Upload 9 files

.gitignore

@@ -0,0 +1,161 @@
+# Byte-compiled / optimized / DLL files
+cacert.pem
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

Home.py

@@ -0,0 +1,68 @@
+import streamlit as st
+from dotenv import load_dotenv
+from utils import *
+
+# #********SIDE BAR*******
+# with st.sidebar:
+#      st.sidebar.title("🗝️")
+
+
+#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'] =[]
+
+
+def main():
+    load_dotenv()
+    st.set_page_config(page_title="Ticket Tool", page_icon='🎫')
+
+    st.header("Automatic Ticket Classification Tool")
+    st.write("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("automatic-ticket-tool",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- load_qa_chain
+        response=get_answer(relavant_docs,user_input)
+        st.write(response)
+
+
+        #Button to create a ticket with respective department
+        button = st.button("Do you want to 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()
+
+
+

Pipfile

@@ -0,0 +1,24 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+openai = "*"
+langchain = "*"
+streamlit = "*"
+python-dotenv = "*"
+langchain-community = "*"
+langchain-openai = "*"
+sentence-transformers = "*"
+tiktoken = "*"
+pinecone-client = "*"
+pandas = "*"
+pypdf = "*"
+joblib = "*"
+scikit-learn = "*"
+
+[dev-packages]
+
+[requires]
+python_version = "3.10"

requirements.txt

@@ -0,0 +1,12 @@
+openai
+langchain
+streamlit
+langchain-community
+sentence-transformers
+tiktoken
+python-dotenv
+pinecone-client
+pypdf
+joblib
+pandas
+scikit-learn

utils.py

@@ -0,0 +1,117 @@
+from pypdf import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
+from langchain.llms import OpenAI
+# import pinecone
+from langchain.vectorstores import Pinecone as pc
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from langchain.chains.question_answering import load_qa_chain
+from langchain.callbacks import get_openai_callback
+import joblib
+import os
+# since there have been changes import Pinecone directly from Pinecone and alias above as pc from lc
+from pinecone import Pinecone
+
+
+pinecone_api_key=os.environ["PINECONE_API_KEY"]
+
+
+#**********Functions to load data 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():
+    #embeddings = OpenAIEmbeddings()
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    return embeddings
+
+#Function to push data to Pinecone
+def push_to_pinecone(pinecone_index_name, embeddings, docs):
+    # pineone.init below is no longer supported
+    # pinecone.init(
+    # api_key=pinecone_api_key,
+    # environment=pinecone_environment
+    # )
+    Pinecone(api_key=pinecone_api_key)
+    index_name = pinecone_index_name
+    index = pc.from_documents(docs, embeddings, index_name=index_name)
+    return index
+
+
+
+
+#*********Functions for Model related tasks************
+#Read dataset for model creation - retrun a df
+def read_data(data):
+    df = pd.read_csv(data,delimiter=',', header=None)
+    return df
+
+#Create embeddings instance - fxn above
+#Generating embeddings for our input dataset
+def create_dataset_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
+
+
+
+#*******UTILs FOR USERS****************
+#Function to pull index data from Pinecone...
+def pull_from_pinecone(pinecone_index_name,embeddings):
+    # pinecone.init(
+    # api_key=pinecone_apikey,
+    # environment=pinecone_environment
+    # )
+    Pinecone(api_key=pinecone_api_key)
+    index_name = pinecone_index_name
+    index = pc.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):
+    # load from the model we created
+    Fitmodel = joblib.load('modelsvm.pk1')
+    result=Fitmodel.predict([query_result])
+    return result[0]