code fix

conv_career_tools_adriana.py

@@ -1,347 +1,347 @@
-#!/usr/bin/env python
-# coding: utf-8
-
-# # Career Conversation Project
-
-# In[41]:
-
-
-from dotenv import load_dotenv
-from openai import OpenAI
-import json
-import os
-import requests
-from pypdf import PdfReader
-import gradio as gr
-
-
-# In[42]:
-
-
-load_dotenv(override=True)
-openai = OpenAI()
-gemini = OpenAI(
-    api_key = os.getenv('GOOGLE_API_KEY'),
-    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
-)
-
-
-# In[43]:
-
-
-pushover_user = os.getenv("PUSHOVER_USER")
-pushover_token = os.getenv("PUSHOVER_TOKEN")
-pushover_url = "https://api.pushover.net/1/messages.json"
-
-
-# In[44]:
-
-
-reader = PdfReader("../me/linkedin.pdf")
-linkedin = ""
-for page in reader.pages:
-    text = page.extract_text()
-    if text:
-        linkedin += text
-
-with open("../me/summary.txt", "r", encoding="utf-8") as f:
-    summary = f.read()
-
-name = "Adriana Salcedo"
-
-
-# In[45]:
-
-
-def push(message):
-    print(f"Push: {message}")
-    payload = {"user": pushover_user, "token": pushover_token, "message": message}
-    requests.post(pushover_url, data=payload)
-
-
-# ## Tools
-
-# In[46]:
-
-
-def record_user_details(email, name="Name not provided", notes="not provided"):
-    push(f"Recording interest from {name} with email {email} and notes {notes}")
-    return {"recorded": "ok"}
-
-
-def record_unknown_question(question):
-    push(f"Recording {question} asked that I couldn't answer")
-    return {"recorded": "ok"}
-
-def record_personal_question(question, acceptable):
-    if acceptable:
-        push(f'A personal question was asked and answered:\n {question}')
-    else:
-        push(f'A personal question was asked and not answered:\n {question}')
-    return {"recorded": "ok"}
-    
-
-def record_skill_question(question):
-    push(f'A skill-related question was asked:\n {question}')
-    return {'recorded': 'ok'}
-
-
-# In[47]:
-
-
-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
-    }
-}
-
-
-# In[48]:
-
-
-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
-    }
-}
-
-
-# In[49]:
-
-
-record_personal_question_json = {
-    'name': 'record_personal_question',
-    'description': 'Use this tool to log if a personal question was asked. Indicate if the question is acceptable (can be answered) or not.',
-    'parameters': {
-        'type': 'object',
-        'properties': {
-            'question': {
-                'type': 'string',
-                'description': 'Question that will not be answered'
-            },
-            'acceptable': {
-                'type': 'boolean',
-                'description': 'Indicates if a question is acceptable or not'
-            }
-        },
-        'required': ['question', 'acceptable'],
-        'additionalProperties': False
-    }
-}
-
-
-# In[50]:
-
-
-record_skill_question_json = {
-    'name': 'record_skill_question',
-    'description': (
-        "Whenever a user asks about any skill, technology, tool, programming language, or experience"
-        "regardless of whether it is present in the profile or not. ALWAYS use this tool to notify the owner. "
-        "Pass the original user question as the argument. "
-        "Examples: 'Do you know Python?', 'Have you worked with Tableau?', 'Are you familiar with cloud computing?'"
-    ),
-    'parameters': {
-        'type': 'object',
-        'properties': {
-            'question': {
-                'type': 'string',
-                'description': 'Skill-related question was asked'
-            },
-        },
-        'required': ['question'],
-        'additionalProperties': False
-    }
-}
-
-
-# In[51]:
-
-
-tools = [{"type": "function", "function": record_user_details_json},
-        {"type": "function", "function": record_unknown_question_json},
-        {'type': 'function', 'function': record_personal_question_json},
-        {'type': 'function', 'function': record_skill_question_json}
-        
-]
-
-
-# In[52]:
-
-
-def handle_tool_calls(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
-
-
-# In[53]:
-
-
-system_prompt = f"You are acting as {name}. You are answering questions on {name}'s website, \
-particularly questions related to {name}'s career, background, skills and experience. \
-Your responsibility is to represent {name} for interactions on the website as faithfully as possible. \
-You are given a summary of {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. "
-
-system_prompt += f"\n\n## Summary:\n{summary}\n\n## LinkedIn Profile:\n{linkedin}\n\n"
-system_prompt += f"With this context, please chat with the user, always staying in character as {name}."
-
-
-# ## Implement Evaluator
-
-# In[54]:
-
-
-from pydantic import BaseModel
-
-class Evaluation(BaseModel):
-    is_acceptable: bool
-    feedback: str
-
-
-# In[55]:
-
-
-evaluator_system_prompt = f"You are an evaluator that decides whether a response to a question is acceptable. \
-You are provided with a conversation between a User and an Agent. Your task is to decide whether the Agent's latest response is acceptable quality. \
-The Agent is playing the role of {name} and is representing {name} on their website. \
-The Agent has been instructed to be professional and engaging, as if talking to a potential client or future employer who came across the website. \
-The Agent has been provided with context on {name} in the form of their summary and LinkedIn details. Here's the information:"
-
-evaluator_system_prompt += f"\n\n## Summary:\n{summary}\n\n## LinkedIn Profile:\n{linkedin}\n\n"
-evaluator_system_prompt += f"With this context, please evaluate the latest response, replying with whether the response is acceptable and your feedback if necessary."
-
-
-# In[56]:
-
-
-def evaluator_user_prompt(reply, message, history):
-    user_prompt = f"Here's the conversation between the User and the Agent: \n\n{history}\n\n"
-    user_prompt += f"Here's the latest message from the User: \n\n{message}\n\n"
-    user_prompt += f"Here's the latest response from the Agent: \n\n{reply}\n\n"
-    user_prompt += f"Please evaluate the response, replying with whether it is acceptable."
-    return user_prompt
-
-
-# In[57]:
-
-
-def evaluate(reply, message, history) -> Evaluation:
-
-    messages = [{"role": "system", "content": evaluator_system_prompt}] + [{"role": "user", "content": evaluator_user_prompt(reply, message, history)}]
-    response = gemini.beta.chat.completions.parse(model="gemini-2.0-flash", messages=messages, response_format=Evaluation)
-    return response.choices[0].message.parsed
-
-
-# In[58]:
-
-
-def push_evaluation(question, answer, evaluation):
-    message_text = (
-        f'New Evaluation:\n'
-        f'Question: {question}\n'
-        f'Agent answer: {answer}\n'
-        f'Evaluation: {'is acceptable' if evaluation.is_acceptable else 'not acceptable'}'
-    )
-
-    #print("MESSAGE TEXT FÜR PUSH:", message_text)
-    
-    payload = {"user": pushover_user, 
-               "token": pushover_token, 
-               "message": message_text}
-    requests.post(pushover_url, data=payload)
-
-
-# In[59]:
-
-
-def chat(message, history):
-
-    messages = [{"role": "system", "content": system_prompt}] + history + [{"role": "user", "content": message}]
-    done = False
-    while not done:
-
-        
-        response = openai.chat.completions.create(model="gpt-4o-mini", messages=messages, tools=tools)
-
-        finish_reason = response.choices[0].finish_reason
-
-
-        # Tool Calls
-        if finish_reason=="tool_calls":
-            msg = response.choices[0].message
-            tool_calls = msg.tool_calls
-            results = handle_tool_calls(tool_calls)
-            messages.append(msg)
-            messages.extend(results)
-
-            response_final = openai.chat.completions.create(model="gpt-4o-mini", messages=messages)
-            agent_reply = response_final.choices[0].message.content
-
-            # Evaluation
-            evaluation = evaluate(agent_reply, message, history)
-            push_evaluation(message, agent_reply, evaluation)
-
-            return agent_reply
-            
-        else:
-            done = True
-    return response.choices[0].message.content
-
-
-# In[ ]:
-
-
-demo = gr.ChatInterface(chat, type="messages")
-
-
-# In[ ]:
-
-
-if __name__ == '__main__':
-    demo.launch()
-
-
-# In[ ]:
-
-
-
-
+#!/usr/bin/env python
+# coding: utf-8
+
+# # Career Conversation Project
+
+# In[41]:
+
+
+from dotenv import load_dotenv
+from openai import OpenAI
+import json
+import os
+import requests
+from pypdf import PdfReader
+import gradio as gr
+
+
+# In[42]:
+
+
+load_dotenv(override=True)
+openai = OpenAI()
+gemini = OpenAI(
+    api_key = os.getenv('GOOGLE_API_KEY'),
+    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
+)
+
+
+# In[43]:
+
+
+pushover_user = os.getenv("PUSHOVER_USER")
+pushover_token = os.getenv("PUSHOVER_TOKEN")
+pushover_url = "https://api.pushover.net/1/messages.json"
+
+
+# In[44]:
+
+
+reader = PdfReader("../me/linkedin.pdf")
+linkedin = ""
+for page in reader.pages:
+    text = page.extract_text()
+    if text:
+        linkedin += text
+
+with open("../me/summary.txt", "r", encoding="utf-8") as f:
+    summary = f.read()
+
+name = "Adriana Salcedo"
+
+
+# In[45]:
+
+
+def push(message):
+    print(f"Push: {message}")
+    payload = {"user": pushover_user, "token": pushover_token, "message": message}
+    requests.post(pushover_url, data=payload)
+
+
+# ## Tools
+
+# In[46]:
+
+
+def record_user_details(email, name="Name not provided", notes="not provided"):
+    push(f"Recording interest from {name} with email {email} and notes {notes}")
+    return {"recorded": "ok"}
+
+
+def record_unknown_question(question):
+    push(f"Recording {question} asked that I couldn't answer")
+    return {"recorded": "ok"}
+
+def record_personal_question(question, acceptable):
+    if acceptable:
+        push(f'A personal question was asked and answered:\n {question}')
+    else:
+        push(f'A personal question was asked and not answered:\n {question}')
+    return {"recorded": "ok"}
+    
+
+def record_skill_question(question):
+    push(f'A skill-related question was asked:\n {question}')
+    return {'recorded': 'ok'}
+
+
+# In[47]:
+
+
+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
+    }
+}
+
+
+# In[48]:
+
+
+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
+    }
+}
+
+
+# In[49]:
+
+
+record_personal_question_json = {
+    'name': 'record_personal_question',
+    'description': 'Use this tool to log if a personal question was asked. Indicate if the question is acceptable (can be answered) or not.',
+    'parameters': {
+        'type': 'object',
+        'properties': {
+            'question': {
+                'type': 'string',
+                'description': 'Question that will not be answered'
+            },
+            'acceptable': {
+                'type': 'boolean',
+                'description': 'Indicates if a question is acceptable or not'
+            }
+        },
+        'required': ['question', 'acceptable'],
+        'additionalProperties': False
+    }
+}
+
+
+# In[50]:
+
+
+record_skill_question_json = {
+    'name': 'record_skill_question',
+    'description': (
+        "Whenever a user asks about any skill, technology, tool, programming language, or experience"
+        "regardless of whether it is present in the profile or not. ALWAYS use this tool to notify the owner. "
+        "Pass the original user question as the argument. "
+        "Examples: 'Do you know Python?', 'Have you worked with Tableau?', 'Are you familiar with cloud computing?'"
+    ),
+    'parameters': {
+        'type': 'object',
+        'properties': {
+            'question': {
+                'type': 'string',
+                'description': 'Skill-related question was asked'
+            },
+        },
+        'required': ['question'],
+        'additionalProperties': False
+    }
+}
+
+
+# In[51]:
+
+
+tools = [{"type": "function", "function": record_user_details_json},
+        {"type": "function", "function": record_unknown_question_json},
+        {'type': 'function', 'function': record_personal_question_json},
+        {'type': 'function', 'function': record_skill_question_json}
+        
+]
+
+
+# In[52]:
+
+
+def handle_tool_calls(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
+
+
+# In[53]:
+
+
+system_prompt = f"You are acting as {name}. You are answering questions on {name}'s website, \
+particularly questions related to {name}'s career, background, skills and experience. \
+Your responsibility is to represent {name} for interactions on the website as faithfully as possible. \
+You are given a summary of {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. "
+
+system_prompt += f"\n\n## Summary:\n{summary}\n\n## LinkedIn Profile:\n{linkedin}\n\n"
+system_prompt += f"With this context, please chat with the user, always staying in character as {name}."
+
+
+# ## Implement Evaluator
+
+# In[54]:
+
+
+from pydantic import BaseModel
+
+class Evaluation(BaseModel):
+    is_acceptable: bool
+    feedback: str
+
+
+# In[55]:
+
+
+evaluator_system_prompt = f"You are an evaluator that decides whether a response to a question is acceptable. \
+You are provided with a conversation between a User and an Agent. Your task is to decide whether the Agent's latest response is acceptable quality. \
+The Agent is playing the role of {name} and is representing {name} on their website. \
+The Agent has been instructed to be professional and engaging, as if talking to a potential client or future employer who came across the website. \
+The Agent has been provided with context on {name} in the form of their summary and LinkedIn details. Here's the information:"
+
+evaluator_system_prompt += f"\n\n## Summary:\n{summary}\n\n## LinkedIn Profile:\n{linkedin}\n\n"
+evaluator_system_prompt += f"With this context, please evaluate the latest response, replying with whether the response is acceptable and your feedback if necessary."
+
+
+# In[56]:
+
+
+def evaluator_user_prompt(reply, message, history):
+    user_prompt = f"Here's the conversation between the User and the Agent: \n\n{history}\n\n"
+    user_prompt += f"Here's the latest message from the User: \n\n{message}\n\n"
+    user_prompt += f"Here's the latest response from the Agent: \n\n{reply}\n\n"
+    user_prompt += f"Please evaluate the response, replying with whether it is acceptable."
+    return user_prompt
+
+
+# In[57]:
+
+
+def evaluate(reply, message, history) -> Evaluation:
+
+    messages = [{"role": "system", "content": evaluator_system_prompt}] + [{"role": "user", "content": evaluator_user_prompt(reply, message, history)}]
+    response = gemini.beta.chat.completions.parse(model="gemini-2.0-flash", messages=messages, response_format=Evaluation)
+    return response.choices[0].message.parsed
+
+
+# In[58]:
+
+
+def push_evaluation(question, answer, evaluation):
+    message_text = (
+        f'New Evaluation:\n'
+        f'Question: {question}\n'
+        f'Agent answer: {answer}\n'
+        f"Evaluation: {'is acceptable' if evaluation.is_acceptable else 'not acceptable'}"
+    )
+
+    #print("MESSAGE TEXT FÜR PUSH:", message_text)
+    
+    payload = {"user": pushover_user, 
+               "token": pushover_token, 
+               "message": message_text}
+    requests.post(pushover_url, data=payload)
+
+
+# In[59]:
+
+
+def chat(message, history):
+
+    messages = [{"role": "system", "content": system_prompt}] + history + [{"role": "user", "content": message}]
+    done = False
+    while not done:
+
+        
+        response = openai.chat.completions.create(model="gpt-4o-mini", messages=messages, tools=tools)
+
+        finish_reason = response.choices[0].finish_reason
+
+
+        # Tool Calls
+        if finish_reason=="tool_calls":
+            msg = response.choices[0].message
+            tool_calls = msg.tool_calls
+            results = handle_tool_calls(tool_calls)
+            messages.append(msg)
+            messages.extend(results)
+
+            response_final = openai.chat.completions.create(model="gpt-4o-mini", messages=messages)
+            agent_reply = response_final.choices[0].message.content
+
+            # Evaluation
+            evaluation = evaluate(agent_reply, message, history)
+            push_evaluation(message, agent_reply, evaluation)
+
+            return agent_reply
+            
+        else:
+            done = True
+    return response.choices[0].message.content
+
+
+# In[ ]:
+
+
+demo = gr.ChatInterface(chat, type="messages")
+
+
+# In[ ]:
+
+
+if __name__ == '__main__':
+    demo.launch()
+
+
+# In[ ]:
+
+
+
+