}")
-            return "I apologize, but I encountered an error processing your request. Please try again later."
+        return response.choices[0].message.content
 
         
 

requirements.txt

@@ -1,9 +1,5 @@
-numpy==1.23.5
 requests
 python-dotenv
 gradio
 pypdf
 openai
-faiss-cpu==1.7.4
-transformers>=4.30.0
-torch>=2.0.0