vector store works on local

.gitignore

@@ -0,0 +1,3 @@
+.venv
+.env
+__pycache__

Makefile.venv

@@ -0,0 +1,272 @@
+#
+# SEAMLESSLY MANAGE PYTHON VIRTUAL ENVIRONMENT WITH A MAKEFILE
+#
+# https://github.com/sio/Makefile.venv             v2023.04.17
+#
+#
+# Insert `include Makefile.venv` at the bottom of your Makefile to enable these
+# rules.
+#
+# When writing your Makefile use '$(VENV)/python' to refer to the Python
+# interpreter within virtual environment and '$(VENV)/executablename' for any
+# other executable in venv.
+#
+# This Makefile provides the following targets:
+#   venv
+#       Use this as a dependency for any target that requires virtual
+#       environment to be created and configured
+#   python, ipython
+#       Use these to launch interactive Python shell within virtual environment
+#   shell, bash, zsh
+#       Launch interactive command line shell. "shell" target launches the
+#       default shell Makefile executes its rules in (usually /bin/sh).
+#       "bash" and "zsh" can be used to refer to the specific desired shell.
+#   show-venv
+#       Show versions of Python and pip, and the path to the virtual environment
+#   clean-venv
+#       Remove virtual environment
+#   $(VENV)/executable_name
+#       Install `executable_name` with pip. Only packages with names matching
+#       the name of the corresponding executable are supported.
+#       Use this as a lightweight mechanism for development dependencies
+#       tracking. E.g. for one-off tools that are not required in every
+#       developer's environment, therefore are not included into
+#       requirements.txt or setup.py.
+#       Note:
+#           Rules using such target or dependency MUST be defined below
+#           `include` directive to make use of correct $(VENV) value.
+#       Example:
+#           codestyle: $(VENV)/pyflakes
+#               $(VENV)/pyflakes .
+#       See `ipython` target below for another example.
+#
+# This Makefile can be configured via following variables:
+#   PY
+#       Command name for system Python interpreter. It is used only initially to
+#       create the virtual environment
+#       Default: python3
+#   REQUIREMENTS_TXT
+#       Space separated list of paths to requirements.txt files.
+#       Paths are resolved relative to current working directory.
+#       Default: requirements.txt
+#
+#       Non-existent files are treated as hard dependencies,
+#       recipes for creating such files must be provided by the main Makefile.
+#       Providing empty value (REQUIREMENTS_TXT=) turns off processing of
+#       requirements.txt even when the file exists.
+#   SETUP_PY, SETUP_CFG, PYPROJECT_TOML, VENV_LOCAL_PACKAGE
+#       Space separated list of paths to files that contain build instructions
+#       for local Python packages. Corresponding packages will be installed
+#       into venv in editable mode along with all their dependencies.
+#       Default: setup.py setup.cfg pyproject.toml (whichever present)
+#
+#       Non-existent and empty values are treated in the same way as for REQUIREMENTS_TXT.
+#   WORKDIR
+#       Parent directory for the virtual environment.
+#       Default: current working directory.
+#   VENVDIR
+#       Python virtual environment directory.
+#       Default: $(WORKDIR)/.venv
+#
+# This Makefile was written for GNU Make and may not work with other make
+# implementations.
+#
+#
+# Copyright (c) 2019-2023 Vitaly Potyarkin
+#
+# Licensed under the Apache License, Version 2.0
+#    <http://www.apache.org/licenses/LICENSE-2.0>
+#
+
+
+#
+# Configuration variables
+#
+
+WORKDIR?=.
+VENVDIR?=$(WORKDIR)/.venv
+REQUIREMENTS_TXT?=$(wildcard requirements.txt)  # Multiple paths are supported (space separated)
+SETUP_PY?=$(wildcard setup.py)                  # Multiple paths are supported (space separated)
+SETUP_CFG?=$(foreach s,$(SETUP_PY),$(wildcard $(patsubst %setup.py,%setup.cfg,$(s))))
+PYPROJECT_TOML?=$(wildcard pyproject.toml)
+VENV_LOCAL_PACKAGE?=$(SETUP_PY) $(SETUP_CFG) $(PYPROJECT_TOML)
+MARKER=.initialized-with-Makefile.venv
+
+
+#
+# Python interpreter detection
+#
+
+_PY_AUTODETECT_MSG=Detected Python interpreter: $(PY). Use PY environment variable to override
+
+ifeq (ok,$(shell test -e /dev/null 2>&1 && echo ok))
+NULL_STDERR=2>/dev/null
+else
+NULL_STDERR=2>NUL
+endif
+
+ifndef PY
+_PY_OPTION:=python3
+ifeq (ok,$(shell $(_PY_OPTION) -c "print('ok')" $(NULL_STDERR)))
+PY=$(_PY_OPTION)
+endif
+endif
+
+ifndef PY
+_PY_OPTION:=$(VENVDIR)/bin/python
+ifeq (ok,$(shell $(_PY_OPTION) -c "print('ok')" $(NULL_STDERR)))
+PY=$(_PY_OPTION)
+$(info $(_PY_AUTODETECT_MSG))
+endif
+endif
+
+ifndef PY
+_PY_OPTION:=$(subst /,\,$(VENVDIR)/Scripts/python)
+ifeq (ok,$(shell $(_PY_OPTION) -c "print('ok')" $(NULL_STDERR)))
+PY=$(_PY_OPTION)
+$(info $(_PY_AUTODETECT_MSG))
+endif
+endif
+
+ifndef PY
+_PY_OPTION:=py -3
+ifeq (ok,$(shell $(_PY_OPTION) -c "print('ok')" $(NULL_STDERR)))
+PY=$(_PY_OPTION)
+$(info $(_PY_AUTODETECT_MSG))
+endif
+endif
+
+ifndef PY
+_PY_OPTION:=python
+ifeq (ok,$(shell $(_PY_OPTION) -c "print('ok')" $(NULL_STDERR)))
+PY=$(_PY_OPTION)
+$(info $(_PY_AUTODETECT_MSG))
+endif
+endif
+
+ifndef PY
+define _PY_AUTODETECT_ERR
+Could not detect Python interpreter automatically.
+Please specify path to interpreter via PY environment variable.
+endef
+$(error $(_PY_AUTODETECT_ERR))
+endif
+
+
+#
+# Internal variable resolution
+#
+
+VENV=$(VENVDIR)/bin
+EXE=
+# Detect windows
+ifeq (win32,$(shell $(PY) -c "import __future__, sys; print(sys.platform)"))
+VENV=$(VENVDIR)/Scripts
+EXE=.exe
+endif
+
+touch=touch $(1)
+ifeq (,$(shell command -v touch $(NULL_STDERR)))
+# https://ss64.com/nt/touch.html
+touch=type nul >> $(subst /,\,$(1)) && copy /y /b $(subst /,\,$(1))+,, $(subst /,\,$(1))
+endif
+
+RM?=rm -f
+ifeq (,$(shell command -v $(firstword $(RM)) $(NULL_STDERR)))
+RMDIR:=rd /s /q
+else
+RMDIR:=$(RM) -r
+endif
+
+
+#
+# Virtual environment
+#
+
+.PHONY: venv
+venv: $(VENV)/$(MARKER)
+
+.PHONY: clean-venv
+clean-venv:
+	-$(RMDIR) "$(VENVDIR)"
+
+.PHONY: show-venv
+show-venv: venv
+	@$(VENV)/python -c "import sys; print('Python ' + sys.version.replace('\n',''))"
+	@$(VENV)/pip --version
+	@echo venv: $(VENVDIR)
+
+.PHONY: debug-venv
+debug-venv:
+	@echo "PATH (Shell)=$$PATH"
+	@$(MAKE) --version
+	$(info PATH (GNU Make)="$(PATH)")
+	$(info SHELL="$(SHELL)")
+	$(info PY="$(PY)")
+	$(info REQUIREMENTS_TXT="$(REQUIREMENTS_TXT)")
+	$(info VENV_LOCAL_PACKAGE="$(VENV_LOCAL_PACKAGE)")
+	$(info VENVDIR="$(VENVDIR)")
+	$(info VENVDEPENDS="$(VENVDEPENDS)")
+	$(info WORKDIR="$(WORKDIR)")
+
+
+#
+# Dependencies
+#
+
+ifneq ($(strip $(REQUIREMENTS_TXT)),)
+VENVDEPENDS+=$(REQUIREMENTS_TXT)
+endif
+
+ifneq ($(strip $(VENV_LOCAL_PACKAGE)),)
+VENVDEPENDS+=$(VENV_LOCAL_PACKAGE)
+endif
+
+$(VENV):
+	$(PY) -m venv $(VENVDIR)
+	$(VENV)/python -m pip install --upgrade pip setuptools wheel
+
+$(VENV)/$(MARKER): $(VENVDEPENDS) | $(VENV)
+ifneq ($(strip $(REQUIREMENTS_TXT)),)
+	$(VENV)/pip install $(foreach path,$(REQUIREMENTS_TXT),-r $(path))
+endif
+ifneq ($(strip $(VENV_LOCAL_PACKAGE)),)
+	$(VENV)/pip install $(foreach path,$(sort $(VENV_LOCAL_PACKAGE)),-e $(dir $(path)))
+endif
+	$(call touch,$(VENV)/$(MARKER))
+
+
+#
+# Interactive shells
+#
+
+.PHONY: python
+python: venv
+	exec $(VENV)/python
+
+.PHONY: ipython
+ipython: $(VENV)/ipython
+	exec $(VENV)/ipython
+
+.PHONY: shell
+shell: venv
+	. $(VENV)/activate && exec $(notdir $(SHELL))
+
+.PHONY: bash zsh
+bash zsh: venv
+	. $(VENV)/activate && exec $@
+
+
+#
+# Commandline tools (wildcard rule, executable name must match package name)
+#
+
+ifneq ($(EXE),)
+$(VENV)/%: $(VENV)/%$(EXE) ;
+.PHONY:    $(VENV)/%
+.PRECIOUS: $(VENV)/%$(EXE)
+endif
+
+$(VENV)/%$(EXE): $(VENV)/$(MARKER)
+	$(VENV)/pip install --upgrade $*
+	$(call touch,$@)

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 +1,67 @@
+from dotenv import load_dotenv
+import streamlit as st
+from user_utils import *
+
+#Creating session variables
+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'] =[]
+
+load_dotenv()
+
+def main():
+    
+
+    st.header("Automatic Ticket Classification Tool")
+    #Capture user input
+    st.write("We are here to help you, please ask your question:")
+    user_input = st.text_input("🔍")
+
+    if user_input:
+
+        #creating embeddings instance
+        embeddings=create_embeddings()
+
+        #Function to pull index data from Pinecone
+        index=pull_from_pinecone(embeddings)
+        
+        #This function will help us in fetching the top relevent documents from our vector store - Pinecone Index
+        relavant_docs=get_similar_docs(index,user_input)
+
+        #This will return the fine tuned response by LLM
+        response=get_answer(relavant_docs,user_input)
+        st.write(response)
+
+        
+        #Button to create a ticket with respective department
+        button = st.button("Submit ticket?")
+
+        if button:
+            #Get Response
+            
+
+            embeddings = create_embeddings()
+            query_result = embeddings.embed_query(user_input)
+
+            #loading the ML model, so that we can use it to predit the class to which this compliant belongs to...
+            department_value = predict(query_result)
+            st.write("your ticket has been sumbitted to : "+department_value)
+
+            #Appending the tickets to below list, so that we can view/use them later on...
+            if department_value=="HR":
+                st.session_state['HR_tickets'].append(user_input)
+            elif department_value=="IT":
+                st.session_state['IT_tickets'].append(user_input)
+            else:
+                st.session_state['Transport_tickets'].append(user_input)
+
+
+
+if __name__ == '__main__':
+    main()
+
+
+

makefile

@@ -0,0 +1,14 @@
+
+
+PYTHON_BINARY = $(VENV)/python
+STREAMLIT_BINARY = $(VENV)/streamlit
+
+
+re-venv: clean-venv venv
+
+run: venv
+	$(PYTHON_BINARY) app.py
+	$(STREAMLIT_BINARY) run app.py
+
+
+include Makefile.venv

pages/Create_ML_Model.py

@@ -0,0 +1,110 @@
+import streamlit as st
+from pages.admin_utils import *
+from sklearn.svm import SVC
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import StandardScaler
+import joblib
+
+from pages.admin_utils import *
+
+
+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)
+
+# Adding content to each tab
+
+#Data Preprocessing TAB
+with tabs[0]:
+    st.header('Data Preprocessing')
+    st.write('Here we preprocess the data...')
+
+    # Capture the CSV file
+    data = st.file_uploader("Upload CSV file",type="csv")
+
+    button = st.button("Load data",key="data")
+
+    if button:
+        with st.spinner('Wait for it...'):
+            our_data=read_data(data)
+            embeddings=get_embeddings()
+            st.session_state['cleaned_data'] = create_embeddings(our_data,embeddings)
+        st.success('Done!')
+
+
+#Model Training TAB
+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('Wait for it...'):
+                st.session_state['sentences_train'], st.session_state['sentences_test'], st.session_state['labels_train'], st.session_state['labels_test']=split_train_test__data(st.session_state['cleaned_data'])
+                
+                # Initialize a support vector machine, with class_weight='balanced' because 
+                # our training set has roughly an equal amount of positive and negative 
+                # sentiment sentences
+                st.session_state['svm_classifier']  = make_pipeline(StandardScaler(), SVC(class_weight='balanced')) 
+
+                # fit the support vector machine
+                st.session_state['svm_classifier'].fit(st.session_state['sentences_train'], st.session_state['labels_train'])
+            st.success('Done!')
+
+#Model Evaluation TAB
+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('Wait for it...'):
+            accuracy_score=get_score(st.session_state['svm_classifier'],st.session_state['sentences_test'],st.session_state['labels_test'])
+            st.success(f"Validation accuracy is {100*accuracy_score}%!")
+
+
+            st.write("A sample run:")
+
+
+            #text="lack of communication regarding policy updates salary, can we please look into it?"
+            text="Rude driver with scary driving"
+            st.write("***Our issue*** : "+text)
+
+            #Converting out TEXT to NUMERICAL representaion
+            embeddings= get_embeddings()
+            query_result = embeddings.embed_query(text)
+
+            #Sample prediction using our trained model
+            result= st.session_state['svm_classifier'].predict([query_result])
+            st.write("***Department it belongs to*** : "+result[0])
+            
+
+        st.success('Done!')
+
+#Save model TAB
+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('Wait for it...'):
+             joblib.dump(st.session_state['svm_classifier'], 'modelsvm.pk1')
+        st.success('Done!')

pages/Load_Data_Store.py

@@ -0,0 +1,36 @@
+import streamlit as st
+from dotenv import load_dotenv
+from pages.admin_utils import *
+
+
+def main():
+    load_dotenv()
+    st.set_page_config(page_title="Dump PDF to Pinecone - Vector Store")
+    st.title("Please upload your files...📁 ")
+
+    # Upload the pdf file
+    pdf = st.file_uploader("Only PDF files allowed", type=["pdf"])
+
+    # Extract the whole text from the uploaded pdf file
+    if pdf is not None:
+        with st.spinner('Wait for it...'):
+            text=read_pdf_data(pdf)
+            st.write("👉Reading PDF done")
+
+            # Create chunks
+            docs_chunks=split_data(text)
+            #st.write(docs_chunks)
+            st.write("👉Splitting data into chunks done")
+
+            # Create the embeddings
+            embeddings=create_embeddings_load_data()
+            st.write("👉Creating embeddings instance done")
+
+            # Build the vector store (Push the PDF data embeddings)
+            push_to_pinecone(embeddings,docs_chunks)
+
+        st.success("Successfully pushed the embeddings to Pinecone")
+
+
+if __name__ == '__main__':
+    main()

pages/Pending_tickets.py

@@ -0,0 +1,26 @@
+import streamlit as st
+ 
+st.title('Departments')
+ 
+# Create tabs
+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/admin_utils.py

@@ -0,0 +1,88 @@
+import os
+
+import pandas as pd
+import pinecone
+from dotenv import load_dotenv
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.embeddings.sentence_transformer import \
+    SentenceTransformerEmbeddings
+from langchain.llms import OpenAI
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Pinecone
+from pypdf import PdfReader
+from sklearn.model_selection import train_test_split
+from functools import lru_cache
+
+
+#**********Functions to help you load documents to PINECONE***********
+
+#Read PDF data
+def read_pdf_data(pdf_file):
+    pdf_page = PdfReader(pdf_file)
+    text = ""
+    for page in pdf_page.pages:
+        text += page.extract_text()
+    return text
+
+#Split data into chunks
+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
+
+#Create embeddings instance
+def create_embeddings_load_data():
+    #embeddings = OpenAIEmbeddings()
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    return embeddings
+
+
+@lru_cache
+def pine_cone_index(pinecone_index_name: str | None):
+    load_dotenv()
+    pinecone.init(
+    api_key=os.getenv('PINECONE_API_KEY'),
+    environment=os.getenv('PINECONE_ENV'),
+    )
+
+    index_name = pinecone_index_name or os.getenv('PINECONE_INDEX_NAME')
+    if index_name is None:
+        raise ValueError('PINECONE_INDEX_NAME is not set')
+    return index_name
+
+
+def push_to_pinecone(embeddings,docs,pinecone_index_name: str | None=None):
+    index_name = pine_cone_index(pinecone_index_name)
+    index = Pinecone.from_documents(docs, embeddings, index_name=index_name)
+    return index
+
+#*********Functions for dealing with Model related tasks...************
+
+#Read dataset for model creation
+def read_data(data):
+    df = pd.read_csv(data,delimiter=',', header=None)  
+    return df
+
+#Create embeddings instance
+def get_embeddings():
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    return embeddings
+
+#Generating embeddings for our input dataset
+def create_embeddings(df,embeddings):
+    df[2] = df[0].apply(lambda x: embeddings.embed_query(x))
+    return df
+
+#Splitting the data into train & test
+def split_train_test__data(df_sample):
+    # Split into training and testing sets
+    sentences_train, sentences_test, labels_train, labels_test = train_test_split(
+    list(df_sample[2]), list(df_sample[1]), test_size=0.25, random_state=0)
+    print(len(sentences_train))
+    return sentences_train, sentences_test, labels_train, labels_test
+
+#Get the accuracy score on test data
+def get_score(svm_classifier,sentences_test,labels_test):
+    score = svm_classifier.score(sentences_test, labels_test)
+    return score

requirements.txt

@@ -0,0 +1,13 @@
+langchain
+openai
+Streamlit
+huggingface_hub
+python-dotenv
+watchdog
+tiktoken
+pinecone-client
+pypdf
+joblib
+pandas
+scikit-learn
+sentence_transformers

user_utils.py

@@ -0,0 +1,43 @@
+import os
+
+import joblib
+from langchain.callbacks import get_openai_callback
+from langchain.chains.question_answering import load_qa_chain
+from langchain.embeddings.sentence_transformer import \
+    SentenceTransformerEmbeddings
+from langchain.llms import OpenAI
+from langchain.vectorstores import Pinecone
+
+from pages.admin_utils import pine_cone_index
+
+
+#Function to pull index data from Pinecone
+def pull_from_pinecone(embeddings,pinecone_index_name: str | None=None):
+    index_name = pine_cone_index(pinecone_index_name)
+
+    index = Pinecone.from_existing_index(index_name, embeddings)
+    return index
+
+def create_embeddings():
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    return embeddings
+
+#This function will help us in fetching the top relevent documents from our vector store - Pinecone Index
+def get_similar_docs(index,query,k=2):
+
+    similar_docs = index.similarity_search(query, k=k)
+    return similar_docs
+
+def get_answer(docs,user_input):
+    chain = load_qa_chain(OpenAI(), chain_type="stuff")
+    with get_openai_callback() as cb:
+        response = chain.run(input_documents=docs, question=user_input)
+    return response
+
+
+def predict(query_result):
+    if os.path.exists('modelsvm.pk1'):
+        Fitmodel = joblib.load('modelsvm.pk1')
+        result=Fitmodel.predict([query_result])
+        return result[0]
+    return "No Idea?"