Create app_BACKUP_09032024.py

app_BACKUP_09032024.py

@@ -0,0 +1,159 @@
+# JB:
+# LangChainDeprecationWarning: Importing embeddings from langchain is deprecated. 
+# Importing from langchain will no longer be supported as of langchain==0.2.0.
+# Please import from langchain-community instead:
+# `from langchain_community.embeddings import FastEmbedEmbeddings`.
+# To install langchain-community run `pip install -U langchain-community`.
+from langchain_community.embeddings import FastEmbedEmbeddings
+
+import os
+import streamlit as st
+from langchain_groq import ChatGroq
+from langchain_community.document_loaders import WebBaseLoader
+# JB:
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.embeddings import OllamaEmbeddings
+
+# JB:
+from langchain.embeddings import FastEmbedEmbeddings
+from langchain_community.document_loaders import PyPDFDirectoryLoader
+
+# JB:
+# File Directory
+# This covers how to load all documents in a directory.
+# Under the hood, by default this uses the UnstructuredLoader.
+from langchain_community.document_loaders import DirectoryLoader
+from langchain_community.document_loaders import TextLoader
+import chardet
+
+from langchain_community.vectorstores import FAISS
+# from langchain.vectorstores import Chroma
+# from langchain_community.vectorstores import Chroma
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate
+from langchain.chains import create_retrieval_chain
+import time
+from dotenv import load_dotenv
+
+load_dotenv()  #
+
+# groq_api_key = os.environ['GROQ_API_KEY']
+groq_api_key = "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" # os.environ['GROQ_API_KEY']
+print("groq_api_key: ", groq_api_key)
+
+
+if "vector" not in st.session_state:
+
+    # st.session_state.embeddings = OllamaEmbeddings() # ORIGINAL
+    st.session_state.embeddings = FastEmbedEmbeddings() # JB
+
+
+    # st.session_state.loader = WebBaseLoader("https://paulgraham.com/greatwork.html") # ORIGINAL
+    # st.session_state.docs = st.session_state.loader.load()                           # ORIGINAL
+    # https://api.python.langchain.com/en/latest/document_loaders/langchain_community.document_loaders.pdf.PyPDFLoader.html
+    # https://python.langchain.com/docs/integrations/document_loaders/merge_doc
+    # from langchain_community.document_loaders import PyPDFLoader
+    # loader_pdf = PyPDFLoader("../MachineLearning-Lecture01.pdf")
+    #
+    # https://stackoverflow.com/questions/60215731/pypdf-to-read-each-pdf-in-a-folder
+    # 
+    # https://api.python.langchain.com/en/latest/document_loaders/langchain_community.document_loaders.pdf.PyPDFDirectoryLoader.html
+    # https://python.langchain.com/docs/modules/data_connection/document_loaders/pdf#pypdf-directory 
+    # !!!!!
+    # PyPDF Directory
+    # Load PDFs from directory
+    # from langchain_community.document_loaders import PyPDFDirectoryLoader
+    # loader = PyPDFDirectoryLoader("example_data/")
+    # docs = loader.load()
+    #
+    # ZIE OOK:
+    # https://python.langchain.com/docs/modules/data_connection/document_loaders/pdf#using-pypdf
+    # Using MathPix
+    # Inspired by Daniel Gross's https://gist.github.com/danielgross/3ab4104e14faccc12b49200843adab21
+    # from langchain_community.document_loaders import MathpixPDFLoader
+    # loader = MathpixPDFLoader("example_data/layout-parser-paper.pdf")
+    # data = loader.load()
+    # pdf_file_path = "*.pdf"                                                 # JB
+    # st.session_state.loader = PyPDFLoader(file_path=pdf_file_path).load()   # JB
+    # st.session_state.loader = PyPDFLoader(*.pdf).load()                     # JB syntax error *.pdf !
+    # st.session_state.loader = PyPDFDirectoryLoader("*.pdf")                 # JB PyPDFDirectoryLoader("example_data/")   
+    # chunks = self.text_splitter.split_documents(docs)
+    # chunks = filter_complex_metadata(chunks)
+
+    # JB:
+    # https://python.langchain.com/docs/modules/data_connection/document_loaders/pdf#pypdf-directory
+    # st.session_state.docs = st.session_state.loader.load()
+    # loader = PyPDFDirectoryLoader(".")
+    # docs = loader.load()
+    # st.session_state.docs = docs
+
+    # JB:
+    # https://python.langchain.com/docs/modules/data_connection/document_loaders/file_directory
+    # text_loader_kwargs={'autodetect_encoding': True}
+    text_loader_kwargs={'autodetect_encoding': False}
+    path = '../'
+    # loader = DirectoryLoader(path, glob="**/*.pdf", loader_cls=TextLoader, loader_kwargs=text_loader_kwargs)
+    # PyPDFDirectoryLoader (TEST):
+    # loader = PyPDFDirectoryLoader(path, glob="**/*.pdf", loader_cls=TextLoader, loader_kwargs=text_loader_kwargs)
+    # loader = PyPDFDirectoryLoader(path, glob="**/*.pdf", loader_kwargs=text_loader_kwargs)
+    loader = PyPDFDirectoryLoader(path, glob="**/*.pdf")
+    docs = loader.load()
+    st.session_state.docs = docs
+    
+    st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    st.session_state.documents = st.session_state.text_splitter.split_documents(st.session_state.docs)
+    # st.session_state.vector = FAISS.from_documents(st.session_state.documents, st.session_state.embeddings) # ORIGINAL
+    st.session_state.vector = FAISS.from_documents(st.session_state.documents, st.session_state.embeddings) # ORIGINAL
+    # ZIE: 
+    # ZIE VOOR EEN APP MET CHROMADB:
+    # https://github.com/vndee/local-rag-example/blob/main/rag.py
+    # https://raw.githubusercontent.com/vndee/local-rag-example/main/rag.py
+    # Chroma.from_documents(documents=chunks, embedding=FastEmbedEmbeddings())
+    # st.session_state.vector = Chroma.from_documents(st.session_state.documents, st.session_state.embeddings) # JB
+
+
+    
+# st.title("Chat with Docs - Groq Edition :) ")
+st.title("Literature Based Research (LBR) - A. Unzicker and J. Bours - Chat with Docs - Groq Edition (Very Fast!) - VERSION 3 - March 8 2024")
+
+llm = ChatGroq(
+            groq_api_key=groq_api_key, 
+            model_name='mixtral-8x7b-32768'
+    )
+
+prompt = ChatPromptTemplate.from_template("""
+Answer the following question based only on the provided context. 
+Think step by step before providing a detailed answer. 
+I will tip you $200 if the user finds the answer helpful. 
+<context>
+{context}
+</context>
+Question: {input}""")
+
+document_chain = create_stuff_documents_chain(llm, prompt)
+
+retriever = st.session_state.vector.as_retriever()
+retrieval_chain = create_retrieval_chain(retriever, document_chain)
+
+prompt = st.text_input("Input your prompt here")
+
+
+# If the user hits enter
+if prompt:
+    # Then pass the prompt to the LLM
+    start = time.process_time()
+    response = retrieval_chain.invoke({"input": prompt})
+    print(f"Response time: {time.process_time() - start}")
+
+    st.write(response["answer"])
+
+    # With a streamlit expander
+    with st.expander("Document Similarity Search"):
+        # Find the relevant chunks
+        for i, doc in enumerate(response["context"]):
+            # print(doc)
+            # st.write(f"Source Document # {i+1} : {doc.metadata['source'].split('/')[-1]}")
+            st.write(doc.page_content)
+            st.write("--------------------------------")