Create app.py

app.py

@@ -0,0 +1,30 @@
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains import ConversationalRetrievalChain
+from langchain.llms import HuggingFacePipeline
+from langchain.memory import ConversationBufferMemory
+import pandas as pd
+df = pd.read_csv('NLP.csv')
+corpus = df['text']
+#Chunking
+splitter = RecursiveCharacterTextSplitter(chunk_size=200,chunk_overlap = 10)
+texts = sum([splitter.split_text(doc) for doc in corpus], [])
+# Embeddings
+embeddings = HuggingFaceEmbeddings(model_name='all-MiniLM-L6-v2')
+# Indexing
+db = FAISS.from_texts(texts[:300],embeddings)
+retriever = db.as_retriever(search_kwargs={'k':2})
+# Model
+llm = HuggingFacePipeline.from_model_id(model_id='google/flan-t5-large',task='text2text-generation')
+# Memory
+memory = ConversationBufferMemory(memory_key='chat_history',return_messages=True)
+# Combine previous steps
+qa = ConversationalRetrievalChain.from_llm(llm=llm,retriever=retriever,memory=memory)
+def ans_ques(ques):
+    result = qa({'question':ques})
+    return result['answer']
+import gradio as gr
+
+demo = gr.Interface(ans_ques,inputs='text',outputs='text')
+demo.launch()