updated feedback:

2025-02-10 21:39:23 +00:00
parent 82df82f7c5 b22d4afeb6
commit a760469ecd
11 changed files with 1729 additions and 343 deletions
@@ -0,0 +1,304 @@
+import os
+import requests
+from dotenv import load_dotenv
+from langchain_openai import ChatOpenAI
+from langchain_core.prompts.prompt import PromptTemplate
+from langchain_core.output_parsers import StrOutputParser, JsonOutputParser
+from langchain_openai import OpenAIEmbeddings
+from langchain_core.documents import Document
+from uuid import uuid4
+import json
+import getpass
+import numpy as np
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from sklearn.metrics.pairwise import cosine_similarity
+from typing import List
+import time
+from datetime import datetime
+import pytz
+import logging
+load_dotenv()
+
+os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
+
+llm_temp = ChatOpenAI(model="gpt-4o-mini", temperature=0.7)
+def generate_theme(conversation_data, resume, full_history, form_response=None, feedback=None, previous_result=None) -> dict:
+    try:
+        # Define prompt for summarizing and extracting the required fields
+        theme_prompt = PromptTemplate(
+            template="""
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+You are a Fire Fighter Interview preparation assistant that generates STARTPOP FORMAT based on user interaction with AI.
+Your responsibilities include carefully analyzing user interactions, themes, resumes,Onboarding questions and answers and work history to generate detailed STARTPOP formats for specific themes.
+
+### Context and Guidelines:
+1. **Purpose**: Generate a single behavioral question with a detailed STARTPOP format.
+2. **Input Sources**:
+   - Current theme
+   - User interaction with AI
+   - User resume
+   - Full work history
+   - Onboarding questions and answers for additional context
+3. **Output Format**: JSON object with the following fields:
+   - `theme_title`: Title of the theme provided.
+   - `question`: Behavioral question aligned with the theme.
+   - `Situation`: A bulleted list (75-100 words).
+   - `Task`: A bulleted list (50 words).
+   - `Action`: A bulleted list (2 negative actions and 2 positive actions).
+   - `Results and Transitions`: A bulleted list (25-50 words).
+   - `Personal Lessons`: A bulleted list (25-50 words).
+   - `Observations of Others`: A bulleted list (25 words).
+   - `Professional Connection`: A bulleted list (25-50 words). Additionally:
+     - Connect to the theme of the question.
+     - Creatively express why you should be part of their team.
+
+### Key Concepts in Firefighting:
+Throughout most Probationary Firefighter Interviews, evaluators assess alignment with the **7 Main Concepts of Firefighting**:
+- **High Performance Teams**
+- **Situational Awareness**
+- **Being a Great Problem Solver**
+- **Customer Service**
+- **Building Construction, Mechanical Aptitude**
+- **Emergency Medicine Experience**
+- **Mental and Physical Health**
+
+Additionally, they evaluate communication skills, competence, and likability.
+
+### 20 Important Themes:
+These themes are used for behavioral questions:
+- Customer Service
+- Conflict
+- Challenge
+- Leadership
+- Stress
+- Successful Team
+- Diversity
+- Mistake
+- Unsuccessful Team
+- Disagreement
+- Bent a Rule
+- Delivered a Difficult Message
+- Displayed Integrity
+- Took a Shortcut
+- Didn’t Follow the Rules
+- Emergency Response
+- Dealt with Disabilities
+- Solved a Big Problem
+- Continuous Improvement
+- Handled Sensitive Information
+
+### Behavioral Question Starters:
+Behavioral questions often begin with phrases like:
+- "Tell me a time when..."
+- "Can you tell me about a time when you..."
+- "Describe a situation where you had to..."
+- "Give me an example of how you..."
+- "Have you ever been in a position where you needed to..."
+- "Walk me through a time when you..."
+
+### STARTPOP Framework:
+The STARTPOP framework enhances the traditional STAR method. It includes:
+1. **Situation**: Set up the scenario concisely (include dates, ages, places, and circumstances).
+2. **Task**: Explain what needed to be done and why.
+3. **Actions**: Outline both negative and positive approaches.
+4. **Results and Transitions**: Share outcomes and ensure coherence.
+5. **Personal Lessons**: Reflect on what you learned.
+6. **Observations of Others**: Share insights about others involved.
+7. **Professional Connection**: Relate the experience to firefighting and express your desire to join the team.
+
+### Example STARTPOP:
+**Question**: Tell me a time when you made a mistake and how you fixed it?
+
+- **Situation**:
+  - In the Fall, my business, Tiger Building Services, does eavestrough cleaning.
+  - In 2019, we were working on a job late in the day, tired and running out of sunlight.
+  - I used handheld blowers without checking the wetness of debris, creating a muddy mess on the customer's deck.
+  - The customer was upset, and I realized my mistake.
+
+- **Task**:
+  - Defuse the situation and clean up the mess quickly.
+  - Protect my company's reputation and ensure good customer experiences.
+
+- **Actions**:
+  - Negative: Matching the customer's anger or ignoring the problem.
+  - Positive: Getting off the roof safely, apologizing, and switching strategies.
+  - Positive: Cleaning the gutters by hand and offering a free soft wash service.
+
+- **Results and Transitions**:
+  - The job took longer than expected, but we waived fees due to the inconvenience.
+  - The customer was satisfied after our resolution plan.
+
+- **Personal Lessons**:
+  - I learned to own up to mistakes, stay empathetic, and de-escalate tense situations.
+
+- **Observations of Others**:
+  - People are entitled to their emotions, and following SOPs prevents mistakes.
+
+- **Professional Connection**:
+  - Mistakes happen, but learning from them is crucial.
+  - I align with Markham Fire's values of transparency and accountability.
+
+### JSON Output Requirements:
+Generate a well-structured JSON output with the following fields:
+- `theme_title`
+- `question`
+- `Situation`
+- `Task`
+- `Action`
+- `Results and Transitions`
+- `Personal Lessons`
+- `Observations of Others`
+- `Professional Connection`
+
+### Review Process:
+1. Ensure all news items align with the specified theme and meet relevance criteria.
+2. Verify the JSON format is flawless, comprehensive, and well-structured.
+
+### Additional Notes:
+- You may be provided with feedback and previous results if the user is dissatisfied.
+- Use this feedback to refine and regenerate the STARTPOP.
+
+<|eot_id|><|start_header_id|>user<|end_header_id|>
+Rules for Generating Each Component:
+1. Situation: 75-100 words.
+2. Task: 50 words.
+3. Actions: 2 negative actions and 2 positive actions.
+4. Results: 25-50 words.
+5. Personal Lessons: 25-50 words.
+6. Observations of Others: 25 words.
+7. Professional Connection: 25-50 words + creative connection to the theme and team invitation.
+NOTE: MAKE SURE THE OUT IS WELL  DETAILED
+CONVERSATION DATA: {conversation_data}
+FEEDBACK: {feedback}
+PREVIOUS RESULT: {previous_result}
+USER RESUME: {resume}
+FULL WORK HISTORY: {full_history}
+Onboarding questions and answers for additional context: {form_response}
+<|start_header_id|>assistant<|end_header_id|>
+Return just the JSON output without any other explanation or comments.
+Thank you for your thorough and precise processing!
+
+""",
+            input_variables=["resume", "conversation_data", "feedback","form_response" "previous_result", "full_history"],
+        )
+
+        # Pipeline to process the prompt and parse output
+        theme_router = theme_prompt | llm_temp | JsonOutputParser()
+
+        # Call the pipeline and generate the cohesive output
+        output = theme_router.invoke({
+            "conversation_data": conversation_data,
+            "feedback": feedback,
+            "previous_result": previous_result,
+            "resume": resume,
+            "full_history": full_history,
+            "form_response":form_response
+        })
+
+        print(f"Output: {output}")
+        return output
+
+    except Exception as e:
+        print(f"Error: {e}")
+        return {}
+
+
+
+
+from fastapi import Response, HTTPException, Depends
+from typing import Optional
+import os
+import requests
+import datetime
+import base64  # For encoding the PDF content in Base64
+
+@app.post("/rescue-career/generate-theme")
+async def generate_pdf_endpoint(
+    request: GeneratePDFRequest,
+    api_key: str = Depends(get_api_key)
+):
+    
+    try:
+        # Fetch conversation data using the conversation_id
+        conversation_data = await get_conversation_data(request.conversation_id)
+        
+        if not conversation_data:
+            raise HTTPException(
+                status_code=404,
+                detail=f"No conversation found with ID {request.conversation_id}"
+            )
+        
+        resume_docs = ""
+        if request.resume_url:
+            docs = load_document(request.resume_url)
+            if not docs:
+                raise HTTPException(
+                    status_code=400, 
+                    detail="Invalid resume URL: Unable to fetch document"
+                )
+            resume_docs = "\n".join(f"- {doc.page_content}" for doc in docs)
+
+        full_history_docs = ""
+        if request.full_history_url:
+            docs = load_document(request.full_history_url)
+            if not docs:
+                raise HTTPException(
+                    status_code=400, 
+                    detail="Invalid full_history URL: Unable to fetch document"
+                )
+            full_history_docs = "\n".join(f"- {doc.page_content}" for doc in docs)
+
+        form_response_docs = ""
+        if request.form_id:
+            try:
+                x_api_key = os.getenv("BACKEND_XAPI_KEY")
+                url = f"{os.getenv('BACKEND_BASE_URL')}/v3/api/custom/theme-document/answer/{request.form_id}?x-project={x_api_key}"
+                result = requests.get(url)
+                form_response = result.json()  # Return response in JSON format
+                form_response_docs = "\n".join(f"- {form_response}")
+            except:
+                raise HTTPException(
+                    status_code=400, 
+                    detail="Unable to fetch onboarding data"
+                )
+
+        # Generate theme data using the generate_theme function
+        theme_data = generate_theme(
+            conversation_data=conversation_data,
+            feedback=request.feedback,
+            previous_result=request.previous_results,
+            resume=resume_docs,
+            form_response=form_response_docs,
+            full_history=full_history_docs
+        )  
+
+        if not theme_data:
+            raise HTTPException(
+                status_code=500,
+                detail="Failed to generate theme data"
+            )
+        
+        # Generate the PDF using the create_pdf function
+        pdf_content = create_pdf(theme_data)
+        
+        # Encode the PDF content in Base64
+        pdf_base64 = base64.b64encode(pdf_content).decode("utf-8")
+        
+        # Create filename with timestamp
+        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
+        filename = f"theme_{timestamp}.pdf"
+        
+        # Return both the PDF (as Base64) and the theme data in a JSON response
+        return {
+            "theme_data": theme_data,
+            "pdf": {
+                "filename": filename,
+                "content": pdf_base64
+            }
+        }
+    
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"Error generating PDF: {str(e)}"
+        )
@@ -0,0 +1,368 @@
+import os
+from typing import Optional
+from fastapi import FastAPI, HTTPException, Security, Depends
+from fastapi.security import APIKeyHeader
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
+from dotenv import load_dotenv
+from utils.document_loader import load_document
+import json
+from pydantic import BaseModel
+from src.llm import ai_chat
+from langchain_openai import ChatOpenAI
+import requests
+import tempfile
+from scripts.generate_pdf  import create_pdf
+from scripts.generate_theme import generate_theme
+from scripts.generate_quiz import generate_quiz
+from typing import Dict, Any
+from fastapi.responses import Response
+from datetime import datetime
+from fastapi import HTTPException
+from pydantic import BaseModel
+from typing import Optional, Union, Dict, Any
+import os
+import requests
+import os
+from PyPDF2 import PdfReader
+from config import QUIZ_TYPES
+# Load environment variables
+load_dotenv()
+API_KEY = os.getenv("API_KEY_ACCESS")
+
+base_path = os.path.join("data", "config_files")
+QUESTIONS_PATH = os.path.join(base_path, "questions.json")
+THEME_CONTEXT_PATH = os.path.join(base_path, "theme_context.json")
+
+# Load themes at module level
+with open(THEME_CONTEXT_PATH, "r") as f:
+    themes = json.load(f)
+
+# Initialize FastAPI app
+app = FastAPI(
+    title="Fire Fighter Interview API",
+    description="API For fire fighter",
+    version="1.0.0"
+)
+
+# Add CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Setup API key authentication
+api_key_header = APIKeyHeader(name="Authorization", auto_error=False)
+
+
+
+async def get_api_key(api_key_header: str = Security(api_key_header)) -> str:
+    """Validate API key from header"""
+    if not api_key_header or not api_key_header.startswith('Bearer '):
+        raise HTTPException(
+            status_code=401,
+            detail={"error": "Unauthorized", "message": "API key is missing or invalid."}
+        )
+    
+    token = api_key_header.split(' ')[1]
+    if token != API_KEY:
+        raise HTTPException(
+            status_code=401,
+            detail={"error": "Unauthorized", "message": "API key does not match."}
+        )
+    
+    return token
+
+class ChatRequest(BaseModel):
+    resume_url: Optional[str] = None
+    query: str=None
+    conversation_id: str
+    theme_id: Optional[int] = 1
+
+class ChatResponse(BaseModel):
+    message: str
+    end: bool
+    error: Optional[str] = None
+
+
+
+class GeneratePDFRequest(BaseModel):
+    conversation_id: str
+    feedback: Optional[str] = None
+    previous_results: Optional[Dict[str, Any]] = None
+    resume_url: Optional[str] = None
+    full_history_url: Optional[str] = None
+    form_id:Optional[int] = None
+
+class QuizRequest(BaseModel):
+    pdf_url: str
+    quiz_type: int  # 1, 2, or 3 corresponding to QUIZ_TYPES
+
+class QuizResponse(BaseModel):
+    success: bool
+    message: str
+    quiz_data: Optional[Dict[str, Any]] = None
+    error: Optional[str] = None
+    
+
+async def extract_pdf_text(pdf_url: str) -> Union[str, None]:
+    """Extract text from PDF and handle potential errors."""
+    try:
+        response = requests.get(pdf_url)
+        response.raise_for_status()
+        
+        # Create a temporary file
+        with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as temp_pdf:
+            temp_pdf.write(response.content)
+            temp_path = temp_pdf.name
+
+        # Extract text from PDF
+        reader = PdfReader(temp_path)
+        text = "\n\n".join(
+            page.extract_text() for page in reader.pages if page.extract_text()
+        )
+
+        # Clean up temporary file
+        os.unlink(temp_path)
+
+        if not text.strip():
+            return None
+        return text
+
+    except requests.RequestException as e:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Error downloading PDF: {str(e)}"
+        )
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"Error processing PDF: {str(e)}"
+        )
+
+@app.post("/rescue-career/chat", response_model=ChatResponse)
+async def chat_endpoint(
+    request: ChatRequest,
+    api_key: str = Depends(get_api_key)
+):
+    try:
+        # Validate theme
+        matching_themes = [t for t in themes if t["id"] == request.theme_id]
+        if not matching_themes:
+            raise HTTPException(
+                status_code=400,
+                detail=f"No theme found with ID {request.theme_id}"
+            )
+
+        # Only try to load document if resume_url is provided
+        resume_docs = ""
+        if request.resume_url:
+            docs = load_document(request.resume_url)
+            if not docs:
+                raise HTTPException(
+                    status_code=400, 
+                    detail="Invalid resume URL: Unable to fetch document"
+                )
+            resume_docs = "\n".join(f"- {doc.page_content}" for doc in docs)
+
+        # Get AI chat response
+        response = ai_chat(
+            query=request.query,
+            conversation_id=request.conversation_id,
+            theme_id=request.theme_id,
+            resume=resume_docs
+        )
+
+        # Parse response
+        try:
+            parsed_response = json.loads(response)
+            return ChatResponse(
+                message=parsed_response.get("message", ""),
+                end=parsed_response.get("end", "no") == "yes",
+                error=None
+            )
+        except json.JSONDecodeError:
+            return ChatResponse(
+                message=response,
+                end=False,
+                error=None
+            )
+
+    except HTTPException as e:
+        # Re-raise HTTP exceptions
+        raise
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"Error processing chat request: {str(e)}"
+        )
+     
+
+@app.post("/rescue-career/generate-theme")
+async def generate_pdf_endpoint(
+    request: GeneratePDFRequest,
+    api_key: str = Depends(get_api_key)
+):
+    
+    try:
+        # Here you would fetch the conversation data using the conversation_id
+        # This is a placeholder - replace with your actual conversation data fetching logic
+        conversation_data = await get_conversation_data(request.conversation_id)
+        
+        if not conversation_data:
+            raise HTTPException(
+                status_code=404,
+                detail=f"No conversation found with ID {request.conversation_id}"
+            )
+        
+        resume_docs = ""
+        if request.resume_url:
+            docs = load_document(request.resume_url)
+            if not docs:
+                raise HTTPException(
+                    status_code=400, 
+                    detail="Invalid resume URL: Unable to fetch document"
+                )
+            resume_docs = "\n".join(f"- {doc.page_content}" for doc in docs)
+
+
+        full_history_docs = ""
+        if request.full_history_url:
+            docs = load_document(request.full_history_url)
+            if not docs:
+                raise HTTPException(
+                    status_code=400, 
+                    detail="Invalid full_history URL: Unable to fetch document"
+                )
+            full_history_docs = "\n".join(f"- {doc.page_content}" for doc in docs)
+
+        form_response_docs = ""
+        if request.form_id:
+            try:
+                x_api_key = os.getenv("BACKEND_XAPI_KEY")
+                url = f"{os.getenv('BACKEND_BASE_URL')}/v3/api/custom/theme-document/answer/{request.form_id}?x-project={x_api_key}"
+                result = requests.get(url)
+                form_response = result.json()  # Return response in JSON format
+                form_response_docs =  "\n".join(f"- {form_response}")
+            except:
+                raise HTTPException(
+                    status_code=400, 
+                    detail="Unable to fetch onborading data"
+                )
+        # Generate theme data using the generate_theme function
+        theme_data = generate_theme(
+            conversation_data=conversation_data,
+            feedback=request.feedback,
+            previous_result=request.previous_results,
+            resume = resume_docs,
+            form_response=form_response_docs,
+            full_history = full_history_docs
+        )  
+        
+        if not theme_data:
+            raise HTTPException(
+                status_code=500,
+                detail="Failed to generate theme data"
+            )
+        
+        # Generate the PDF using the create_pdf function
+        pdf_content = create_pdf(theme_data)
+        
+        # Create filename with timestamp
+        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+        filename = f"theme_{timestamp}.pdf"
+        
+        # Return the PDF as a response
+        return Response(
+            content=pdf_content,
+            media_type="application/pdf",
+            headers={
+                "Content-Disposition": f'attachment; filename="{filename}"'
+            }
+        )
+    
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"Error generating PDF: {str(e)}"
+        )
+        
+@app.post("/rescue-career/generate-quiz", response_model=QuizResponse)
+async def generate_quiz_endpoint(
+    request: QuizRequest,
+    api_key: str = Depends(get_api_key)
+):
+    """Generate quiz based on PDF content and quiz type."""
+    # Validate quiz type
+    if request.quiz_type not in QUIZ_TYPES:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Invalid quiz type. Must be one of: {list(QUIZ_TYPES)}"
+        )
+
+    try:
+        # Extract text from PDF
+        pdf_text = await extract_pdf_text(request.pdf_url)
+        if not pdf_text:
+            return QuizResponse(
+                success=False,
+                message="PDF extraction completed but no text content found",
+                error="Empty PDF content"
+            )
+            
+        # Generate quiz using the existing function
+        quiz_data = generate_quiz(
+            startpop_pdf=pdf_text,
+            quiz_type=request.quiz_type
+        )
+
+        if not quiz_data:
+            return QuizResponse(
+                success=False,
+                message="Quiz generation failed",
+                error="Unable to generate quiz from the provided content"
+            )
+
+        return QuizResponse(
+            success=True,
+            message="Quiz generated successfully",
+            quiz_data=quiz_data
+        )
+
+    except HTTPException as he:
+        raise he
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"Unexpected error during quiz generation: {str(e)}"
+        )
+        
+        
+        
+async def get_conversation_data(conversation_id: str) -> dict:
+    """
+    Fetch conversation data using the conversation ID.
+    Replace this with your actual implementation to fetch conversation data.
+    """
+    try:
+        storage_path = "conversations.json"
+        with open(storage_path, 'r') as f:
+                convs =  json.load(f)
+        convs_id = convs[conversation_id]
+        return convs_id
+    except Exception as e:
+        print(f"Error fetching conversation data: {e}")
+        return None
+    
+    
+@app.on_event("startup")
+async def startup_event():
+    """Initialize required components on startup"""
+    pass
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run("app:app", host="0.0.0.0", port=5048, reload=True)