added adjustmensts to roles and questions

This commit is contained in:
OwusuBlessing
2024-09-10 21:22:52 +01:00
parent 348c871abc
commit 594f0eadb3
5 changed files with 339 additions and 71 deletions
+3 -59
View File
@@ -19,7 +19,7 @@ def allowed_file(filename):
"""Check if the file has an allowed extension."""
return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
@sops_bp.route('/get_roles', methods=['POST'])
@sops_bp.route('/personal_assessment/get_roles', methods=['POST'])
def get_roles():
# Check if the post request has the file part
if 'document' not in request.files:
@@ -44,7 +44,8 @@ def get_roles():
docs = load_document(file_path)
# Generate roles from the docs
roles = sop_generator.get_roles(docs)["roles"]
parser = DocumentParser()
roles = parser.get_roles(docs)["roles"]
# Cleanup: Delete all files in the upload directory after processing
delete_all_files_in_directory(upload_folder)
@@ -60,63 +61,6 @@ def get_roles():
@sops_bp.route('/generate_questions_from_doc', methods=['POST'])
def generate_questions_from_sop():
# Check if the POST request has the file part
if 'document' not in request.files:
return jsonify({"error": "No file part", "message": "Please upload a file with the key 'document'."}), 400
print("Running................")
file = request.files['document']
roles_json = request.form.get('roles') # Get the roles as a JSON string
if not roles_json:
return jsonify({"error": "No roles provided", "message": "Please provide a list of roles in the 'roles' field."}), 400
try:
roles = json.loads(roles_json) # Parse the roles from JSON string to a list
print(f"Roles are:{roles}")
except json.JSONDecodeError:
return jsonify({"error": "Invalid JSON", "message": "The 'roles' field contains invalid JSON."}), 400
# If the user does not select a file, the browser may also submit an empty part without a filename
if file.filename == '':
return jsonify({"error": "No selected file", "message": "A file was not selected for upload. Please select a valid file."}), 400
if file and allowed_file(file.filename):
filename = secure_filename(file.filename)
upload_folder = current_app.config['UPLOAD_FOLDER']
file_path = os.path.join(upload_folder, filename)
# Save the file to the upload folder
file.save(file_path)
try:
# Use the utility function to generate docs from the file
docs = load_document(file_path)
# Check if the document can generate SOPs for the roles
status_check = sop_generator.check_role_sop(roles=roles, docs=docs)
if not status_check["status"]:
return jsonify({"error": "Document cannot extract SOPs", "message": status_check["message"]}), 400
# Generate SOPs based on the roles provided
sop_generator = DocumentParser()
sops = sop_generator.generate_sops_from_doc(docs)
# Cleanup: Delete all files in the upload directory after processing
delete_all_files_in_directory(upload_folder)
return jsonify({"sops": sops, "message": "SOPs successfully generated for the roles from the document."}), 200
except Exception as e:
# Cleanup: Delete all files in the upload directory if an error occurs
delete_all_files_in_directory(upload_folder)
return jsonify({"error": "Processing error", "message": f"An error occurred while processing the document: {str(e)}"}), 500
return jsonify({"error": "File type not allowed", "message": "The uploaded file type is not allowed. Please upload a PDF, DOC, or DOCX file."}), 400
@sops_bp.route('/personal_assessment/generate_sops_from_doc', methods=['POST'])
+9 -9
View File
@@ -1,21 +1,26 @@
from pydantic import BaseModel, Field
from typing import List, Optional
class RoleSops(BaseModel):
role:str
class Categories(BaseModel):
must: Optional[List[str]] = Field(default_factory=list)
shall: Optional[List[str]] = Field(default_factory=list)
will: Optional[List[str]] = Field(default_factory=list)
class RoleSops(BaseModel):
role:str
sops:Categories
#class RoleSOPs(BaseModel):
# sops: SOPs
class Roles_response(BaseModel):
roles: list[str]
class SOPsFound(BaseModel):
message: str
status: bool
class RolesResponse(BaseModel):
roles: List[str]
class SOPsResponse(BaseModel):
roles_sops: List[RoleSops]
@@ -27,11 +32,6 @@ class VisionMissionResponse(BaseModel):
mission: List[str]
class Categories(BaseModel):
must: Optional[List[str]] = Field(default_factory=list)
shall: Optional[List[str]] = Field(default_factory=list)
will: Optional[List[str]] = Field(default_factory=list)
class ExecutivesSops(BaseModel):
executive_sops: List[RoleSops]
+3 -2
View File
@@ -275,7 +275,7 @@ def get_sop_for_department_workers():
5. Use the provided document and the workers and department information to generate the SOP.
6. If the provided document cannot provide SOPs for a specific worker stated, then return an empty list for the SOP for that worker.
Example format:
Example forma
{
"departments": [
{
@@ -287,8 +287,9 @@ def get_sop_for_department_workers():
"shall": ["Submit monthly reports"],
"will": ["Improve efficiency"]
}
]
}
]
}s
}
'''
+294
View File
@@ -0,0 +1,294 @@
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.models.sop_response_schemas import *
from dotenv import load_dotenv
load_dotenv()
#SopGeneratorDocument
class DocumentParser:
def __init__(self):
self.api_key = os.getenv("OPENAI_API_KEY")
self.client = OpenAI(api_key=self.api_key)
self.model = "gpt-4o-2024-08-06"
def _extract_text_from_docs(self, docs):
"""Extract text content from document objects."""
return [doc.page_content for doc in docs]
# Existing methods...
def extract_sops_from_doc(self, docs) -> VisionMissionResponse:
"""
Extracts Vision, Mission, and SOPs categorized into 'must,' 'shall,' and 'will' from the document.
:param docs: The document(s) from which to extract information.
:return: VisionMissionResponse containing the vision, mission, and role-specific SOPs.
"""
try:
docs_text = self._extract_text_from_docs(docs)
prompt = get_sop_extraction_from_doc()
response = self.client.beta.chat.completions.parse(
model=self.model,
messages=[
{
"role": "system",
"content": f'''{prompt}'''
},
{
"role": "user",
"content": [{"type": "text", "text": text} for text in docs_text],
}
],
response_format=SOPsResponse,
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:
return False
def extract_vision_mission(self, docs) -> VisionMissionResponse:
"""
Extracts Vision, Mission, and SOPs categorized into 'must,' 'shall,' and 'will' from the document.
:param docs: The document(s) from which to extract information.
:return: VisionMissionResponse containing the vision, mission, and role-specific SOPs.
"""
try:
docs_text = self._extract_text_from_docs(docs)
prompt = get_vision_mission_extraction_from_doc()
response = self.client.beta.chat.completions.parse(
model=self.model,
messages=[
{
"role": "system",
"content": f'''{prompt}'''
},
{
"role": "user",
"content": [{"type": "text", "text": text} for text in docs_text],
}
],
response_format=VisionMissionResponse,
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:
return False
'''def extract_departments_and_managers(self, docs):
"""
Extract departments and managerial roles from the document.
:param docs: List of document chunks
:return: Dictionary containing departments and their managerial roles
"""
try:
docs_text = self._extract_text_from_docs(docs)
prompt = get_departments_and_roles_extraction_prompt()
response = self.client.beta.chat.completions.parse(
model=self.model,
messages=[
{"role": "system", "content": prompt},
{"role": "user", "content": [{"type": "text", "text": text} for text in docs_text]}
],
response_format=DepartmentsAndRolesResponse,
max_tokens=4096,
temperature=0.1
)
return json.loads(response.choices[0].message.content)
except json.JSONDecodeError:
return False'''
def extract_departments_and_managers_workers(self, docs):
"""
Extract departments, managers, and workers from the document.
:param docs: List of document chunks
:return: Dictionary containing departments, their managers, and workers.
"""
try:
docs_text = self._extract_text_from_docs(docs)
prompt = get_departments_managers_workers_extraction_prompt() # Update your prompt to handle managers and workers
response = self.client.beta.chat.completions.parse(
model=self.model,
messages=[
{"role": "system", "content": prompt},
{"role": "user", "content": [{"type": "text", "text": text} for text in docs_text]}
],
response_format=DepartmentsAndWorkersResponse, # Use the updated response schema
max_tokens=4096,
temperature=0.1
)
return json.loads(response.choices[0].message.content)
except json.JSONDecodeError:
return False
def extract_roles_with_reference_managers(self, docs, reference_roles):
try:
# Extract departments and managers from the document
sop_doc = DocumentParser()
departments_and_roles = sop_doc.extract_departments_and_managers_workers(docs)
# Prepare extracted roles (only managers)
extracted_managers = []
for department in departments_and_roles['departments']:
extracted_managers.extend([
{
'name': manager['name'],
'position': manager.get('position', 'Unknown Position'),
'role': manager.get('role', 'Unknown Role') # PRP or SRP classification
}
for manager in department['managers']
])
# Generate prompt for the LLM to compare reference roles with extracted roles
prompt = get_roles_reference_comparison()
# Send prompt to the LLM for comparison
response = self.client.beta.chat.completions.parse(
model=self.model,
messages=[
{"role": "system", "content": f"The reference roles are{reference_roles} while the extracted roles are {extracted_managers}"},
{"role": "user", "content": prompt}
],
max_tokens=1024,
temperature=0.1,
response_format=RolesComparisonResponse
)
comparison_result = json.loads(response.choices[0].message.content)
# Return the result as a JSON response
return comparison_result
except Exception as e:
print(f"Error occurred: {e}")
return False
def extract_roles_with_reference_workers(self, docs, reference_roles):
try:
# Extract departments and managers from the document
sop_doc = DocumentParser()
departments_and_roles = sop_doc.extract_departments_and_managers_workers(docs)
# Prepare extracted roles (only managers)
extracted_workers = []
for department in departments_and_roles['departments']:
extracted_workers.extend([
{
'name': worker['name'],
'position': worker.get('position', 'Unknown Position'),
'role': "worker" # PRP or SRP classification
}
for worker in department['workers']
])
# Generate prompt for the LLM to compare reference roles with extracted roles
prompt = get_roles_reference_comparison()
# Send prompt to the LLM for comparison
response = self.client.beta.chat.completions.parse(
model=self.model,
messages=[
{"role": "system", "content": f"The reference roles are{reference_roles} while the extracted roles are {extracted_workers}"},
{"role": "user", "content": prompt}
],
max_tokens=1024,
temperature=0.1,
response_format=RolesComparisonResponse
)
comparison_result = json.loads(response.choices[0].message.content)
# Return the result as a JSON response
return comparison_result
except Exception as e:
print(f"Error occurred: {e}")
return False
def extract_managers_workers(self, docs):
"""
Extract departments, managers, and workers from the document.
:param docs: List of document chunks
:return: Dictionary containing departments, their managers, and workers.
"""
try:
docs_text = self._extract_text_from_docs(docs)
prompt = get_managers_workers_extraction_prompt() # Update your prompt to handle managers and workers
response = self.client.beta.chat.completions.parse(
model=self.model,
messages=[
{"role": "system", "content": prompt},
{"role": "user", "content": [{"type": "text", "text": text} for text in docs_text]}
],
response_format=DepartmentMembers, # Use the updated response schema
max_tokens=4096,
temperature=0.1
)
return json.loads(response.choices[0].message.content)
except json.JSONDecodeError:
return False
def extract_sops_for_workers_by_department(self, docs,depts_workers):
"""
Extract departments, managers, and workers from the document.
:param docs: List of document chunks
:return: Dictionary containing departments, their managers, and workers.
"""
try:
docs_text = self._extract_text_from_docs(docs)
prompt = get_sop_for_department_workers() # Update your prompt to handle managers and workers
response = self.client.beta.chat.completions.parse(
model=self.model,
messages=[
{"role": "system", "content": prompt},
{"role": "user", "content": f"Workers information: {depts_workers}"},
{"role": "user", "content": [{"type": "text", "text": text} for text in docs_text]}
],
response_format=WorkerSOPsResponse, # Use the updated response schema
max_tokens=4096,
temperature=0.1
)
return json.loads(response.choices[0].message.content)
except json.JSONDecodeError:
return False
+30 -1
View File
@@ -14,7 +14,7 @@ class DocumentParser:
def __init__(self):
self.api_key = os.getenv("OPENAI_API_KEY")
self.client = OpenAI(api_key=self.api_key)
self.model = "gpt-4o-2024-08-06"
self.model = "gpt-4o-mini"
def _extract_text_from_docs(self, docs):
"""Extract text content from document objects."""
@@ -93,6 +93,35 @@ class DocumentParser:
except:
return False
def get_roles(self, docs):
# Extract the text content from the Document objects
docs_text = [doc.page_content for doc in docs]
response = self.client.beta.chat.completions.parse(
model=self.model,
messages=[
{
"role": "system",
"content": '''Suppose you are a role/postion extractor from a company document ,
you extract the roles as a list e.g["finacial analyist,"data scientist]... etc
if no roles are found return and empty list''',
},
{
"role": "user",
"content": [
{
"type": "text", # Changed from "document chunk" to "text"
"text": text
} for text in docs_text
]
}
],
response_format=Roles_response,
max_tokens=1024,
temperature=0.1
)
return json.loads(response.choices[0].message.content)
'''def extract_departments_and_managers(self, docs):
"""
Extract departments and managerial roles from the document.