first commit

Documents/Tickets.csv

@@ -0,0 +1,177 @@
+"The bus arrived late again, causing me to miss an important meeting.",Transportation
+"The taxi driver took a longer route, resulting in an inflated fare.",Transportation
+"There's no proper signage at the train station, making it confusing for passengers.",Transportation
+The flight was delayed for hours without any proper explanation.,Transportation
+The bus driver was rude and unprofessional during the entire journey.,Transportation
+"The train compartments were overcrowded, and there were no seats available.",Transportation
+"I booked a cab, but it never arrived at the designated pick-up location.",Transportation
+"The airline lost my luggage, and I haven't received any updates on its whereabouts.",Transportation
+"The taxi had a broken seatbelt, posing a safety risk during the ride.",Transportation
+"The bus broke down in the middle of the journey, causing a significant delay.",Transportation
+"The train schedule is inconsistent, with frequent cancellations and delays.",Transportation
+The airline customer service was unresponsive and provided no assistance.,Transportation
+"The taxi smelled strongly of smoke, making the ride uncomfortable and unpleasant.",Transportation
+There's a lack of wheelchair accessibility on public transportation vehicles.,Transportation
+The flight attendant was rude and disrespectful towards passengers.,Transportation
+"The bus station lacks proper facilities, including restrooms and waiting areas.",Transportation
+"The taxi driver was speeding and driving recklessly, compromising passenger safety.",Transportation
+The train ticketing system charged me twice for the same journey.,Transportation
+"The airline overbooked the flight, causing me to be denied boarding.",Transportation
+"The taxi driver refused to take me to my destination, citing a short trip.",Transportation
+The bus seats were uncomfortable and in poor condition.,Transportation
+"The train announcements were unclear, making it difficult to understand the next stop.",Transportation
+"I purchased an online ticket, but the QR code was not recognized by the ticket scanner.",Transportation
+"The airline misplaced my pet during the flight, causing distress and anxiety.",Transportation
+"The taxi meter was tampered with, resulting in an inflated fare.",Transportation
+"The bus driver skipped my designated stop, forcing me to walk a long distance.",Transportation
+"The train platform was overcrowded, and there were no proper crowd management measures.",Transportation
+The airline canceled my flight without any prior notification or alternative arrangements.,Transportation
+"The taxi driver took a longer route to increase the fare, even though I provided directions.",Transportation
+"The bus was dirty and poorly maintained, with broken seats and windows.",Transportation
+"The train was extremely overcrowded, with passengers struggling to find space.",Transportation
+I had difficulty finding a parking space at the airport due to insufficient availability.,Transportation
+The taxi driver was playing loud music and refused to lower the volume upon request.,Transportation
+"The bus driver was not following the designated route, causing confusion among passengers.",Transportation
+"The train ticket vending machine was out of order, causing inconvenience to passengers.",Transportation
+I experienced motion sickness due to poor driving skills of the taxi driver.,Transportation
+The airline changed my flight schedule without notifying me in advance.,Transportation
+"The bus was not wheelchair accessible, making it challenging for passengers with disabilities.",Transportation
+"The train doors were malfunctioning, posing a safety hazard during boarding and disembarking.",Transportation
+"The taxi driver was using a mobile phone while driving, endangering passengers' safety.",Transportation
+"The bus driver was constantly honking unnecessarily, causing disturbance and discomfort.",Transportation
+"The train was overcrowded, and there were no functioning air conditioning units.",Transportation
+I received no assistance with my heavy luggage from the airline staff.,Transportation
+"The taxi driver dropped me off at the wrong location, despite providing the correct address.",Transportation
+"The bus schedule was inaccurate, with buses arriving either too early or too late.",Transportation
+"The train station lacks proper lighting, posing safety concerns during evening hours.",Transportation
+"I was wrongly charged for excess baggage on the airline, even though I was within the allowed limit.",Transportation
+The taxi driver was driving aggressively and abruptly changing lanes without warning.,Transportation
+The software crashes frequently during data entry. It's affecting my productivity.,IT
+I haven't received my salary for the past two months. Can someone from HR please look into this?,HR
+"The network is slow, and I'm unable to access important files. Could the IT team check it?",IT
+I'm facing issues with my medical insurance coverage. Can HR assist me in resolving this matter?,HR
+"The printer in our department is constantly jamming, causing delays in our work. IT, please fix it urgently.",IT
+"I've been experiencing harassment from a colleague. HR, I need your help to address this problem.",HR
+"The system keeps logging me out repeatedly. IT, please investigate and resolve this issue.",IT
+"I have a concern regarding my vacation leave balance. HR, can you provide clarification?",HR
+"There's a problem with the email server. I can't send or receive emails. IT, please resolve it quickly.",IT
+"I believe there's an error in my tax deductions. HR, could you please review my payroll details?",HR
+"The new software update is causing compatibility issues with my computer. IT, can you assist in fixing it?",IT
+"HR, I haven't received any response to my promotion request. Can you please update me on the status?",HR
+"The internet connection in our office is unreliable. IT, please look into this matter as soon as possible.",IT
+"I need assistance with setting up my company email on my mobile device. IT, can you guide me through it?",IT
+"I'm facing difficulties accessing my employee benefits portal. HR, can you help me resolve this issue?",HR
+"IT, I accidentally deleted an important file. Is there any way to recover it?",IT
+"I have concerns about the working hours. HR, can we discuss possible adjustments?",HR
+"The video conferencing software is not functioning properly. IT, please fix it before our meeting.",IT
+"I have questions about the company's policy on parental leave. HR, can you provide me with the details?",HR
+"IT, the projector in the meeting room is not working. We need it for the presentation.",IT
+"I'm having trouble accessing my employee account. HR, can you assist me in resetting my password?",HR
+"The software is giving me error messages whenever I try to save my work. IT, please resolve this issue.",IT
+"HR, there's an error in my employment contract. Can you review it and make the necessary corrections?",HR
+"IT, I need a software license key to install a program on my computer. Can you provide it?",IT
+"I'm experiencing issues with my company-issued laptop. HR, can you arrange for a replacement?",HR
+"The server is down, and we are unable to access our files. IT, please fix it immediately.",IT
+"I have concerns about the work environment. HR, can we schedule a meeting to discuss it?",HR
+"IT, the wireless network is not available in certain areas of the office. Can you investigate the issue?",IT
+"I need help with updating my personal information in the HR system. HR, can you guide me through the process?",HR
+"The software is not compatible with my operating system. IT, can you recommend a solution?",IT
+"The HR department did not process my vacation request on time, causing inconvenience.",HR
+"IT, the email attachments are not opening correctly. Please resolve this issue promptly.",IT
+"There's a discrepancy in my performance evaluation. HR, can we schedule a meeting to discuss it?",HR
+I'm unable to access the HR portal to update my personal information. Can someone assist me with this?,HR
+The IT helpdesk has not responded to my support ticket for three days. Please prioritize it.,IT
+"I have concerns about the onboarding process. HR, can we improve the orientation program?",HR
+"IT, the software license on my computer has expired. Can you renew it?",IT
+"I'm facing difficulties with the time tracking system. HR, can you provide guidance on how to use it?",HR
+"The Wi-Fi network in our office is not secure. IT, please ensure that appropriate measures are taken.",IT
+I'm experiencing issues with the HR benefits enrollment process. Can someone assist me with this?,HR
+"IT, I need assistance in setting up a virtual private network (VPN) for secure remote access.",IT
+"There's a conflict within our team. HR, can you mediate and help resolve the issue?",HR
+"I'm receiving spam emails repeatedly. IT, please enhance the email filtering system.",IT
+The HR department has not provided me with the required training materials. Can this be addressed?,HR
+"IT, I accidentally deleted an important file from the shared drive. Can you recover it?",IT
+"I have concerns about the employee recognition program. HR, can we implement improvements?",HR
+"The IT system crashed during an important presentation, causing embarrassment. Please fix this issue.",IT
+I'm experiencing difficulties with the HR self-service portal. Can someone provide technical support?,HR
+"IT, the video conferencing software is not compatible with my device. Please suggest an alternative.",IT
+"There's an error in my salary calculation. HR, can you review it and rectify the mistake?",HR
+"I'm unable to print documents from my computer. IT, can you investigate and resolve the issue?",IT
+The HR department needs to streamline the employee appraisal process. Can improvements be made?,HR
+"IT, my computer is running slow, affecting my productivity. Can you optimize its performance?",IT
+"I have concerns about the diversity and inclusion initiatives. HR, can we discuss this further?",HR
+The IT team needs to provide more comprehensive cybersecurity training to employees.,IT
+I'm experiencing delays in receiving responses from the HR department. Can this be addressed?,HR
+"IT, the website is not loading properly. Please investigate and fix the issue.",IT
+"There's a lack of communication regarding policy updates. HR, can we improve internal notifications?",HR
+"I need assistance with data recovery from a damaged hard drive. IT, can you help me retrieve the files?",IT
+The HR department needs to address the employee morale issue. Can we conduct a survey?,HR
+The IT department has not resolved my software installation issue despite multiple requests.,IT
+"HR, there is a discrepancy in my employee benefits coverage. Can you please investigate and rectify it?",HR
+"I'm experiencing network connectivity problems in the conference room. IT, can you check and fix it?",IT
+"There's a conflict between me and my supervisor. HR, I need assistance in resolving this matter.",HR
+"IT, the server is experiencing frequent outages, disrupting our work. Please address the issue urgently.",IT
+"I have concerns about the transparency of the promotion process. HR, can we discuss this and provide clarity?",HR
+"IT, my computer is infected with a virus. Please perform a thorough scan and remove any malware.",IT
+"I'm having difficulties accessing my training materials on the learning management system. HR, can you help?",HR
+The IT helpdesk provided incorrect instructions for resolving my technical issue. Can someone correct it?,IT
+"I believe my performance review was biased and unfair. HR, can you conduct a thorough investigation?",HR
+"IT, I need assistance in recovering a deleted email from my inbox. Is it possible to retrieve it?",IT
+"There's a lack of communication regarding company policies. HR, can we improve the dissemination process?",HR
+"I'm experiencing frequent system crashes while using a specific software. IT, can you investigate and fix it?",IT
+The HR department has not responded to my leave application. Can you please expedite the approval process?,HR
+"IT, I accidentally formatted my external hard drive. Is there any way to recover the lost data?",IT
+"I have concerns about the effectiveness of our performance appraisal system. HR, can we explore improvements?",HR
+"The IT network in our office is not secure, leaving us vulnerable to cyber threats. Please address the issue.",IT
+I'm facing difficulties accessing the HR policy manual. Can you provide an updated version or alternative access?,HR
+"IT, the software update has caused compatibility issues with other applications. Can you find a solution?",IT
+"There's an error in my timesheet records. HR, can you rectify it to ensure accurate payroll processing?",HR
+"I'm unable to connect to the VPN for remote access. IT, can you troubleshoot and help me establish a connection?",IT
+The HR department needs to enhance communication channels for employee feedback. Can improvements be made?,HR
+"IT, the conference room audio system is malfunctioning, affecting our meetings. Please fix it as soon as possible.",IT
+"I have concerns about the accuracy of my expense reimbursements. HR, can we review and reconcile the records?",HR
+The IT team needs to improve response time for resolving technical issues. Urgent matters are being delayed.,IT
+"I'm experiencing delays in receiving my performance bonus. HR, can you check the status and provide an update?",HR
+"IT, the software license on my computer is about to expire. Can you renew it before it causes any disruptions?",IT
+"There's a lack of diversity in the company's hiring process. HR, can we implement more inclusive practices?",HR
+"I need assistance with data backup and recovery procedures. IT, can you provide guidance on best practices?",IT
+The HR department needs to address concerns related to work-life balance. Can we implement flexible policies?,HR
+"IT, the software application is crashing whenever I try to export data. Can you investigate and fix the issue?",IT
+"I have concerns about the transparency of the salary structure. HR, can we discuss and provide more clarity?",HR
+"The network printer in our department is constantly offline. IT, please resolve this issue as it hampers productivity.",IT
+I'm facing difficulties accessing my performance metrics on the HR portal. Can you provide assistance?,HR
+"IT, there's a persistent issue with the video conferencing system. It frequently disconnects during meetings.",IT
+"I've been subjected to workplace bullying by a colleague. HR, I need your immediate intervention to address this.",HR
+"The software license on my computer has expired. IT, can you provide a renewed license key?",IT
+I'm experiencing challenges with the HR onboarding process. Can you streamline and improve it?,HR
+"IT, my computer is infected with malware. Can you perform a thorough scan and remove the malicious files?",IT
+"I have concerns about the accuracy of my attendance records. HR, can we review and rectify any discrepancies?",HR
+The IT helpdesk is not responsive to my technical support requests. It's causing delays in my work.,IT
+"HR, I need clarification regarding the company's bereavement leave policy. Can you provide detailed information?",HR
+"The software is not compatible with my operating system. IT, can you recommend an alternative solution?",IT
+"I'm facing difficulties accessing my employee benefits portal. HR, can you provide guidance on resolving this?",HR
+"IT, there's a problem with the server configuration, leading to intermittent downtime. Please address it urgently.",IT
+"I believe there's an error in my performance appraisal rating. HR, can you review and amend it accordingly?",HR
+"The IT network in our office is not reliable. It frequently disconnects, disrupting our work.",IT
+"I'm unable to access the HR policy manual. HR, can you provide an updated copy or alternative access?",HR
+"IT, my laptop is overheating, which is affecting its performance. Can you provide a solution to prevent this?",IT
+The HR department needs to improve communication regarding employee development opportunities.,HR
+I'm experiencing delays in receiving responses to my HR inquiries. Can this be addressed promptly?,HR
+"IT, the software update has caused a loss of data on my computer. Is there any way to recover the lost files?",IT
+"There's a lack of clarity in the company's remote work policy. HR, can we discuss and provide clear guidelines?",HR
+"I'm unable to access my email account. IT, can you assist in resolving this issue?",IT
+The HR department needs to address concerns related to employee recognition and rewards programs.,HR
+"IT, the server response time is significantly slow, affecting our productivity. Please optimize its performance.",IT
+"I have concerns about the fairness of the promotion process. HR, can we ensure equal opportunities for all employees?",HR
+"The software interface is not user-friendly. IT, can you provide training or alternative software options?",IT
+I'm experiencing challenges with the HR grievance handling process. Can you provide guidance and support?,HR
+"IT, there's an issue with the backup system. It's not capturing the latest data. Please investigate and fix it.",IT
+The HR department needs to improve communication regarding policy updates and changes.,HR
+I'm facing difficulties with the IT asset management system. Can you provide assistance in tracking and managing assets?,IT
+"IT, the website is not loading properly in certain browsers. Can you investigate and resolve the compatibility issue?",IT
+"There's a lack of diversity in the company's leadership positions. HR, can we implement strategies for promoting diversity?",HR
+"I'm experiencing difficulties with the remote access VPN. IT, can you troubleshoot and help me establish a secure connection?",IT
+The HR department needs to address concerns related to employee morale and job satisfaction.,HR
+"IT, the software is not saving my preferences and settings. Can you investigate and fix the issue?",IT
+"I have concerns about the accuracy of my expense reimbursements. HR, can we review and rectify any discrepancies?",HR
+The IT network in our office is not secure. Can you implement additional security measures to protect sensitive data?,IT

app.py

@@ -0,0 +1,47 @@
+import streamlit as st
+import utils.user_utils as uu
+
+if 'HR_tickets' not in st.session_state:
+    st.session_state['HR_tickets'] =[]
+if 'IT_tickets' not in st.session_state:
+    st.session_state['IT_tickets'] =[]
+if 'Transport_tickets' not in st.session_state:
+    st.session_state['Transport_tickets'] =[]
+if 'PINECONE_API_KEY' not in st.session_state:
+    st.session_state['PINECONE_API_KEY'] = ''
+
+def main():
+    st.header("Automatic Ticket Classification Tool")
+    st.write("We are here to help you. Please ask a question")
+    user_input = st.text_input("🔎")
+
+    st.sidebar.title("😎🗝️")
+    st.session_state['PINECONE_API_KEY' ]= st.sidebar.text_input("What's your Pinecone API key?",type="password")
+
+    if user_input:
+        embedder = uu.initiate_embedder()
+
+        index = uu.pull_from_pinecone(st.session_state['PINECONE_API_KEY'], 'tickets', embedder)
+
+        similar_docs = uu.get_similar_docs(index, user_input)
+
+        response = uu.get_answer(similar_docs, user_input)
+        st.write(response)
+
+        button = st.button("Submit Ticket?")
+
+        if button:
+            embedded_query = embedder.embed_query(user_input)
+            department = uu.predict(embedded_query)
+            st.write("your ticket has been sumbitted to : " + department)
+            
+            if department == 'HR':
+                st.session_state['HR_tickets'].append(user_input)
+            elif department == 'IT':
+                st.session_state['IT_tickets'].append(user_input)
+            else:
+                st.session_state['Transport_tickets'].append(user_input)
+
+
+if __name__ == '__main__':
+    main()

pages/Pending_tickets.py

@@ -0,0 +1,25 @@
+import streamlit as st
+
+st.title("Department")
+
+tab_titles = ['HR Support', 'IT Support', 'Transportation Support']
+tabs = st.tabs(tab_titles)
+ 
+# Add content to each tab...
+with tabs[0]:
+    st.header('HR Support tickets')
+    for ticket in st.session_state['HR_tickets']:
+        st.write(str(st.session_state['HR_tickets'].index(ticket)+1)+" : "+ticket)
+    
+ 
+with tabs[1]:
+    st.header('IT Support tickets')
+    for ticket in st.session_state['IT_tickets']:
+        st.write(str(st.session_state['IT_tickets'].index(ticket)+1)+" : "+ticket)
+ 
+with tabs[2]:
+    st.header('Transportation Support tickets')
+    for ticket in st.session_state['Transport_tickets']:
+        st.write(str(st.session_state['Transport_tickets'].index(ticket)+1)+" : "+ticket)
+    
+ 

pages/create_ML_model.py

@@ -0,0 +1,83 @@
+import streamlit as st
+from sklearn.svm import SVC
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import StandardScaler
+import joblib
+
+import utils.admin_utils as au
+
+if 'cleaned_data' not in st.session_state:
+    st.session_state['cleaned_data'] =''
+if 'sentences_train' not in st.session_state:
+    st.session_state['sentences_train'] =''
+if 'sentences_test' not in st.session_state:
+    st.session_state['sentences_test'] =''
+if 'labels_train' not in st.session_state:
+    st.session_state['labels_train'] =''
+if 'labels_test' not in st.session_state:
+    st.session_state['labels_test'] =''
+if 'svm_classifier' not in st.session_state:
+    st.session_state['svm_classifier'] =''
+
+ 
+st.title("Let's build our Model...")
+ 
+# Create tabs
+tab_titles = ['Data Preprocessing', 'Model Training', 'Model Evaluation',"Save Model"]
+tabs = st.tabs(tab_titles)
+
+with tabs[0]:
+    st.header('Data Preprocessing')
+    st.write('Here we preprocess the data...')
+
+    data = st.file_uploader("Upload CSV file", type='csv')
+    button = st.button("Load data", key='data')
+
+    if button:
+        with st.spinner("uploading data..."):
+            df = au.read_data(data)
+            embedder = au.initiate_embedder()
+            st.session_state['cleaned_data'] = au.create_embedding(df, embedder)
+        st.success("Finished uploading and embedding csv")
+    
+with tabs[1]:
+    st.header("Model Training")
+    st.write("Here we train the model...")
+    button = st.button("Train Model", key='model')
+    if button:
+        with st.spinner("Training model..."):
+            st.session_state['sentences_train'], st.session_state['sentences_test'], st.session_state['labels_train'], st.session_state['labels_test'] = au.split_train_test_data(st.session_state['cleaned_data'])
+            st.session_state['svm_classifier'] = make_pipeline(StandardScaler(), SVC(class_weight='balanced')) 
+            st.session_state['svm_classifier'].fit(st.session_state['sentences_train'], st.session_state['labels_train'])
+        st.success('Finished Training model!')
+
+with tabs[2]:
+    st.header('Model Evaluation')
+    st.write('Here we evaluate the model...')
+    button = st.button("Evaluate model",key="Evaluation")
+
+    if button:
+        with st.spinner("Evaluating model..."):
+            acc_score = au.get_score(st.session_state['svm_classifier'], st.session_state['sentences_test'], st.session_state['labels_test'])
+            st.success(f"Validation accuracy: {100 * acc_score}%")
+            st.write("A sample run:")
+            text = "Rude driver with scary driving"
+            st.write("*** Our Issue ***: " + text)
+
+            embedder = au.initiate_embedder()
+            query_result = embedder.embed_query(text)
+
+            result = st.session_state['svm_classifier'].predict([query_result])
+            st.write("*** Department it belongs to ***: " + result[0])
+    
+        st.success("Finished")
+
+with tabs[3]:
+    st.header('Save model')
+    st.write('Here we save the model...')
+
+    button = st.button("Save model",key="save")
+    if button:
+        with st.spinner('Saving model...'):
+             joblib.dump(st.session_state['svm_classifier'], 'modelsvm.pk1')
+        st.success('Done!')

pages/load_data_store.py

@@ -0,0 +1,38 @@
+import streamlit as st
+import utils.admin_utils as au
+
+def main():
+
+    if 'PINECONE_API_KEY' not in st.session_state:
+        st.session_state['PINECONE_API_KEY'] = ''
+
+    st.set_page_config("Dump PDF to Pinecone - Vector Store")
+    st.title("Please upload your files...📁")
+    
+    st.sidebar.title("😎🗝️")
+    st.session_state['PINECONE_API_KEY' ]= st.sidebar.text_input("What's your Pinecone API key?",type="password")
+
+    pdf = st.file_uploader("Only PDF files allowed...", type=['pdf'])
+
+    if pdf and st.session_state['PINECONE_API_KEY']:
+        with st.spinner("Wait...."):
+            
+            text = au.read_pdf(pdf)
+            st.write("👉Reading PDF done")
+            chunks = au.split_data(text)
+            st.write("👉Splitting data into chunks done")
+            embedder = au.initiate_embedder()
+            st.write("👉Creating embeddings instance done")
+
+            au.push_to_pinecone(st.session_state['PINECONE_API_KEY'], 'tickets', embedder, chunks)
+        st.success("Successfully pushed the embeddings to Pinecone")
+    else:
+        if not st.session_state['PINECONE_API_KEY']:
+            st.error("Please provide pinecone API key")
+        else:
+            st.error("Please provide a PDF file")
+
+
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,12 @@
+langchain==0.1.4
+streamlit==1.29.0
+openai==1.10.0
+tiktoken==0.5.2
+python-dotenv==1.0.1
+pinecone-client==3.0.1
+pypdf==4.0.1
+joblib==1.3.2
+pandas==2.2.0
+scikit-learn==1.4.0
+sentence-transformers==2.3.0
+langchain-openai==0.0.5

utils/admin_utils.py

@@ -0,0 +1,58 @@
+from pypdf import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_openai import OpenAIEmbeddings
+from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
+from langchain_openai import OpenAI
+from pinecone import Pinecone
+from langchain_pinecone import PineconeVectorStore
+import pandas as pd
+from sklearn.model_selection import train_test_split
+
+##################### FUNCTIONS FOR UPLOADING DOCUMENT TO PINECONE #####################
+
+def read_pdf(pdf):
+    pdf_pages = PdfReader(pdf)
+    text = ''
+    for page in pdf_pages.pages:
+        text += page.extract_text()
+    return text
+
+def split_data(text):
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=50)
+    docs = text_splitter.split_text(text)
+    docs_chunks = text_splitter.create_documents(docs)
+    return docs_chunks
+
+def initiate_embedder():
+    embedder = SentenceTransformerEmbeddings(model_name='all-MiniLM-L6-v2')
+    return embedder
+
+def push_to_pinecone(pinecone_apikey,pinecone_index_name,embedder,docs):
+    Pinecone(api_key=pinecone_apikey)
+    index = PineconeVectorStore.from_documents(docs, embedder,index_name = pinecone_index_name)
+    return index
+
+##################### FUNCTIONS FOR MODEL PREPROCESSING/ TRAINING #####################
+
+def read_data(data):
+    df = pd.read_csv(data, delimiter=',', header=None)
+    return df
+
+def create_embedding(df, embedder):
+    df[2] = df[0].apply(lambda x: embedder.embed_query(x))
+    return df
+
+def split_train_test_data(df_sample):
+    x_train, x_test, y_train, y_test = train_test_split(
+                                                        list(df_sample[2]), 
+                                                        list(df_sample[1]),
+                                                            test_size=0.25, 
+                                                            random_state=42
+                                                        )
+    print(len(x_train))
+    return x_train, x_test, y_train, y_test
+
+def get_score(svm_classifier, x_test, y_test):
+    score = svm_classifier.score(x_test, y_test)
+    return score
+    

utils/constants.py

@@ -0,0 +1 @@
+MODEL = 'modelsvm.pk1'

utils/user_utils.py

@@ -0,0 +1,33 @@
+from pinecone import Pinecone
+from langchain_pinecone import PineconeVectorStore
+from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
+from langchain_openai import OpenAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain_community.callbacks import get_openai_callback
+import joblib
+from utils.constants import *
+
+def initiate_embedder():
+    embedder = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    return embedder
+
+def pull_from_pinecone(pinecone_apikey,pinecone_index_name,embeddings):
+    Pinecone(api_key=pinecone_apikey)
+
+    index = PineconeVectorStore.from_existing_index(pinecone_index_name, embeddings)
+    return index
+
+def get_similar_docs(index, query, k=2):
+    similar_docs = index.similarity_search(query,k)
+    return similar_docs
+
+def get_answer(docs, query):
+    chain = load_qa_chain(OpenAI(), chain_type="stuff")
+    with get_openai_callback() as cb:
+        response = chain.run(input_documents=docs, question=query)
+    return response
+
+def predict(query):
+    model = joblib.load(MODEL)
+    result = model.predict([query])
+    return result[0]