Update rag.py

rag.py

@@ -1,5 +1,19 @@
 import os
 
+from langchain.chains import LLMChain, RetrievalQA
+from langchain.chat_models import ChatOpenAI
+from langchain.document_loaders import PyPDFLoader, WebBaseLoader
+from langchain.document_loaders.blob_loaders.youtube_audio import YoutubeAudioLoader
+from langchain.document_loaders.generic import GenericLoader
+from langchain.document_loaders.parsers import OpenAIWhisperParser
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.prompts import PromptTemplate
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Chroma
+from langchain.vectorstores import MongoDBAtlasVectorSearch
+
+from pymongo import MongoClient
+
 PDF_URL       = "https://arxiv.org/pdf/2303.08774.pdf"
 WEB_URL       = "https://openai.com/research/gpt-4"
 YOUTUBE_URL_1 = "https://www.youtube.com/watch?v=--khbXchTeE"
@@ -17,10 +31,6 @@ MONGODB_INDEX_NAME        = "default"
 LLM_CHAIN_PROMPT = PromptTemplate(input_variables = ["question"], template = os.environ["LLM_TEMPLATE"])
 RAG_CHAIN_PROMPT = PromptTemplate(input_variables = ["context", "question"], template = os.environ["RAG_TEMPLATE"])
 
-RAG_OFF     = "Off"
-RAG_CHROMA  = "Chroma"
-RAG_MONGODB = "MongoDB"
-
 client = MongoClient(MONGODB_ATLAS_CLUSTER_URI)
 collection = client[MONGODB_DB_NAME][MONGODB_COLLECTION_NAME]
 
@@ -28,8 +38,6 @@ config = {
     "chunk_overlap": 150,
     "chunk_size": 1500,
     "k": 3,
-    "model_name": "gpt-4-0613",
-    "temperature": 0,
 }
 
 def document_loading_splitting():