Update app.py

app.py

@@ -1,43 +1,43 @@
 import gradio as gr
 # from langchain.llms import GooglePalm
 from langchain_google_genai import GoogleGenerativeAI
+from langchain.document_loaders.csv_loader import CSVLoader
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.prompts import PromptTemplate
+from langchain.chains import RetrievalQA
+import warnings
 
-from transformers import AutoModelForCausalLM, AutoTokenizer
 
-llm = "mistralai/Mixtral-8x22B-Instruct-v0.1"
+# from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import pipeline
 
-api_key = "AIzaSyCdM_aAIsW_nPbjarOF83mbX1_z1cVX2_M"
+pipe = pipeline("text-generation", model = "meta-llama/Meta-Llama-3-70B-Instruct")
+
+# llm = "mistralai/Mixtral-8x22B-Instruct-v0.1"
+
+# api_key = "AIzaSyCdM_aAIsW_nPbjarOF83mbX1_z1cVX2_M"
 
 # llm = GoogleGenerativeAI(model="models/text-bison-001", google_api_key=api_key)
 # llm = GooglePalm(google_api_key = api_key, temperature=0.7)
 
-from langchain.document_loaders.csv_loader import CSVLoader
-
+# LOADING CSV FILE
 loader = CSVLoader(file_path='aiotsmartlabs_faq.csv', source_column = 'prompt')
 data = loader.load()
 
-from langchain_huggingface import HuggingFaceEmbeddings
-from langchain.vectorstores import FAISS
-import warnings
-
-# Suppress specific warnings if they are not critical
+# SUPPRESSING WARNINGS
 warnings.filterwarnings("ignore", category=UserWarning, message="TypedStorage is deprecated")
 warnings.filterwarnings("ignore", category=FutureWarning, message="`resume_download` is deprecated")
 
-# Define the embedding model
-# Using a smaller model for demonstration purposes; adjust according to your needs
-model_name = "BAAI/bge-m3"
 
-# Initialize HuggingFace embeddings
+# EMBEDDING MODEL
+model_name = "BAAI/bge-m3"
 instructor_embeddings = HuggingFaceEmbeddings(model_name=model_name)
 
 # Create FAISS vector store from documents
 vectordb = FAISS.from_documents(documents=data, embedding=instructor_embeddings)
-
 retriever = vectordb.as_retriever()
 
-from langchain.prompts import PromptTemplate
-
 prompt_template = """Given the following context and a question, generate an answer based on the context only.
 
 In the answer try to provide as much text as possible from "response" section in the source document context without making much changes.
@@ -52,7 +52,6 @@ PROMPT = PromptTemplate(
     template = prompt_template, input_variables = ["context", "question"]
 )
 
-from langchain.chains import RetrievalQA
 
 chain = RetrievalQA.from_chain_type(llm = llm,
             chain_type="stuff",