Upload 3 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+docs/Ali_Md_Monsur_Masterthesis.pdf filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,59 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain.llms import HuggingFacePipeline
+from langchain.chains import RetrievalQA
+
+checkpoint = "LaMini-T5-738M"
+
+@st.cache_resource
+def load_llm():
+    tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+    model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
+    pipe = pipeline(
+        'text2text-generation',
+        model=model,
+        tokenizer=tokenizer,
+        max_length=256,
+        do_sample=True,
+        temperature=0.3,
+        top_p=0.95
+    )
+    return HuggingFacePipeline(pipeline=pipe)
+
+@st.cache_resource
+def qa_llm():
+    llm = load_llm()
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    db = FAISS.load_local("faiss_index", embeddings)
+    retriever = db.as_retriever()
+    qa = RetrievalQA.from_chain_type(
+        llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True)
+    return qa
+
+def process_answer(instruction):
+    qa = qa_llm()
+    generated_text = qa(instruction)
+    answer = generated_text['result']
+    return answer, generated_text
+
+def main():
+    st.title("Search Your PDF 🐦📄")
+    with st.expander("About the App"):
+        st.markdown(
+            """
+            This is a Generative AI powered Question and Answering app that responds to questions about your PDF File.
+            """
+        )
+    question = st.text_area("Enter your Question")
+    if st.button("Ask"):
+        st.info("Your Question: " + question)
+        
+        st.info("Your Answer")
+        answer, metadata = process_answer(question)
+        st.write(answer)
+        st.write(metadata)
+
+if __name__ == '__main__':
+    main()

docs/Ali_Md_Monsur_Masterthesis.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d4815c2923a3b8a116976dcf225ae21a670d83ac7d9895bfe418ca6343160d
+size 3059014

ingest.py

@@ -0,0 +1,30 @@
+import os
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader, PDFMinerLoader
+from langchain_community.embeddings import SentenceTransformerEmbeddings
+from langchain_community.vectorstores import FAISS
+
+def main():
+    documents = []
+    for root, dirs, files in os.walk("docs"):
+        for file in files:
+            if file.endswith(".pdf"):
+                print(file)
+                loader = PDFMinerLoader(os.path.join(root, file))
+    documents = loader.load()
+    
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=500)
+    texts = text_splitter.split_documents(documents)
+    
+    # Create embeddings
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    
+    # Create FAISS index
+    db = FAISS.from_documents(texts, embeddings)
+    
+    # Save the index
+    db.save_local("faiss_index")
+
+if __name__ == "__main__":
+    main()