Create app.py

app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+import os
+
+
+
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_community.chat_models import ChatOpenAI
+from langchain.chains.question_answering import load_qa_chain
+
+
+
+st.set_page_config('preguntaDOC')
+st.header("Pregunta a tu PDF")
+OPENAI_API_KEY = st.text_input('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', type='password')
+pdf_obj = st.file_uploader("Carga tu documento", type="pdf", on_change=st.cache_resource.clear)
+
+@st.cache_resource 
+def create_embeddings(pdf):
+    pdf_reader = PdfReader(pdf)
+    text = ""
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1800,
+        chunk_overlap=1000,
+        length_function=len
+        )        
+    chunks = text_splitter.split_text(text)
+
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
+    knowledge_base = FAISS.from_texts(chunks, embeddings)
+
+    return knowledge_base
+
+if pdf_obj:
+    knowledge_base = create_embeddings(pdf_obj)
+    user_question = st.text_input("Haz una pregunta sobre tu PDF:")
+
+    if user_question:
+        os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
+        docs = knowledge_base.similarity_search(user_question, 3)
+        llm = ChatOpenAI(model_name='gpt-3.5-turbo')
+        chain = load_qa_chain(llm, chain_type="stuff")
+        respuesta = chain.run(input_documents=docs, question=user_question)
+
+        st.write(respuesta)    
+
+
+