Upload streamlit app to ask Groq about a PDF

app.py

@@ -0,0 +1,68 @@
+import streamlit as st
+import os
+
+from groq import Groq
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceEmbeddings 
+#from langchain.vectorstores import FAISS
+from langchain_community.vectorstores import FAISS
+from langchain_groq import ChatGroq
+#from langchain.chat_models import ChatOpenAI
+from langchain.chains.question_answering import load_qa_chain
+
+st.set_page_config('Lectorín')
+st.header("Pregunta a tu PDF")
+GROQ_API_KEY = st.text_input('Groq API Key', value="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", type='password')
+pdf_obj = st.file_uploader("Carga tu documento", type="pdf", on_change=st.cache_resource.clear)
+modelos = {
+    'multi, 512, 0.47G, 384 - intfloat/multilingual-e5-small': ('intfloat/multilingual-e5-small',512),
+    'multi, 256, 0.08G, 384 - multi-qa-MiniLM-L6-cos-v1': ('multi-qa-MiniLM-L6-cos-v1',256),
+    'multi,8192, 2.27G,1024 - BAAI/bge-m3': ('BAAI/bge-m3', 8192),
+}
+modelo = st.selectbox('Modelo de embedding', list(modelos.keys()))
+modelo_embeddings, sequence = modelos[modelo]
+chunk_size = sequence * 5 # en español, de media una palabra tiene 5 caracteres
+
+modelos_llm = [
+    'llama3-70b-8192',
+    'llama3-8b-8192',
+    'mixtral-8x7b-32768',
+    'gemma-7b-it'
+]
+modelo_llm = st.selectbox('Modelo de lenguaje', list(modelos_llm))
+
+@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=chunk_size,
+        chunk_overlap=150,
+        length_function=len
+        )        
+
+    chunks = text_splitter.split_text(text)
+    embeddings = HuggingFaceEmbeddings(model_name=modelo_embeddings)
+    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["GROQ_API_KEY"] = GROQ_API_KEY
+        #os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
+        docs = knowledge_base.similarity_search(user_question, 5)
+        llm = ChatGroq(groq_api_key = os.getenv('GROQ_API_KEY'),model = modelo_llm)        
+        #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)

requirements.txt

@@ -0,0 +1,10 @@
+groq
+#openai
+langchain
+langchain-community
+langchain_groq
+PyPDF2
+streamlit
+sentence_transformers
+faiss-cpu
+#faiss-gpu