from dotenv import load_dotenv from openai import OpenAI import json import os import requests from pypdf import PdfReader import gradio as gr import glob import random import threading import time import io import pathlib import base64 # Load environment variables from .env file load_dotenv(override=True) def push(text): """ Sends a push notification using the Pushover API. This function requires PUSHOVER_TOKEN and PUSHOVER_USER to be set as environment variables. """ requests.post( "https://api.pushover.net/1/messages.json", data={ "token": os.getenv("PUSHOVER_TOKEN"), "user": os.getenv("PUSHOVER_USER"), "message": text, } ) def record_user_details(email, name="Name not provided", notes="not provided"): """ Records a user's details and sends a push notification. """ push(f"Recording {name} with email {email} and notes {notes}") return {"recorded": "ok"} def record_unknown_question(question): """ Records an unanswered question and sends a push notification. """ push(f"Recording {question}") return {"recorded": "ok"} def get_instagram_link(): """ Returns the Instagram URL for Aneet Padda. """ return {"url": "https://www.instagram.com/aneetpadda_/"} def get_local_images(): """ Selects four unique random image paths from me/images. """ image_paths = glob.glob('me/images/*') if len(image_paths) < 4: # Fallback if there are fewer than 4 images return image_paths + [None] * (4 - len(image_paths)) return random.sample(image_paths, 4) def browse_for_image(): """ Fetches a list of images that are likely to be of movie actresses. Note: A real-time web search for specific images is not possible in this environment. This function returns a hardcoded set of working image URLs. """ # Using placeholder images that will always be available return [ "https://placehold.co/600x400/FF5733/FFFFFF?text=Image+1", "https://placehold.co/600x400/33FF57/000000?text=Image+2", "https://placehold.co/600x400/3357FF/FFFFFF?text=Image+3", "https://placehold.co/600x400/FF33A1/000000?text=Image+4", "https://placehold.co/600x400/A133FF/FFFFFF?text=Image+5", "https://placehold.co/600x400/57FF33/000000?text=Image+6", "https://placehold.co/600x400/FF5733/FFFFFF?text=Image+7", "https://placehold.co/600x400/33FF57/000000?text=Image+8" ] def get_next_images(history): """ Selects the next four images to display. The first time, it shows images from the local 'me/images' folder. Subsequent clicks will fetch new, random images from the internet. """ # Check if this is the first click or if we are already displaying internet images if not history or not all(isinstance(path, str) and path.startswith('me/images') for path in history): # Fetch new random images from the internet all_internet_images = browse_for_image() new_images = random.sample(all_internet_images, 4) history = new_images return new_images[0], new_images[1], new_images[2], new_images[3], history else: # Initial display of local images unshown_images = [path for path in get_local_images() if path not in history] if len(unshown_images) >= 4: selected_images = random.sample(unshown_images, 4) history.extend(selected_images) return selected_images[0], selected_images[1], selected_images[2], selected_images[3], history else: # Local images exhausted, switch to internet images all_internet_images = browse_for_image() new_images = random.sample(all_internet_images, 4) history = new_images return new_images[0], new_images[1], new_images[2], new_images[3], history def reset_images(): """ Resets the displayed images to the initial set from the local 'me/images' folder. """ initial_images = get_local_images() return initial_images[0], initial_images[1], initial_images[2], initial_images[3], initial_images # Tool definitions for function calling record_user_details_json = { "name": "record_user_details", "description": "Use this tool to record that a user is interested in being in touch and provided an email address", "parameters": { "type": "object", "properties": { "email": { "type": "string", "description": "The email address of this user" }, "name": { "type": "string", "description": "The user's name, if they provided it" }, "notes": { "type": "string", "description": "Any additional information about the conversation that's worth recording to give context" } }, "required": ["email"], "additionalProperties": False } } record_unknown_question_json = { "name": "record_unknown_question", "description": "Always use this tool to record any question that couldn't be answered as you didn't know the answer", "parameters": { "type": "object", "properties": { "question": { "type": "string", "description": "The question that couldn't be answered" }, }, "required": ["question"], "additionalProperties": False } } get_instagram_link_json = { "name": "get_instagram_link", "description": "Always use this tool when a user asks for Aneet Padda's Instagram link", "parameters": { "type": "object", "properties": {}, "additionalProperties": False } } tools = [ {"type": "function", "function": record_user_details_json}, {"type": "function", "function": record_unknown_question_json}, {"type": "function", "function": get_instagram_link_json} ] class Me: def __init__(self): # Initialize the Gemini client using the OpenAI library with the specified base URL and model. # This allows using the OpenAI-compatible API endpoint for Gemini. # Make sure to have GOOGLE_API_KEY set in your environment or .env file. google_api_key = os.getenv("GOOGLE_API_KEY") self.gemini = OpenAI(api_key=google_api_key, base_url="https://generativelanguage.googleapis.com/v1beta/openai/") self.model_name = "gemini-2.0-flash" self.name = "Aneet Padda" # Read the LinkedIn profile from the PDF reader = PdfReader("me/aneetinfo.pdf") self.linkedin = "" for page in reader.pages: text = page.extract_text() if text: self.linkedin += text # Read the summary from the text file with open("me/summary.txt", "r", encoding="utf-8") as f: self.summary = f.read() # Get local images to reference in the system prompt self.local_images = glob.glob('me/images/*') self.image_description = "The following images of Aneet Padda are available: " + ", ".join(self.local_images) def handle_tool_call(self, tool_calls): """ Executes the function calls returned by the model. """ results = [] for tool_call in tool_calls: tool_name = tool_call.function.name arguments = json.loads(tool_call.function.arguments) 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): """ Generates the system prompt for the model. """ 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. \ If a user asks for your social media, like your Instagram, you can use your get_instagram_link tool to provide the URL." # Add a more casual, friendly, and expressive tone to the system prompt system_prompt += "\n\nYour tone should be casual and friendly, like you're chatting with a friend. Feel free to use emojis and conversational language to make the interaction more engaging. \ When a user sends an image, you should act like a friend commenting on it. If it's a nice, appropriate image, give a positive comment. If it's an inappropriate or bad image, you should say 'please don't send images like this.' Make sure to summarize the image in a fun, conversational way before replying." system_prompt += f"\n\n## Summary:\n{self.summary}\n\n## LinkedIn Profile:\n{self.linkedin}\n\n" system_prompt += f"## Available Images:\n{self.image_description}\n\n" system_prompt += f"With this context, please chat with the user, always staying in character as {self.name}." return system_prompt def chat(self, message, history): """ Handles the chat conversation with the model, including image processing. """ # Send a notification for every user message received. push(f"New user question: {message}") # Handle the user message, which may include an image messages = [{"role": "system", "content": self.system_prompt()}] + history # Check if the user message contains an image if isinstance(message, tuple) and message: # This is the corrected check for image uploads from Gradio image_path = message[0] # Read the image and encode to base64 # Use 'rb' to read the file in binary mode for base64 encoding with open(image_path, "rb") as image_file: base64_image = base64.b64encode(image_file.read()).decode("utf-8") # Create the payload for the vision model vision_message = { "role": "user", "parts": [ {"text": "Describe this image and tell me if it's appropriate. Then give a short, friendly comment on it."}, {"inline_data": {"mime_type": "image/jpeg", "data": base64_image}} ] } # Send a notification with a summary of the image push(f"User uploaded an image. Analyzing image content...") # Call Gemini with the image and text prompt try: vision_response = self.gemini.chat.completions.create( model=self.model_name, messages=messages + [vision_message], tools=tools ) agent_reply = vision_response.choices[0].message.content return agent_reply except Exception as e: print(f"Error processing image: {e}") return "I'm sorry, I couldn't process that image right now." else: # Regular text message messages.append({"role": "user", "content": message}) done = False while not done: response = self.gemini.chat.completions.create(model=self.model_name, messages=messages, tools=tools) if response.choices[0].finish_reason=="tool_calls": message = response.choices[0].message tool_calls = message.tool_calls results = self.handle_tool_call(tool_calls) messages.append(message) messages.extend(results) else: done = True return response.choices[0].message.content # Function to get a random image from the local folder for the profile pic def get_random_local_image(): image_paths = glob.glob('me/images/*') if image_paths: return random.choice(image_paths) return None # Return None if no images are found if __name__ == "__main__": # Custom CSS for the new design custom_css = """ body { background-color: #000; color: #fff; } .gradio-container.dark { background-color: #000; } .gradio-container .main { padding: 0; max-width: none; } .chat-header { display: flex; flex-direction: column; align-items: center; padding: 20px; background-color: #000; border-bottom: 1px solid #333; } .chat-header-img { width: 100px; height: 100px; border-radius: 50%; object-fit: cover; border: 3px solid #666; } .chat-header-text h3 { margin: 10px 0 0; font-size: 1.5em; text-align: center; } .chat-header-text p { margin: 0; font-size: 0.9em; color: #bbb; text-align: center; } .chat-input-row { background-color: #000; padding: 10px; border-top: 1px solid #333; display: flex; align-items: center; } #msg_box { background-color: #222; border-radius: 20px; border: 1px solid #444; color: white; padding: 10px; } #upload_btn { background-color: transparent; border: none; color: white; font-size: 1.5em; padding: 5px; cursor: pointer; } .gradio-container .message { border-radius: 20px; padding: 10px 15px; } .gradio-container .message-wrap.user { background-color: #007aff; color: white; } .gradio-container .message-wrap.bot { background-color: #2c2c2c; color: white; } .blue-checkmark { color: #007aff; } """ me = Me() # Initial images to display initial_images = get_local_images() initial_profile_image = get_random_local_image() with gr.Blocks(css=custom_css, theme=gr.themes.Monochrome( font=["Inter", "sans-serif"], primary_hue="blue", neutral_hue="gray", )) as demo: # State to keep track of chat history chatbot_state = gr.State([]) # New chat interface with a single profile header with gr.Column(elem_id="main-chat-container"): with gr.Row(elem_classes=["chat-header"]): profile_button = gr.Button( variant="link", elem_classes=["chat-header-img-button"], interactive=True ) profile_image = gr.Image( value=initial_profile_image, show_label=False, elem_classes=["chat-header-img"], interactive=False # Make the image itself not interactive ) with gr.Column(elem_classes=["chat-header-text"]): gr.Markdown("### Aneet Padda ✅") gr.Markdown("aneetpadda_ · Instagram") # View Profile button to redirect to Instagram gr.Button("View Profile", link="https://www.instagram.com/aneetpadda_/") # Chatbot and message input chatbot = gr.Chatbot(label="Chat with the agent", type="messages", layout="bubble", height=500) # The input area, with the upload button inside the textbox with gr.Row(elem_classes=["chat-input-row"]): with gr.Row(elem_id="msg_box"): upload_btn = gr.UploadButton( "📎", file_types=["image"], file_count="single", elem_id="upload_btn" ) msg = gr.Textbox(placeholder="Message...", show_label=False, scale=1) submit_btn = gr.Button("➡️", scale=0, variant="primary") # Functions to handle messages and uploads def add_message(text, file_obj, history): # Check if an image file was uploaded if file_obj: # Add the image path as the user's message, in the correct dictionary format history.append({'role': 'user', 'content': (file_obj.name,)}) elif text: # Add the text message as the user's message, in the correct dictionary format history.append({'role': 'user', 'content': text}) else: return history return "", None, history def get_agent_response(history): if not history: return history # The user's message is the content of the last dictionary in the history user_message = history[-1]['content'] # Pass the full history (excluding the un-filled bot response) to the chat function response = me.chat(user_message, history[:-1]) # Append the bot's response to the history as a new dictionary history.append({'role': 'assistant', 'content': response}) return history # Connect the components to their functions msg.submit( fn=add_message, inputs=[msg, gr.File(visible=False), chatbot_state], outputs=[msg, upload_btn, chatbot_state], queue=False, ).then( fn=get_agent_response, inputs=chatbot_state, outputs=chatbot, queue=False ) submit_btn.click( fn=add_message, inputs=[msg, gr.File(visible=False), chatbot_state], outputs=[msg, upload_btn, chatbot_state], queue=False, ).then( fn=get_agent_response, inputs=chatbot_state, outputs=chatbot, queue=False ) upload_btn.upload( fn=add_message, inputs=[msg, upload_btn, chatbot_state], outputs=[msg, upload_btn, chatbot_state], queue=False, ).then( fn=get_agent_response, inputs=chatbot_state, outputs=chatbot, queue=False ) # Make the profile image clickable to change the image profile_button.click( fn=get_random_local_image, inputs=None, outputs=profile_image ) demo.launch()