Uploaded

Chatbot.py

@@ -0,0 +1,33 @@
+import streamlit as st
+from dotenv import load_dotenv
+load_dotenv()
+import os
+import google.generativeai as genai
+
+os.getenv("GOOGLE_API_KEY")
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+def show():    
+    st.header("Chatbot")
+    model=genai.GenerativeModel('gemini-1.0-pro-latest')
+    chat=model.start_chat(history=[])
+    if 'chat_history' not in st.session_state:
+        st.session_state['chat_history'] = []
+    input=st.text_input("Input Prompt: ",key="input")
+
+    submit=st.button("Submit")
+
+    if submit and input:
+        
+        
+        response=chat.send_message(input,stream=True)
+        st.session_state['chat_history'].append(("You", input))
+        st.subheader("The Response is")
+        for chunk in response:
+            st.write(chunk.text)
+            st.session_state['chat_history'].append(("Bot", chunk.text))
+        
+
+    st.subheader("The Chat History is")
+    
+    for role, text in st.session_state['chat_history']:
+        st.write(f"{role}: {text}")

Image_QA_Gemini.py

@@ -0,0 +1,30 @@
+import streamlit as st
+from dotenv import load_dotenv
+load_dotenv()
+import os
+from PIL import Image
+import google.generativeai as genai
+
+os.getenv("GOOGLE_API_KEY")
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+def show():    
+    st.header("Image QA")
+    input=st.text_input("Input Prompt: ",key="input")
+    file=st.file_uploader("Chose an image...",type=["jpg","jpeg","png"])
+    image=""
+    if file is not None:
+        image=Image.open(file)
+        st.image(image)
+
+    submit=st.button("Submit")
+
+    if submit:
+        model=genai.GenerativeModel('gemini-pro-vision')
+        st.subheader("The Response is")
+        if input!="":
+            response=model.generate_content([input,image])
+            st.write(response.text)
+
+        else:
+            response=model.generate_content(image)
+            st.write(response.text)

MCQ_Gen.py

@@ -0,0 +1,156 @@
+from fpdf import FPDF
+class PDF(FPDF):
+    def header(self):
+        self.set_font('Arial', 'B', 12)
+        self.cell(0, 10, 'MCQ Quiz', 0, 1, 'C')
+
+    def chapter_title(self, num, label):
+        self.set_font('Arial', '', 12)
+        self.cell(0, 10, 'Question %d: %s' % (num, label), 0, 1, 'L')
+        self.ln(5)
+
+    def chapter_body(self, body):
+        self.set_font('Arial', '', 12)
+        self.multi_cell(0, 10, body)
+        self.ln()
+
+    def add_question(self, num, question, options):
+        self.chapter_title(num, question)
+        for key, option in options.items():
+            self.chapter_body(f"{key}. {option}")
+        self.ln()
+
+    def add_answers_section(self, answers):
+        self.add_page()
+        self.set_font('Arial', 'B', 12)
+        self.cell(0, 10, 'Answers', 0, 1, 'C')
+        self.ln(10)
+        self.set_font('Arial', '', 12)
+        for num, answer in answers.items():
+            self.cell(0, 10, f"Question {num}: {answer}", 0, 1, 'L')
+
+
+
+import streamlit as st
+from dotenv import load_dotenv
+load_dotenv()
+import os
+import json
+import base64
+from langchain_google_genai import ChatGoogleGenerativeAI
+os.getenv("GOOGLE_API_KEY")
+RESPONSE_JSON = {
+    "1": {
+        "mcq": "multiple choice question",
+        "options": {
+            "a": "choice here",
+            "b": "choice here",
+            "c": "choice here",
+            "d": "choice here",
+        },
+        "correct": "correct answer",
+    },
+    "2": {
+        "mcq": "multiple choice question",
+        "options": {
+            "a": "choice here",
+            "b": "choice here",
+            "c": "choice here",
+            "d": "choice here",
+        },
+        "correct": "correct answer",
+    },
+    "3": {
+        "mcq": "multiple choice question",
+        "options": {
+            "a": "choice here",
+            "b": "choice here",
+            "c": "choice here",
+            "d": "choice here",
+        },
+        "correct": "correct answer",
+    },
+}
+TEMPLATE="""
+Text:{text}
+You are an expert MCQ maker. Given the above text, it is your job to \
+create a quiz  of {number} multiple choice questions for {subject} students in {tone} tone. 
+Make sure the questions are not repeated and check all the questions to be conforming the text as well.
+Make sure to format your response like  RESPONSE_JSON below  and use it as a guide. \
+Ensure to make {number} MCQs
+### RESPONSE_JSON
+{response_json}
+
+"""
+
+TEMPLATE2="""
+You are an expert english grammarian and writer. Given a Multiple Choice Quiz for {subject} students.\
+You need to evaluate the complexity of the question and give a complete analysis of the quiz. Only use at max 50 words for complexity analysis. 
+if the quiz is not at per with the cognitive and analytical abilities of the students,\
+update the quiz questions which needs to be changed and change the tone such that it perfectly fits the student abilities
+Quiz_MCQs:
+{quiz}
+
+Check from an expert English Writer of the above quiz:
+"""
+def show():    
+    st.header("MCQ_Generator")
+    TEXT=st.text_input("Input Prompt: ",key="input1")
+    NUMBER=st.text_input("Number of MCQs ",key="input2")
+    SUBJECT=st.text_input("Topic of MCQs ",key="input3")
+    TONE=st.text_input("Difficulty Level ",key="input4")
+
+    submit=st.button("Submit")
+
+    if submit and TEXT:
+        llm = ChatGoogleGenerativeAI(model="gemini-pro",temperature=0.9)
+        from langchain.prompts import PromptTemplate
+        from langchain.chains import LLMChain
+        from langchain.chains import SequentialChain
+        quiz_generation_prompt = PromptTemplate(
+            input_variables=["text", "number", "subject", "tone", "response_json"],
+            template=TEMPLATE
+        )
+        quiz_chain=LLMChain(llm=llm, prompt=quiz_generation_prompt, output_key="quiz", verbose=True)
+        quiz_evaluation_prompt=PromptTemplate(input_variables=["subject", "quiz"], template=TEMPLATE)
+        review_chain=LLMChain(llm=llm, prompt=quiz_evaluation_prompt, output_key="review", verbose=True)
+        generate_evaluate_chain=SequentialChain(chains=[quiz_chain, review_chain], input_variables=["text", "number", "subject", "tone", "response_json"],
+                                        output_variables=["quiz", "review"], verbose=True,)
+        response=generate_evaluate_chain(
+            {
+                "text": TEXT,
+                "number": NUMBER,
+                "subject":SUBJECT,
+                "tone": TONE,
+                "response_json": json.dumps(RESPONSE_JSON)
+            }
+        )
+        quiz=response.get("quiz")
+        if '### RESPONSE_JSON\n' in quiz:
+            quiz = quiz.split('### RESPONSE_JSON\n')[1]
+            quiz = json.loads(quiz)
+        else:
+            quiz=json.loads(quiz)
+        pdf = PDF()
+        pdf.add_page()
+        pdf.set_title(SUBJECT+" Quiz")
+        answers = {}
+        for key, value in quiz.items():
+            question_num = int(key)
+            pdf.add_question(question_num, value["mcq"], value["options"])
+            answers[question_num] = value["correct"]
+        pdf.add_answers_section(answers)
+
+        pdf_file_path =SUBJECT+"_mcq.pdf"
+        pdf.output(pdf_file_path)
+        
+        with open(pdf_file_path, "rb") as pdf_file:
+            st.download_button(
+                label="Download "+SUBJECT+" Quiz PDF",
+                data=pdf_file,
+                file_name=SUBJECT+"_quiz.pdf",
+                mime="application/pdf",
+            )
+
+        pdf_display = f'<iframe src="data:application/pdf;base64,{base64.b64encode(open(pdf_file_path, "rb").read()).decode()}" width="700" height="1000" type="application/pdf"></iframe>'
+        st.markdown(pdf_display, unsafe_allow_html=True)

QA_Gemini.py

@@ -0,0 +1,23 @@
+import streamlit as st
+from dotenv import load_dotenv
+load_dotenv()
+import os
+import google.generativeai as genai
+
+os.getenv("GOOGLE_API_KEY")
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+def show():    
+    st.header("QA Gemeni")
+    input=st.text_input("Input Prompt: ",key="input")
+
+    submit=st.button("Submit")
+
+    if submit:
+        model=genai.GenerativeModel('gemini-1.0-pro-latest')
+        st.subheader("The Response is")
+        if input!="":
+            response=model.generate_content(input)
+            st.write(response.text)
+
+        else:
+            st.write("Ask a Question First!!")

chat_with_pdf.py

@@ -0,0 +1,93 @@
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+import os
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+import google.generativeai as genai
+from langchain.vectorstores import Pinecone as PC
+from langchain_google_genai import ChatGoogleGenerativeAI
+
+from dotenv import load_dotenv
+
+load_dotenv()
+os.getenv("GOOGLE_API_KEY")
+os.getenv("PINECONE_API_KEY")
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+os.environ['PINECONE_API_KEY'] = os.getenv("PINECONE_API_KEY")
+
+
+def Pine():
+    from pinecone import Pinecone, ServerlessSpec
+
+    pc = Pinecone(api_key=os.getenv("PINECONE_API_KEY"))
+    index_name = "testing"
+
+    if index_name not in pc.list_indexes().names():
+        pc.create_index(
+            name=index_name,
+            dimension=768,
+            metric="cosine",
+            spec=ServerlessSpec(cloud='aws', region='us-east-1')
+        )
+    return index_name
+
+
+def get_pdf_text(pdf_docs):
+    text = ""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+    return text
+
+
+def get_text_chunks(text):
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+
+def get_vector_store(text_chunks):
+    index_name = Pine()
+    embedding = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    docsearch = PC.from_texts([t for t in text_chunks], embedding, index_name=index_name)
+    return docsearch
+
+
+def showman(pdf_docs):
+    st.header("Chat with PDF")
+
+    user_question = st.text_input("Ask a Question from the PDF Files", key="user_question")
+    ask_another_question = st.button("Ask Another Question",on_click=clear_text)
+
+    if user_question and not ask_another_question:
+        llm = ChatGoogleGenerativeAI(model="models/gemini-1.5-pro-latest", temperature=0.9)
+        from langchain.chains import RetrievalQA
+        qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=st.session_state["docsearch"].as_retriever())
+        response = qa(user_question)
+        st.session_state["response"] = response["result"]
+        st.write("Answer:", st.session_state["response"])
+
+
+def clear_text():
+    st.session_state["user_question"] = ""
+    st.session_state["response"] = ""
+
+def show():
+    with st.sidebar:
+        st.title("Menu:")
+        pdf_docs = st.file_uploader("Upload your PDF Files", accept_multiple_files=True)
+        st.session_state["pdf_docs"] = pdf_docs if pdf_docs is not None else st.session_state.get("pdf_docs", [])
+        processed = st.session_state.get("processed", False)
+
+        if not processed and pdf_docs:
+            if st.button("Submit & Process"):
+                with st.spinner("Processing..."):
+                    raw_text = get_pdf_text(pdf_docs)
+                    text_chunks = get_text_chunks(raw_text)
+                    docsearch = get_vector_store(text_chunks)
+                    st.session_state["docsearch"] = docsearch
+                    st.session_state["processed"] = True
+                st.success("Done!")
+    
+    showman(st.session_state["pdf_docs"])

requirements.txt

@@ -0,0 +1,7 @@
+PyPDF2
+langchain
+langchain_google_genai
+dotenv
+pinecone
+google.generativeai
+fpdf

streamlit.py

@@ -0,0 +1,23 @@
+import streamlit as st
+
+st.set_page_config(page_title="Gemini_Student", page_icon=":material/edit:")
+
+st.sidebar.title("Welcome to Gemeni_Student")
+selection = st.sidebar.radio("",["Chatbot","Image_QA_Gemini","QA_Gemini","MCQ_Gen","chat_with_pdf"])
+
+if selection == "Chatbot":
+    import Chatbot
+    Chatbot.show()
+elif selection == "Image_QA_Gemini":
+    import Image_QA_Gemini
+    Image_QA_Gemini.show()
+elif selection == "QA_Gemini":
+    import QA_Gemini
+    QA_Gemini.show()
+elif selection == "MCQ_Gen":
+    import MCQ_Gen
+    MCQ_Gen.show()
+elif selection == "chat_with_pdf":
+    import chat_with_pdf
+    chat_with_pdf.show()
+