app.py

app.py

@@ -1,82 +1,81 @@
 import os
 import pickle
+os.environ["Hugging_Face_API_KEY"] = "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"
+
+urls = [
+ 'https://zollege.in/exams/bitsat',
+ 'https://zollege.in/exams/cat',
+ 'https://zollege.in/exams/gate',
+ 'https://zollege.in/exams/neet'
+ 'https://zollege.in/exams/lsat',
+ 'https://zollege.in/exams/jee-advanced',
+ 'https://zollege.in/exams/aipmcet']
+
 from langchain.document_loaders import UnstructuredURLLoader
+loaders = UnstructuredURLLoader(urls=urls)
+data = loaders.load()
+
 from langchain.text_splitter import CharacterTextSplitter
+
+text_splitter = CharacterTextSplitter(separator='\n',
+                                      chunk_size=500,
+                                      chunk_overlap=20)
+
+
+docs = text_splitter.split_documents(data)
+
+
 from InstructorEmbedding import INSTRUCTOR
 from langchain.vectorstores import FAISS
+
 from langchain.embeddings import HuggingFaceInstructEmbeddings
+
+instructor_embeddings = HuggingFaceInstructEmbeddings(model_name="sembeddings/model_gpt_trained"
+                        )  # nice working with model = sentence-transformers/all-MiniLM-L6-v2
+
+db_instructEmbedd = FAISS.from_documents(docs, instructor_embeddings)
+retriever = db_instructEmbedd.as_retriever(search_kwargs={"k": 3})
+
+with open("db_instructEmbedd.pkl", "wb") as f:
+    pickle.dump(db_instructEmbedd, f)
+
+with open("db_instructEmbedd.pkl", "rb") as f:
+    retriever = pickle.load(f)
+
+retriever = retriever.as_retriever(search_kwargs={"k": 3})
+
+
+os.environ["HUGGINGFACEHUB_API_TOKEN"] = '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'
+
 from langchain.chains import RetrievalQA
 from langchain import HuggingFaceHub
+
+
+llm = llm=HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.1}) #repo_id = gpt2 works goodd
+
+qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True)
+
+
 import streamlit as st
+
+st.title('Chatbot Trained on Indian Exam Articles')
+st.header("Hi!! How Can I Help You ?")
+
+query = st.chat_input('> ')
+result = qa({'query': query})
+st.write(result['result'])
+st.button('Not Satisfied! Talk to our Expert Here..')
+
+import pprint
+
+os.environ["SERPER_API_KEY"] = "a69857e460dd51585e009a43743711b110b6beee"
+
 from langchain.utilities import GoogleSerperAPIWrapper
 
-class Chatbot:
-    def __init__(self):
-        os.environ["Hugging_Face_API_KEY"] = "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"
-        os.environ["HUGGINGFACEHUB_API_TOKEN"] = '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'
-        os.environ["SERPER_API_KEY"] = "a69857e460dd51585e009a43743711b110b6beee"
-        
-    def load_data(self):
-        urls = [
-            'https://zollege.in/exams/bitsat',
-            'https://zollege.in/exams/cat',
-            'https://zollege.in/exams/gate',
-            'https://zollege.in/exams/neet',
-            'https://zollege.in/exams/lsat',
-            'https://zollege.in/exams/jee-advanced',
-            'https://zollege.in/exams/aipmcet'
-        ]
-
-        loaders = UnstructuredURLLoader(urls=urls)
-        data = loaders.load()
-
-        return data
-
-    def split_documents(self, data):
-        text_splitter = CharacterTextSplitter(separator='\n', chunk_size=500, chunk_overlap=20)
-        docs = text_splitter.split_documents(data)
-
-        return docs
-
-    def create_embeddings(self, docs):
-        instructor_embeddings = HuggingFaceInstructEmbeddings(model_name="sembeddings/model_gpt_trained")
-        db_instructEmbedd = FAISS.from_documents(docs, instructor_embeddings)
-        retriever = db_instructEmbedd.as_retriever(search_kwargs={"k": 3})
-
-        with open("db_instructEmbedd.pkl", "wb") as f:
-            pickle.dump(db_instructEmbedd, f)
-
-        return retriever
-
-    def load_embeddings(self):
-        with open("db_instructEmbedd.pkl", "rb") as f:
-            retriever = pickle.load(f)
-        
-        retriever = retriever.as_retriever(search_kwargs={"k": 3})
-        return retriever
-
-    def create_qa_model(self, retriever):
-        llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature": 0.1})
-        qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True)
-        return qa
-
-    def run_chatbot(self):
-        st.title('Chatbot Trained on Indian Exam Articles')
-        st.header("Hi!! How Can I Help You ?")
-
-        query = st.text_input('')
-        result = self.qa({'query': query})
-        st.write(result['result'])
-
-    def run_google_search(self, query):
-        search = GoogleSerperAPIWrapper()
-        search.run(query)
+search = GoogleSerperAPIWrapper()
+
+search.run(result['query'])
 
 
 if __name__ == "__main__":
-    chatbot = Chatbot()
-    data = chatbot.load_data()
-    docs = chatbot.split_documents(data)
-    retriever = chatbot.create_embeddings(docs)
-    chatbot.qa = chatbot.create_qa_model(retriever)
-    chatbot.run_chatbot()
+    main()