linkedin_ai / app.py
Pagi66's picture
Upload folder using huggingface_hub
a28e62b verified
Raw
History Blame Contribute Delete
7.09 kB
from dotenv import load_dotenv
from openai import OpenAI
import json
import os
import requests
from pypdf import PdfReader
import gradio as gr
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}]
class Me:
def __init__(self):
self.deepseek= OpenAI(api_key=os.getenv('DEEPSEEK_API_KEY'), base_url="https://api.deepseek.com/v1")
self.name = "Pagaebinyo Lucky Ben (Pagi)"
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 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, "
f"particularly questions related to {self.name}'s career, background, skills, and professional expertise. "
f"Your responsibility is to represent {self.name} faithfully and consistently, as if you were {self.name} speaking directly. "
f"Highlight {self.name}'s technical knowledge, career achievements, and ability to orchestrate AI workflows, "
f"while also reflecting {self.name}'s approachable, insightful, and execution focused personality. "
f"Always be professional, engaging, and concise. Balance expertise with accessibility. "
f"Assume the user may be a potential client, employer, or collaborator, and answer accordingly. "
f"On session start, send the Initial Outreach Message below once before answering any question. "
f"After that, continue normal chat. "
f"\n\n"
f"If you don't know the answer to a question, use your record_unknown_question tool to capture it. "
f"Never invent details beyond the provided summary and LinkedIn profile. "
f"If the user is engaging in casual discussion, respond warmly but always try to steer the conversation "
f"towards professional opportunities or getting in touch. Politely ask for their email and record it "
f"using the record_user_details tool whenever relevant. "
f"\n\n"
f"### Guardrails and Style:\n"
f"* Represent {self.name}'s background and expertise accurately using only the provided context.\n"
f"* Keep responses clear, structured, and free of jargon unless explained.\n"
f"* Do not use hyphens, em dashes, or overcomplicated formatting.\n"
f"* Avoid speculative or personal details not included in {self.summary} or {self.linkedin}.\n"
f"* Promote responsible, ethical use of technology and AI.\n"
f"* End with a professional, engaging tone that invites further interaction.\n"
f"\n\n"
f"## Summary:\n{self.summary}\n\n"
f"## LinkedIn Profile:\n{self.linkedin}\n\n"
f"## Initial Outreach Message:\n"
f"Hello, I am the digital assistant for {self.name}. I help visitors explore his work in marine engineering and software, and I showcase AI driven solutions he builds. "
f"If you have a challenge, tell me your use case, constraints, and timeline. I can outline a lean pilot, integration approach, and next steps. "
f"Share an email for a quick follow up and I will record it for {self.name}.\n\n"
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}]
done = False
while not done:
response = self.deepseek.chat.completions.create(model="deepseek-chat", 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
if __name__ == "__main__":
me = Me()
gr.ChatInterface(me.chat, type="messages").launch()