paihari's picture
Update
40b264c verified
import os
from dotenv import load_dotenv
from openai import OpenAI
import gradio as gr
import requests
import json
from PyPDF2 import PdfReader
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.openai = OpenAI()
self.name = "Hariprasad Bantwal"
# Load LinkedIn PDF
reader = PdfReader("./me/linkedin.pdf")
self.linkedin = ""
for page in reader.pages:
text = page.extract_text()
if text:
self.linkedin += text
# Load summary text
with open("./me/summary.txt", "r", encoding="utf-8") as f:
self.summary = f.read()
# Load Resume PDF
resume_reader = PdfReader("./me/Resume.pdf")
self.resume = ""
for resume_page in resume_reader.pages:
text = resume_page.extract_text()
if text:
self.resume += text
# Load 2004-08-Reference
with open("./me/2004-08-Reference.txt", "r", encoding="utf-8") as f:
self.reference_2004_08 = f.read()
# Load 2008-10-Reference_1
with open("./me/2008-10-Reference_1.txt", "r", encoding="utf-8") as f:
self.reference_2008_10_1 = f.read()
# Load 2008-10-Reference
with open("./me/2008-10-Reference.txt", "r", encoding="utf-8") as f:
self.reference_2008_10 = f.read()
# Load 2011-13-Reference
with open("./me/2011-13-Reference.txt", "r", encoding="utf-8") as f:
self.reference_2011_13 = f.read()
# Load 2013-18-Reference
with open("./me/2013-18-Reference.txt", "r", encoding="utf-8") as f:
self.reference_2013_18 = f.read()
# Load 2018-19-Reference
with open("./me/2018-19-Reference.txt", "r", encoding="utf-8") as f:
self.reference_2018_19 = f.read()
# Load 2020-23-Reference
with open("./me/2020-23-Reference.txt", "r", encoding="utf-8") as f:
self.reference_2020_23 = f.read()
# Load 2023-24-Reference
with open("./me/2023-24-Reference.txt", "r", encoding="utf-8") as f:
self.reference_2023_24 = 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, \
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. \
You are given a list of Reference Letters of {self.name}'s which gives you the context, time frame, company name you should also try to use this 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."
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"\n\n## 2004-08-Reference:\n{self.reference_2004_08}\n\n## 2008-10-Reference_1:\n{self.reference_2008_10_1}\n\n"
system_prompt += f"\n\n## 2008-10-Reference:\n{self.reference_2008_10}\n\n## 2011-13-Reference:\n{self.reference_2011_13}\n\n"
system_prompt += f"\n\n## 2013-18-Reference:\n{self.reference_2013_18}\n\n## 2018-19-Reference:\n{self.reference_2018_19}\n\n"
system_prompt += f"\n\n## 2020-23-Reference:\n{self.reference_2020_23}\n\n## 2023-24-Reference:\n{self.reference_2023_24}\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}]
done = False
while not done:
response = self.openai.chat.completions.create(
model="gpt-4o-mini",
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()