Delete app.py

app.py

@@ -1,104 +0,0 @@
-#from langchain import PromptTemplate
-from langchain_core.prompts import PromptTemplate
-import os 
-from langchain_community.embeddings import HuggingFaceBgeEmbeddings
-from langchain_community.vectorstores import FAISS
-from langchain_community.llms.ctransformers import CTransformers
-#from langchain.chains import RetrievalQA
-from langchain.chains.retrieval_qa.base import RetrievalQA
-
-DB_FAISS_PATH = 'vectorstores/'
-
-custom_prompt_template = '''use the following pieces of information to answer the user's questions.
-If you don't know the answer, please just say that don't know the answer, don't try to make uo an answer.
-Context : {context}
-Question : {question}
-only return the helpful answer below and nothing else.
-'''
-
-def set_custom_prompt():
-    """
-    Prompt template for QA retrieval for vector stores
-    """
-    prompt = PromptTemplate(template = custom_prompt_template,
-                            input_variables = ['context','question'])
-    
-    return prompt
-    
-
-def load_llm():
-    llm = CTransformers(
-        model = 'TheBloke/Llama-2-7B-Chat-GGML',
-        #model = AutoModel.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML"),
-        model_type = 'llama',
-        max_new_token = 512,
-        temperature = 0.5
-    )
-    return llm
-
-def retrieval_qa_chain(llm,prompt,db):
-    qa_chain = RetrievalQA.from_chain_type(
-        llm = llm,
-        chain_type = 'stuff',
-        retriever = db.as_retriever(search_kwargs= {'k': 2}),
-        return_source_documents = True,
-        chain_type_kwargs = {'prompt': prompt}
-    )
-
-    return qa_chain
-
-def qa_bot():
-    embeddings = HuggingFaceBgeEmbeddings(model_name = 'sentence-transformers/all-MiniLM-L6-v2',
-                                          model_kwargs = {'device':'cpu'})
-    
-    
-    db = FAISS.load_local(DB_FAISS_PATH, embeddings,allow_dangerous_deserialization=True)
-    llm = load_llm()
-    qa_prompt = set_custom_prompt()
-    qa = retrieval_qa_chain(llm,qa_prompt, db)
-
-    return qa
-
-def final_result(query):
-    qa_result = qa_bot()
-    response = qa_result({'query' : query})
-
-    return response
-
-
-import streamlit as st
-
-# Initialize the bot
-bot = qa_bot()
-
-# def process_query(query):
-#     # Here you would include the logic to process the query and return a response
-#     response, sources = bot.answer_query(query)  # Modify this according to your bot implementation
-#     if sources:
-#         response += f"\nSources: {', '.join(sources)}"
-#     else:
-#         response += "\nNo Sources Found"
-#     return response
-def process_query(query):
-    # Here you would include the logic to process the query and return a response
-    response = bot({'query': query})
-    response_text = response['result']
-    sources = response.get('source_documents', [])
-    if sources:
-        source_list = ', '.join([source.metadata['source'] for source in sources])
-        response_text += f"\nSources: {source_list}"
-        #st.write(response_text)
-    else:
-        response_text += "\nNo Sources Found"
-        #st.write(response_text)
-    return response_text
-
-
-# Setting up the Streamlit app
-st.title('Medical Chatbot')
-
-user_input = st.text_input("Hi, welcome to the medical Bot. What is your query?")
-
-if user_input:
-    output = process_query(user_input)
-    st.text_area("Response", output, height=300)