Spaces:
Sleeping
Sleeping
| from dotenv import load_dotenv | |
| from openai import OpenAI | |
| import json | |
| import os | |
| import requests | |
| from pypdf import PdfReader | |
| from pathlib import Path | |
| import gradio as gr | |
| import time | |
| load_dotenv(override=True) | |
| def push(text): | |
| 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"): | |
| push(f"Recording {name} with email {email} and notes {notes}") | |
| return {"recorded": "ok"} | |
| def record_unknown_question(question): | |
| push(f"Recording {question}") | |
| return {"recorded": "ok"} | |
| 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 | |
| } | |
| } | |
| tools = [{"type": "function", "function": record_user_details_json}, | |
| {"type": "function", "function": record_unknown_question_json}] | |
| def load_pdf_with_cache(pdf_path: str, cache_dir="me/cache") -> str: | |
| pdf_path = Path(pdf_path) | |
| cache_dir = Path(cache_dir) | |
| cache_dir.mkdir(parents=True, exist_ok=True) | |
| cache_file = cache_dir / f"{pdf_path.stem}.txt" | |
| # Use cached text if available | |
| if cache_file.exists(): | |
| with open(cache_file, "r", encoding="utf-8") as f: | |
| return f.read() | |
| # Otherwise parse PDF (slow path) | |
| reader = PdfReader(str(pdf_path)) | |
| text = "" | |
| for page in reader.pages: | |
| page_text = page.extract_text() | |
| if page_text: | |
| text += page_text + "\n" | |
| # Save cache for future cold starts | |
| with open(cache_file, "w", encoding="utf-8") as f: | |
| f.write(text) | |
| return text | |
| class Me: | |
| def __init__(self): | |
| self.openai = OpenAI() | |
| # self.gemini = OpenAI(api_key=os.getenv("GOOGLE_API_KEY"), base_url="https://generativelanguage.googleapis.com/v1beta/openai/") | |
| # self.groq = OpenAI(api_key=os.getenv("GROQ_API_KEY"), base_url="https://api.groq.com/openai/v1") | |
| # self.groq_model_name = "openai/gpt-oss-120b" | |
| self.cur_model = 'gpt' | |
| self.name = "Mohit Kumar" | |
| self.linkedin = load_pdf_with_cache("me/linkedin.pdf") | |
| # 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() | |
| # reader = PdfReader("me/mkt_v1_2pg.pdf") | |
| # self.resume = "" | |
| # for page in reader.pages: | |
| # text = page.extract_text() | |
| # if text: | |
| # self.resume += text | |
| self.resume = load_pdf_with_cache("me/mkt_v1_2pg.pdf") | |
| print("Linkedin and resume loaded successfully.", flush=True) | |
| self._system_prompt = self.system_prompt() | |
| def stream_llm(self, messages): | |
| """ | |
| Tries Groq streaming first, falls back to OpenAI streaming | |
| """ | |
| if self.cur_model == 'groq': | |
| try: | |
| return self.groq.chat.completions.create( | |
| model=self.groq_model_name, | |
| messages=messages, | |
| # tools=tools, | |
| stream=True, | |
| ) | |
| except Exception as e: | |
| print("Groq streaming failed:", e, flush=True) | |
| return self.openai.chat.completions.create( | |
| model="gpt-5-nano", | |
| messages=messages, | |
| # tools=tools, | |
| stream=True, | |
| ) | |
| else: | |
| print("self.cur_model changed. Using gpt nano for streaming.", flush=True) | |
| return self.openai.chat.completions.create( | |
| model="gpt-5-nano", | |
| messages=messages, | |
| # tools=tools, | |
| stream=True, | |
| ) | |
| 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) | |
| 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): | |
| 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. \ | |
| Do not be too pushy about getting in touch via email. my email id is strictly mohit.in@outlook.com, do not use any other email id. You can provide my linkedin profile url as a contact option along with my email id. \ | |
| Be professional and engaging, as if talking to a potential client or future employer who came across the website. Answer in a concise and to the point manner." | |
| system_prompt += f"\n\n## Summary:\n{self.summary}\n\n## LinkedIn Profile:\n{self.linkedin}\n\n## Resume:\n{self.resume}\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): | |
| messages = [{"role": "system", "content": self._system_prompt}] + history + [{"role": "user", "content": message}] | |
| # if not history: | |
| # # messages = [{"role": "system", "content": self.system_prompt()}] + history + [{"role": "user", "content": message}] | |
| # messages = [{"role": "system", "content": self.system_prompt()}] | |
| # else: | |
| # messages = [] | |
| # messages += history | |
| # messages.append({"role": "user", "content": message}) | |
| done = False | |
| while not done: | |
| response = self.openai.chat.completions.create(model="gpt-5-nano", messages=messages, tools=tools) | |
| # try: | |
| # # response = self.gemini.chat.completions.create(model="gemini-2.5-flash", messages=messages, tools=tools) | |
| # response = self.groq.chat.completions.create(model=self.groq_model_name, messages=messages, tools=tools) | |
| # print("Groq successful") | |
| # except Exception as e: | |
| # print("Groq failed:", e, flush=True) | |
| # self.cur_model = 'openai' | |
| # response = self.openai.chat.completions.create(model="gpt-5-nano", messages=messages, tools=tools) | |
| # print("GPT 5 nano successful.", flush=True) | |
| 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 | |
| # stream = self.stream_llm(messages) | |
| # partial = "" | |
| # for chunk in stream: | |
| # delta = chunk.choices[0].delta | |
| # if delta and delta.content: | |
| # partial += delta.content | |
| # yield partial | |
| # time.sleep(0.01) | |
| if __name__ == "__main__": | |
| me = Me() | |
| gr.ChatInterface(me.chat, type="messages").launch() | |