Spaces:
Running
Running
| import streamlit as st | |
| from streamlit_js_eval import streamlit_js_eval | |
| from azure.storage.blob import BlobServiceClient | |
| from azure.cosmos import CosmosClient, exceptions | |
| from PyPDF2 import PdfReader | |
| import io | |
| import openai | |
| import json | |
| import os | |
| import uuid | |
| import time | |
| import calendar | |
| import re | |
| openai.api_key = os.getenv("OPENAI_API_KEY") | |
| openai.api_base = "https://tensora-oai.openai.azure.com/" | |
| openai.api_type = "azure" | |
| openai.api_version = "2023-05-15" | |
| connection_string = os.getenv("CONNECTION") | |
| blob_service_client = BlobServiceClient.from_connection_string(connection_string) | |
| def upload_blob(pdf_name, json_data, pdf_data_jobdescription,pdf_data_cvs, pre_generated_bool, custom_questions): | |
| try: | |
| container_name = "jobdescriptions" | |
| # json_blob_name = f"{pdf_name}_jsondata.json" | |
| pdf_blob_name_jobdescription = f"{pdf_name}.pdf" | |
| container_client = blob_service_client.get_container_client(container_name) | |
| # json_blob_client = container_client.get_blob_client(json_blob_name) | |
| # json_blob_client.upload_blob(json_data.encode('utf-8'), overwrite=True) | |
| pdf_blob_client = container_client.get_blob_client(pdf_blob_name_jobdescription) | |
| pdf_blob_client.upload_blob(pdf_data_jobdescription, overwrite=True) | |
| upload_job_db_item(pdf_name,len(pdf_data_cvs),json.loads(json_data),pre_generated_bool, custom_questions) | |
| if pre_generated_bool: | |
| for i,question in enumerate(custom_questions): | |
| question_nr_for_id = i+1 | |
| question_id = pdf_name + "-question-nr-" + str(question_nr_for_id)+str(calendar.timegm(time.gmtime())) | |
| upload_question_db_item(question_id, pdf_name, question,st.session_state["pdf_data_jobdescription_string"]) | |
| links = [] | |
| names = [] | |
| for i,cv in enumerate(pdf_data_cvs): | |
| cv_nr_for_id = i+1 | |
| cv_session_state_string = "cv-"+str(cv_nr_for_id) | |
| session_state_name = st.session_state[cv_session_state_string] | |
| names.append(session_state_name) | |
| cv_id = pdf_name + "-cv-nr-" + str(cv_nr_for_id)+str(calendar.timegm(time.gmtime())) | |
| upload_db_item(session_state_name, json.loads(json_data), pdf_name, cv_id) | |
| pdf_blob_name_cv = f"{cv_id}.pdf" | |
| pdf_blob_client = container_client.get_blob_client(pdf_blob_name_cv) | |
| pdf_blob_client.upload_blob(pdf_data_cvs[i], overwrite=True) | |
| links.append("https://tensora.ai/workgenius/cv-evaluation2/?job="+cv_id) | |
| st.success('Data and PDF files have been successfully uploaded. The link to the chatbot for the potential candidate is the following: ') | |
| for i,link in enumerate(links): | |
| st.write("Link for the candidate "+names[i]+": ") | |
| st.write(link) | |
| return True | |
| except Exception as e: | |
| print(f"Fehler beim Hochladen der Daten: {str(e)}") | |
| return False | |
| def upload_job_db_item(id, number_of_applicants, data, pre_generated_bool, custom_questions): | |
| endpoint = "https://wg-candidate-data.documents.azure.com:443/" | |
| key = os.getenv("CONNECTION_DB") | |
| client = CosmosClient(endpoint, key) | |
| database = client.get_database_client("ToDoList") | |
| container = database.get_container_client("JobData") | |
| job_item = { | |
| "id": id, | |
| 'partitionKey' : 'wg-job-data-v1', | |
| "title": data["title"], | |
| "number_of_applicants": number_of_applicants, | |
| "every_interview_conducted": False, | |
| "evaluation_email": data["email"], | |
| "question_one": data["question_one"], | |
| "question_two": data["question_two"], | |
| "question_three": data["question_three"], | |
| "pre_generated": pre_generated_bool, | |
| "custom_questions": custom_questions | |
| } | |
| try: | |
| # Fügen Sie das Element in den Container ein | |
| container.create_item(body=job_item) | |
| print("Eintrag erfolgreich in die Cosmos DB eingefügt. Container: Job Data") | |
| except exceptions.CosmosHttpResponseError as e: | |
| print(f"Fehler beim Schreiben in die Cosmos DB: {str(e)}") | |
| except Exception as e: | |
| print(f"Allgemeiner Fehler: {str(e)}") | |
| def upload_db_item(name, data, job_description_id, cv_id): | |
| endpoint = "https://wg-candidate-data.documents.azure.com:443/" | |
| key = os.getenv("CONNECTION_DB") | |
| client = CosmosClient(endpoint, key) | |
| database = client.get_database_client("ToDoList") | |
| container = database.get_container_client("Items") | |
| candidate_item = { | |
| "id": cv_id, | |
| 'partitionKey' : 'wg-candidate-data-v1', | |
| "name": name, | |
| "title": data["title"], | |
| "interview_conducted": False, | |
| "ai_summary": "", | |
| "evaluation_email": data["email"], | |
| "question_one": data["question_one"], | |
| "question_two": data["question_two"], | |
| "question_three": data["question_three"], | |
| "job_description_id": job_description_id, | |
| } | |
| try: | |
| # Fügen Sie das Element in den Container ein | |
| container.create_item(body=candidate_item) | |
| print("Eintrag erfolgreich in die Cosmos DB eingefügt. Container: Items(candidate Data)") | |
| except exceptions.CosmosHttpResponseError as e: | |
| print(f"Fehler beim Schreiben in die Cosmos DB: {str(e)}") | |
| except Exception as e: | |
| print(f"Allgemeiner Fehler: {str(e)}") | |
| def upload_question_db_item(id, job_id, question, job_content): | |
| endpoint = "https://wg-candidate-data.documents.azure.com:443/" | |
| key = os.getenv("CONNECTION_DB") | |
| client = CosmosClient(endpoint, key) | |
| database = client.get_database_client("ToDoList") | |
| container = database.get_container_client("Questions") | |
| question_item = { | |
| "id": id, | |
| "partitionKey" : "wg-question-data-v1", | |
| "job_id": job_id, | |
| "question_content": question, | |
| "job_description": job_content, | |
| } | |
| try: | |
| # Fügen Sie das Element in den Container ein | |
| container.create_item(body=question_item) | |
| print("Eintrag erfolgreich in die Cosmos DB eingefügt. Container: Questions(Question Data)") | |
| except exceptions.CosmosHttpResponseError as e: | |
| print(f"Fehler beim Schreiben in die Cosmos DB: {str(e)}") | |
| except Exception as e: | |
| print(f"Allgemeiner Fehler: {str(e)}") | |
| st.markdown( | |
| """ | |
| <style> | |
| [data-testid=column]{ | |
| text-align: center; | |
| display: flex; | |
| align-items: center; | |
| justify-content: center; | |
| } | |
| </style> | |
| """, | |
| unsafe_allow_html=True, | |
| ) | |
| col1, col2 = st.columns([2, 1]) | |
| if "ai_questions" not in st.session_state: | |
| st.session_state["ai_questions"] = None | |
| if "pdf_data_cvs" not in st.session_state: | |
| st.session_state["pdf_data_cvs"] = None | |
| if "pdf_data_cvs_string" not in st.session_state: | |
| st.session_state["pdf_data_cvs_string"] = None | |
| if "pdf_data_cvs_names" not in st.session_state: | |
| st.session_state["pdf_data_cvs_names"] = [] | |
| if "pdf_data_jobdescription" not in st.session_state: | |
| st.session_state["pdf_data_jobdescription"] = None | |
| if "pdf_data_jobdescription_string" not in st.session_state: | |
| st.session_state["pdf_data_jobdescription_string"] = None | |
| if "final_question_string" not in st.session_state: | |
| st.session_state["final_question_string"] = [] | |
| def adjust_numbering(lst): | |
| return [f"{i + 1}. {item.split('. ', 1)[1]}" for i, item in enumerate(lst)] | |
| with open("sys_prompt_frontend.txt") as f: | |
| sys_prompt = f.read() | |
| col1.title("Job description upload") | |
| col2.image("https://www.workgenius.com/wp-content/uploads/2023/03/WorkGenius_navy-1.svg") | |
| st.write("Please upload the job description and resume(s) as PDF and enter the job title for the position. To receive the evaluation of the potential candidate(s), please provide your email address.") | |
| upload_success = True | |
| #This container represents the form | |
| with st.container(): | |
| #Form section for the files, names, title and mail | |
| uploaded_file_jobdescription = st.file_uploader("Upload the job description:", type=["pdf"], key="job") | |
| job_title = st.text_input("Enter the job title:", key="title") | |
| email = st.text_input("Enter the email:" , key="mail") | |
| uploaded_file_cvs = st.file_uploader("Upload the resume(s):", type=["pdf"],accept_multiple_files=True, key="cvs") | |
| for i,cv in enumerate(st.session_state["cvs"]): | |
| st.text_input(label="Enter the name of the "+str(i+1)+". CV (File: "+cv.name+")", value=cv.name,key="cv-"+str(i+1)) | |
| #Form section for the interview mode (pre generated or not) and additional questions | |
| if len(job_title) > 0 and len(email) > 0 and uploaded_file_jobdescription and len(uploaded_file_cvs)>0: | |
| st.write("Activate the toggle to generate and select the questions in advance. Otherwise the questions will be generated automatically during the interview.") | |
| if not st.session_state["pdf_data_cvs"] and not st.session_state["pdf_data_cvs_string"] and not st.session_state["pdf_data_jobdescription"] and not st.session_state["pdf_data_jobdescription_string"]: | |
| pdf_data_jobdescription = uploaded_file_jobdescription.read() | |
| pdf_data_jobdescription_string = "" | |
| pdf_reader_job = PdfReader(io.BytesIO(pdf_data_jobdescription)) | |
| for page_num in range(len(pdf_reader_job.pages)): | |
| page = pdf_reader_job.pages[page_num] | |
| pdf_data_jobdescription_string += page.extract_text() | |
| pdf_data_cvs = [] | |
| pdf_data_cvs_string = "" | |
| for i,cv in enumerate(st.session_state["cvs"]): | |
| print(cv.name) | |
| st.session_state["pdf_data_cvs_names"].append(cv.name) | |
| # print(cv.name) | |
| # print(cv.size) | |
| cv_data_bytes = cv.read() | |
| # print(len(cv_data_bytes)) | |
| pdf_data_cvs.append(cv_data_bytes) | |
| pdf_reader_cvs = PdfReader(io.BytesIO(cv_data_bytes)) | |
| pdf_data_cvs_string += "CV "+str(i+1)+": " | |
| for page_num in range(len(pdf_reader_cvs.pages)): | |
| page = pdf_reader_cvs.pages[page_num] | |
| pdf_data_cvs_string += page.extract_text() | |
| pdf_data_cvs_string += "\n" | |
| st.session_state["pdf_data_cvs"] = pdf_data_cvs | |
| st.session_state["pdf_data_cvs_string"] = pdf_data_cvs_string | |
| st.session_state["pdf_data_jobdescription"] = pdf_data_jobdescription | |
| st.session_state["pdf_data_jobdescription_string"] = pdf_data_jobdescription_string | |
| if st.session_state["pdf_data_cvs"]: | |
| pdf_data_cvs_string = "" | |
| initial_cv_length = len(st.session_state["pdf_data_cvs"]) | |
| for i,cv in enumerate(st.session_state["cvs"]): | |
| if cv.name not in st.session_state["pdf_data_cvs_names"]: | |
| st.session_state["pdf_data_cvs_names"].append(cv.name) | |
| print("At second:"+cv.name) | |
| cv_data_bytes = cv.read() | |
| st.session_state["pdf_data_cvs"].append(cv_data_bytes) | |
| pdf_reader_cvs = PdfReader(io.BytesIO(cv_data_bytes)) | |
| pdf_data_cvs_string += "CV "+str(i+1+initial_cv_length)+": " | |
| for page_num in range(len(pdf_reader_cvs.pages)): | |
| page = pdf_reader_cvs.pages[page_num] | |
| pdf_data_cvs_string += page.extract_text() | |
| pdf_data_cvs_string += "\n" | |
| st.session_state["pdf_data_cvs_string"] += pdf_data_cvs_string | |
| for i,name in enumerate(st.session_state["pdf_data_cvs_names"]): | |
| # print(name) | |
| found = False | |
| for j,cv in enumerate(st.session_state["cvs"]): | |
| # print(cv.name) | |
| if name == cv.name: | |
| found = True | |
| if not found: | |
| print("gelöscht: "+name) | |
| del st.session_state["pdf_data_cvs"][i] | |
| del st.session_state["pdf_data_cvs_names"][i] | |
| pre_generate = st.toggle("Activate to pre generate questions", key="pre_toggle") | |
| if pre_generate: | |
| system = sys_prompt.format(job=st.session_state["pdf_data_jobdescription_string"], resume=st.session_state["pdf_data_cvs_string"], n=15) | |
| if not st.session_state["ai_questions"]: | |
| try: | |
| # st.write("The questions are generated. This may take a short moment...") | |
| st.info("The questions are generated. This may take a short moment.", icon="ℹ️") | |
| with st.spinner("Loading..."): | |
| res = openai.ChatCompletion.create( | |
| engine="gpt-4", | |
| temperature=0.2, | |
| messages=[ | |
| { | |
| "role": "system", | |
| "content": system, | |
| }, | |
| ], | |
| ) | |
| st.session_state["ai_questions"] = [item for item in res.choices[0]["message"]["content"].split("\n") if len(item) > 0] | |
| for i,q in enumerate(res.choices[0]["message"]["content"].split("\n")): | |
| st.session_state["disable_row_"+str(i)] = False | |
| st.rerun() | |
| except Exception as e: | |
| print(f"Fehler beim generieren der Fragen: {str(e)}") | |
| st.error("An error has occurred. Please reload the page or contact the admin.", icon="🚨") | |
| else: | |
| if len(st.session_state["final_question_string"]) <= 0: | |
| for i,question in enumerate(st.session_state["ai_questions"]): | |
| cols = st.columns([5,1]) | |
| with cols[1]: | |
| # if st.button("Accept",use_container_width=True,key="btn_accept_row_"+str(i)): | |
| # print("accept") | |
| # pattern = re.compile(r"^[1-9][0-9]?\.") | |
| # questions_length = len(st.session_state["final_question_string"]) | |
| # question_from_text_area = st.session_state["text_area_"+str(i)] | |
| # question_to_append = str(questions_length+1)+"."+re.sub(pattern, "", question_from_text_area) | |
| # st.session_state["final_question_string"].append(question_to_append) | |
| # st.session_state["disable_row_"+str(i)] = True | |
| # st.rerun() | |
| if st.button("Delete",use_container_width=True,key="btn_del_row_"+str(i)): | |
| print("delete") | |
| st.session_state["ai_questions"].remove(question) | |
| st.rerun() | |
| with cols[0]: | |
| st.text_area(label="Question "+str(i+1)+":",value=question,label_visibility="collapsed",key="text_area_"+str(i),disabled=st.session_state["disable_row_"+str(i)]) | |
| st.write("If you are satisfied with the questions, then accept them. You can still sort them afterwards.") | |
| if st.button("Accept all questions",use_container_width=True,key="accept_all_questions"): | |
| print("accept all") | |
| for i,question in enumerate(st.session_state["ai_questions"]): | |
| print("accept") | |
| pattern = re.compile(r"^[1-9][0-9]?\.") | |
| questions_length = len(st.session_state["final_question_string"]) | |
| question_from_text_area = st.session_state["text_area_"+str(i)] | |
| question_to_append = str(questions_length+1)+"."+re.sub(pattern, "", question_from_text_area) | |
| st.session_state["final_question_string"].append(question_to_append) | |
| st.session_state["disable_row_"+str(i)] = True | |
| st.rerun() | |
| for i,final_q in enumerate(st.session_state["final_question_string"]): | |
| cols_final = st.columns([5,1]) | |
| with cols_final[1]: | |
| if st.button("Up",use_container_width=True,key="btn_up_row_"+str(i),disabled=True if i == 0 else False): | |
| if i > 0: | |
| # Tausche das aktuelle Element mit dem vorherigen Element | |
| st.session_state.final_question_string[i], st.session_state.final_question_string[i - 1] = \ | |
| st.session_state.final_question_string[i - 1], st.session_state.final_question_string[i] | |
| st.session_state.final_question_string = adjust_numbering(st.session_state.final_question_string) | |
| st.rerun() | |
| if st.button("Down",use_container_width=True,key="btn_down_row_"+str(i), disabled=True if i == len(st.session_state["final_question_string"])-1 else False): | |
| if i < len(st.session_state.final_question_string) - 1: | |
| # Tausche das aktuelle Element mit dem nächsten Element | |
| st.session_state.final_question_string[i], st.session_state.final_question_string[i + 1] = \ | |
| st.session_state.final_question_string[i + 1], st.session_state.final_question_string[i] | |
| st.session_state.final_question_string = adjust_numbering(st.session_state.final_question_string) | |
| st.rerun() | |
| with cols_final[0]: | |
| st.write(final_q) | |
| else: | |
| with st.expander("Enter up to three predefined questions if needed. Otherwise leave it blank:"): | |
| question_one = st.text_input("Enter the first question:") | |
| question_two = st.text_input("Enter the second question:") | |
| question_three = st.text_input("Enter the third question:") | |
| #Form section for Submit and Clear | |
| col_submit_btn, col_empty, col_clear_btn = st.columns([1,4, 1]) | |
| if col_clear_btn.button("Clear " ,use_container_width=True): | |
| streamlit_js_eval(js_expressions="parent.window.location.reload()") | |
| #Code to handle the input | |
| if col_submit_btn.button("Submit", use_container_width=True): | |
| if len(job_title) > 0 and len(email) > 0 and uploaded_file_jobdescription and len(uploaded_file_cvs)>0: | |
| data = { | |
| "title": job_title, | |
| "email": email, | |
| "question_one": "", | |
| "question_two": "", | |
| "question_three": "", | |
| } | |
| if not st.session_state["pre_toggle"]: | |
| if question_one: | |
| data["question_one"] = question_one | |
| if question_two: | |
| data["question_two"] = question_two | |
| if question_three: | |
| data["question_three"] = question_three | |
| json_data = json.dumps(data, ensure_ascii=False) | |
| # Eine zufällige UUID generieren | |
| random_uuid = uuid.uuid4() | |
| # Die UUID als String darstellen | |
| uuid_string = str(random_uuid) | |
| pdf_name = uuid_string | |
| print(st.session_state["final_question_string"]) | |
| # pdf_data_cv = uploaded_file_cv.read() | |
| print(len(st.session_state["pdf_data_cvs"])) | |
| print(st.session_state["pdf_data_cvs_names"]) | |
| upload_success = upload_blob(pdf_name, json_data, st.session_state["pdf_data_jobdescription"],st.session_state["pdf_data_cvs"],st.session_state["pre_toggle"],st.session_state["final_question_string"]) | |
| else: | |
| st.write("Please fill out both fields and upload a PDF file.") | |
| if not upload_success: | |
| st.error('An error has occurred. Please contact the administrator. Sorry for the inconvenience.', icon="🚨") | |