Upload 5 files

.env

@@ -0,0 +1 @@
+GOOGLE_API_KEY = "AIzaSyDKsDooyPRIIz_HAcm5YilrW7iWI4hhpcs"

app.py

@@ -0,0 +1,88 @@
+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 FAISS
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain.prompts import PromptTemplate
+from dotenv import load_dotenv
+
+
+
+load_dotenv()
+
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+
+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=100)
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+def get_vector_store(text_chunks):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    vector_store=FAISS.from_texts(text_chunks, embedding=embeddings)
+    vector_store.save_local("faiss_index")
+
+def get_conversational_chain():
+    prompt_template = """
+    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in the provided
+    context just say. "answer is not available in the context", don't provide the wrong answer\n\n
+    Context: \n {context}?\n
+    Question: \n {question}\n
+    
+    Answer:
+    """
+
+    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
+
+    prompt = PromptTemplate(template = prompt_template, input_variables=["context", "question"])
+    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
+    return chain
+
+def user_input(user_question):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+
+    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+    docs = new_db.similarity_search(user_question)
+
+    chain = get_conversational_chain()
+
+    response = chain(
+        {"input_documents":docs, "question": user_question},
+        return_only_outputs=True
+    )
+
+    print(response)
+    st.write("Reply: ", response["output_text"])
+
+def main():
+    st.set_page_config("Chit Chat with PDFs")
+    st.header("Chit Chat with your PDFs")
+
+    user_question = st.text_input("Ask a question to chat with your pdf")
+
+    if user_question:
+        user_input(user_question)
+    with st.sidebar:
+        st.title("Menu:")
+        pdf_docs = st.file_uploader("Upload your PDF files here!!!", accept_multiple_files=True, type=['pdf'])
+        if st.button("Submit"):
+            with st.spinner("Processing..."):
+                raw_text = get_pdf_text(pdf_docs)
+                text_chunks = get_text_chunks(raw_text)
+                get_vector_store(text_chunks)
+                st.success("Done")
+
+if __name__ == "__main__":
+    main()

faiss_index/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d379f18dcc1f9502791d7278e7b4857ccee07a8e290c12c4f014688282872f
+size 2772

requirements.txt

@@ -0,0 +1,9 @@
+streamlit
+google-generativeai
+python-dotenv
+langchain
+PyPDF2
+chromadb
+faiss-cpu
+langchain_google_genai
+langchain_community