added changes

app.py

@@ -0,0 +1,83 @@
+import streamlit as st
+from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.prompts import PromptTemplate
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_community.llms import CTransformers
+from langchain.chains import RetrievalQA
+
+DB_FAISS_PATH = 'vectorstore/db_faiss'
+
+custom_prompt_template = """Use the following pieces of information to answer the user's question. If you don't know the answer, just say that you don't know, don't try to make up an answer.
+
+Context: {context}
+Question: {question}
+
+Only return the helpful answer below and nothing else.
+Helpful answer: """
+
+def set_custom_prompt():
+    prompt = PromptTemplate(template=custom_prompt_template,
+                          input_variables=['context', 'question'])
+    return prompt
+
+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 load_llm():
+    model_path = "/home/ebiz/Govind/Llama2-Medical-Chatbot/llama-2-7b-chat.ggmlv3.q4_0.bin"
+    llm = CTransformers(
+        model=model_path,
+        model_type="llama",
+        max_new_tokens=1024,
+        temperature=0.5
+    )
+    return llm
+
+def qa_bot():
+    embeddings = HuggingFaceEmbeddings(
+        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 main():
+    st.title("Medical Chatbot")
+    
+    # Initialize session state for chat history
+    if "messages" not in st.session_state:
+        st.session_state.messages = []
+        
+    # Display chat history
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+    
+    # Chat input
+    if prompt := st.chat_input("What is your medical query?"):
+        # Display user message
+        st.session_state.messages.append({"role": "user", "content": prompt})
+        with st.chat_message("user"):
+            st.markdown(prompt)
+            
+        # Generate and display assistant response
+        with st.chat_message("assistant"):
+            with st.spinner("Thinking..."):
+                qa_chain = qa_bot()
+                response = qa_chain({'query': prompt})
+                st.markdown(response["result"])
+                st.session_state.messages.append({"role": "assistant", "content": response["result"]})
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,11 @@
+pypdf
+langchain
+torch
+accelerate
+bitsandbytes
+ctransformers
+sentence_transformers
+faiss_cpu
+chainlit
+huggingface_hub
+langchain_community

vectorstore/db_faiss/model.py

@@ -0,0 +1,105 @@
+from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.prompts import PromptTemplate
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_community.llms import CTransformers
+from langchain.chains import RetrievalQA
+import chainlit as cl
+
+DB_FAISS_PATH = 'vectorstore/db_faiss'
+
+custom_prompt_template = """Use the following pieces of information to answer the user's question.
+If you don't know the answer, just say that you don't know, don't try to make up an answer.
+
+Context: {context}
+Question: {question}
+
+Only return the helpful answer below and nothing else.
+Helpful answer:
+"""
+
+def set_custom_prompt():
+    """
+    Prompt template for QA retrieval for each vectorstore
+    """
+    prompt = PromptTemplate(template=custom_prompt_template,
+                            input_variables=['context', 'question'])
+    return prompt
+
+#Retrieval QA Chain
+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
+
+#Loading the model
+def load_llm():
+    # Load the locally downloaded model here
+    
+    # Path to the specific GGML model file you want to use
+    model_path = "/home/ebiz/Govind/Llama2-Medical-Chatbot/llama-2-7b-chat.ggmlv3.q4_0.bin"
+    
+    
+    llm = CTransformers(
+        model = model_path,
+        model_type="llama",
+        max_new_tokens = 1024,
+        temperature = 0.5
+    )
+    return llm
+
+#QA Model Function
+def qa_bot():
+    embeddings = HuggingFaceEmbeddings(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
+
+#output function
+def final_result(query):
+    qa_result = qa_bot()
+    response = qa_result({'query': query})
+    return response
+
+#chainlit code
+@cl.on_chat_start
+async def start():
+    chain = qa_bot()
+    msg = cl.Message(content="Starting the bot...")
+    await msg.send()
+    msg.content = "Hi, Welcome to Medical Bot. What is your query?"
+    await msg.update()
+
+    cl.user_session.set("chain", chain)
+
+@cl.on_message
+async def main(message: cl.Message):
+    chain = cl.user_session.get("chain") 
+
+    # Disable streaming to avoid duplicate answers
+    cb = cl.AsyncLangchainCallbackHandler(
+        stream_final_answer=False  # Disable streaming to prevent multiple responses
+    )
+
+    res = await chain.acall(message.content, callbacks=[cb])
+    answer = res["result"]
+    sources = res.get("source_documents", [])
+
+    # Ensure the answer is sent once and with sources if available
+    # if sources:
+    #     source_info = "\nSources:\n" + "\n".join([doc.metadata.get("source", "Unknown") for doc in sources])
+    #     answer += source_info
+    # else:
+    #     answer += "\nNo sources found"
+
+    await cl.Message(content=answer).send()
+
+