added worker validation bot

data/raw/coding_task_completion_document.pdf

@@ -0,0 +1,81 @@
+%PDF-1.3
+3 0 obj
+<</Type /Page
+/Parent 1 0 R
+/Resources 2 0 R
+/Contents 4 0 R>>
+endobj
+4 0 obj
+<</Filter /FlateDecode /Length 449>>
+stream
+xœm’OoÛ0Åïý<nÀ Zþç¸tÖÓ€ÛÙ±éD«-¢ì,ûô£dgi‘^l@¢Þ{ü‘1¼<D"+àüðµ‚Çg	2QUß*$‹\Äeꫪ>íL«ôªš^ag†±G§Œ†'ÓLj÷ªßëÛÇçd|“KE”¥P«D
+YB!#Q$A¶:)‚v
B;#AM0Zc:p§Úñálì+Z8ñ
+MMƒDÝÔ÷h–$؆ªfÉè8ã5OôÎ8ßÄ"ÙãšH5¶âMòµ(ãÄ×tÔ@éÙôójÓ™¾7gï´’Ѷ÷Bq&ò2I
¿¬r¾¸†wbtݤ›ÀÐß®o
+ÚÚÕÐY3pÙnÿ:Õã}¬,D’áXÀw�Àãóê“VLÉ‘—EM“Å%ôÕÍ£ˆñψ�ûˆ@–—a|¬ŸxÂÃt<†èº3:5¨¿�ó‚ܱ0¢åßPëA
+ÜÏ2Ñêi$òì=ß3ç¹ÍÒ3á†�@RuŠOÈÔC†erp¸„2šØ{Vdì½WºID™¯|[ZÞÂG‡Ã�×JF_ ŽâôþyÆ”áùþ¿Ë^j�¼ùx­ÿ!*

+endstream
+endobj
+1 0 obj
+<</Type /Pages
+/Kids [3 0 R ]
+/Count 1
+/MediaBox [0 0 595.28 841.89]
+>>
+endobj
+5 0 obj
+<</Type /Font
+/BaseFont /Helvetica-Bold
+/Subtype /Type1
+/Encoding /WinAnsiEncoding
+>>
+endobj
+6 0 obj
+<</Type /Font
+/BaseFont /Helvetica
+/Subtype /Type1
+/Encoding /WinAnsiEncoding
+>>
+endobj
+2 0 obj
+<<
+/ProcSet [/PDF /Text /ImageB /ImageC /ImageI]
+/Font <<
+/F1 5 0 R
+/F2 6 0 R
+>>
+/XObject <<
+>>
+>>
+endobj
+7 0 obj
+<<
+/Producer (PyFPDF 1.7.2 http://pyfpdf.googlecode.com/)
+/CreationDate (D:20240910213710)
+>>
+endobj
+8 0 obj
+<<
+/Type /Catalog
+/Pages 1 0 R
+/OpenAction [3 0 R /FitH null]
+/PageLayout /OneColumn
+>>
+endobj
+xref
+0 9
+0000000000 65535 f 
+0000000606 00000 n 
+0000000890 00000 n 
+0000000009 00000 n 
+0000000087 00000 n 
+0000000693 00000 n 
+0000000794 00000 n 
+0000001004 00000 n 
+0000001113 00000 n 
+trailer
+<<
+/Size 9
+/Root 8 0 R
+/Info 7 0 R
+>>
+startxref

src/api/app.py

@@ -2,6 +2,7 @@ import os
 from flask import Flask
 from src.api.routes.sops import sops_bp
 from src.api.routes.questions import qs_b
+from src.api.routes.chatbot import bot
 
 def create_app():
     app = Flask(__name__)
@@ -9,6 +10,7 @@ def create_app():
     # Register the blueprint with the desired prefix
     app.register_blueprint(sops_bp, url_prefix='/api/v1/sop')
     app.register_blueprint(qs_b,url_prefix='/api/v1/qs')
+    app.register_blueprint(bot,url_prefix='/api/v1/bot')
 
     # Set up the upload folder configuration inside the src directory
     UPLOAD_FOLDER = os.path.join(os.path.dirname(os.path.abspath(__file__)), '../../uploads')

src/api/routes/chatbot.py

@@ -0,0 +1,61 @@
+import os
+from flask import Blueprint, request, jsonify, current_app
+from werkzeug.utils import secure_filename
+from src.services.chatbot import Chatbot
+from src.utils.utils import delete_all_files_in_directory
+from src.utils.document_loader import load_document  
+
+
+# Initialize the Blueprint
+bot = Blueprint('chatbot', __name__)
+
+# Allowed file extensions
+ALLOWED_EXTENSIONS = {'pdf', 'doc', 'docx'}
+
+def allowed_file(filename):
+    """Check if the file has an allowed extension."""
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+@bot.route('/validate_worker_document', methods=['POST'])
+def validate_worker_document():
+    try:
+        # Retrieve form data
+        question = request.form.get('question')
+        file = request.files.get('document')
+
+        if not question or not file:
+            return jsonify({"error": "Missing data", "message": "Question or document not provided."}), 400
+        
+        if file.filename == '':
+            return jsonify({"error": "No selected file", "message": "No file was selected for upload."}), 400
+
+        if file and allowed_file(file.filename):
+            # Secure the file name and save it
+            filename = secure_filename(file.filename)
+            upload_folder = current_app.config['UPLOAD_FOLDER']
+            file_path = os.path.join(upload_folder, filename)
+            file.save(file_path)
+
+            # Load the document for processing
+            docs = load_document(file_path)
+
+            # Instantiate the chatbot service
+            chatbot = Chatbot()
+
+            # Validate the worker's response using the provided document
+            validation_result = chatbot.validate_worker(question, docs)
+
+            if not validation_result:
+                return jsonify({"error": "Validation failed", "message": "Validation process failed."}), 400
+
+            # Clean up uploaded file (optional)
+            os.remove(file_path)
+
+            # Return the validation result
+            return jsonify({"result": validation_result["result"]}), 200
+        
+        else:
+            return jsonify({"error": "Invalid file", "message": "File format not supported."}), 400
+
+    except Exception as e:
+        return jsonify({"error": "Internal Server Error", "message": str(e)}), 500

src/models/bot_response_schema.py

@@ -0,0 +1,7 @@
+
+from pydantic import BaseModel
+from typing import List, Dict
+
+class ValidateWorker(BaseModel):
+    result:str
+    

src/prompts/chatbot.py

@@ -0,0 +1,18 @@
+def validate_worker_prompt() -> str:
+   return """
+    You are a worker in the company "Validate" where you are asked a specific yes or no question:
+    
+    The worker's response: "Yes"
+
+    Since the worker answered "Yes," they are required to submit a document to justify their answer.
+    
+    Your role is to analyze the question being asked, review the document the worker uploaded, and verify whether the worker's answer is valid or not. 
+    The goal is to assess the document's content to see if it aligns with the worker's claim of "Yes."
+
+    response format
+    if not validated return "not validated"
+    {
+      result:"validated" 
+    }
+    """
+    

src/services/chatbot.py

@@ -0,0 +1,66 @@
+import os
+import json
+from openai import OpenAI
+from pydantic import BaseModel, Field
+from typing import List, Dict, Optional
+from src.prompts.sops import *
+from src.prompts.chatbot import *
+from src.models.sop_response_schemas import *
+from src.models.bot_response_schema import *
+from dotenv import load_dotenv
+load_dotenv()
+
+
+#SopGeneratorDocument
+class Chatbot:
+    def __init__(self):
+        self.api_key = os.getenv("OPENAI_API_KEY")
+        self.client = OpenAI(api_key=self.api_key)
+        self.model = "gpt-4o-mini"
+
+    def _extract_text_from_docs(self, docs):
+        """Extract text content from document objects."""
+        return [doc.page_content for doc in docs]
+    # Existing methods...
+
+    def validate_worker(self, question, docs) -> VisionMissionResponse:
+        """
+        This method is responsible for validating the worker's response ("yes" or "no") using the provided document(s).
+        The system generates a prompt, extracts document content, and validates the response using the GPT-4 model.
+
+        :param question: The yes/no question asked to the worker.
+        :param docs: A list of document(s) uploaded by the worker.
+        :return: VisionMissionResponse containing the validated result or None if an error occurs.
+        """
+        try:
+            docs_text = self._extract_text_from_docs(docs)
+            prompt = validate_worker_prompt()
+            response = self.client.beta.chat.completions.parse(
+                model=self.model,
+                messages=[
+                    {
+                        "role": "system",
+                        "content": f'''{prompt} The document is uploaded next.'''
+                    },
+                    {
+                        "role": "user",
+                        "content": f"Question :{question}",
+                    },
+                    {
+                        "role": "user",
+                        "content": [{"type": "text", "text": text} for text in docs_text],
+                    }
+                ],
+                response_format=ValidateWorker,
+                max_tokens=4096,
+                temperature=0.1
+            )
+
+            # Parse the response from the LLM
+            extracted_text = json.loads(response.choices[0].message.content)
+
+            return extracted_text
+
+        except Exception as e:
+            print(f"An error occurred: {e}")
+            return None

test.py

@@ -1,72 +1,16 @@
-import json
+# Example usage of the Chatbot class:
-from src.services.questions_generator import QuestionsGenerator
+from src.services.chatbot import Chatbot
+from src.utils.document_loader import load_document
+if __name__ == "__main__":
+    chatbot = Chatbot()
 
-# Mocking the SOPs input as described in your example
+    # Example inputs
-mock_sops_input = {
+    path = r"C:\Users\User\Desktop\Blessing_AI\MKD\test_erp_ai\erp_ai\test\erp_ai\data\raw\coding_task_completion_document.pdf"
-    "sops": {
-        "departments": [
-            {
-                "name": "Accounts Receivable",
-                "workers": [
-                    {
-                        "name": "Angela Lewis",
-                        "position": "AR Director",
-                        "sops": {
-                            "must": [],
-                            "shall": [],
-                            "will": []
-                        }
-                    },
-                    {
-                        "name": "Jamie Vega",
-                        "position": "AR Supervisor",
-                        "sops": {
-                            "must": [
-                                "Provide escalation information to the AR Director if additional escalations are needed."
-                            ],
-                            "shall": [],
-                            "will": []
-                        }
-                    },
-                    {
-                        "name": "Jessica Merzougui",
-                        "position": "AR Supervisor",
-                        "sops": {
-                            "must": [
-                                "Provide escalation information to the AR Director if additional escalations are needed."
-                            ],
-                            "shall": [],
-                            "will": []
-                        }
-                    },
-                    {
-                        "name": "Deniece Santos",
-                        "position": "AR Analyst",
-                        "sops": {
-                            "must": [],
-                            "shall": [],
-                            "will": []
-                        }
-                    }
-                ]
-            }
-        ]
-    }
-}
 
-# Defining the full input data including additional parameters
+    question = "Have you completed Task X?"
-input_data = {
+    user_input = "Yes"
-    "sops": json.dumps(mock_sops_input),  # Convert SOPs to JSON string format
+    docs = load_document(path)
-    "assessment_type": "progress",        # Set the assessment type
-    "frequency_type": "weekly",           # Set the frequency type (daily, weekly, etc.)
-    "duration": 4                         # Set the duration (number of frequency cycles, e.g., 4 weeks)
-}
 
-# Initialize the QuestionsGenerator
+    # Validate the worker's answer using the provided document
-generator = QuestionsGenerator()
+    validation_result = chatbot.validate_worker(question, docs)
-
+    print(validation_result)
-# Invoke the generate_questions method with the mock input
-questions_response = generator.generate_questions(input_data)
-
-# Print the generated questions response
-print(json.dumps(questions_response, indent=4))