Upload 6 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/71763-gale-encyclopedia-of-medicine.-vol.-1.-2nd-ed.pdf filter=lfs diff=lfs merge=lfs -text
+vectorstores/db_faiss/index.faiss filter=lfs diff=lfs merge=lfs -text

data/71763-gale-encyclopedia-of-medicine.-vol.-1.-2nd-ed.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753cd53b7a3020bbd91f05629b0e3ddcfb6a114d7bbedb22c2298b66f5dd00cc
+size 16127037

ingest.py

@@ -0,0 +1,23 @@
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+
+
+DATA_PATH="data/"
+DB_FAISS_PATH="vectorstores/db_faiss"
+
+def create_vector_db():
+    loader = DirectoryLoader(DATA_PATH, glob='*.pdf', loader_cls=PyPDFLoader)
+    documents =loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    texts = text_splitter.split_documents(documents)
+
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
+    model_kwargs = {'device': 'cpu'})
+
+    db = FAISS.from_documents(texts, embeddings)
+    db.save_local(DB_FAISS_PATH)
+
+if __name__ == "__main__":
+    create_vector_db()

model.py

@@ -0,0 +1,131 @@
+import streamlit as st
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain import PromptTemplate
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.llms import CTransformers
+from langchain.chains import RetrievalQA
+
+DB_FAISS_PATH = 'vectorstores/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():
+    llm = CTransformers(
+        model="TheBloke/Llama-2-7B-Chat-GGML",
+        model_type="llama",
+        max_new_tokens=512,
+        temperature=0.5
+    )
+    return llm
+
+def qa_bot(query):
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
+                                       model_kwargs={'device': 'cpu'})
+    db = FAISS.load_local(DB_FAISS_PATH, embeddings)
+    llm = load_llm()
+    qa_prompt = set_custom_prompt()
+    qa = retrieval_qa_chain(llm, qa_prompt, db)
+
+    # Implement the question-answering logic here
+    response = qa({'query': query})
+    return response['result']
+
+def add_vertical_space(spaces=1):
+    for _ in range(spaces):
+        st.markdown("---") 
+
+def main():
+    st.set_page_config(page_title="Llama-2-GGML Medical Chatbot")
+
+    with st.sidebar:
+        st.title('Llama-2-GGML Medical Chatbot! 🚀🤖')
+        st.markdown('''
+        ## About
+                    
+        The Llama-2-GGML Medical Chatbot uses the **Llama-2-7B-Chat-GGML** model and was trained on medical data from **"The GALE ENCYCLOPEDIA of MEDICINE"**.
+                    
+        ### 🔄Bot evolving, stay tuned!
+        ## Useful Links 🔗
+
+        - **Model:** [Llama-2-7B-Chat-GGML](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML) 📚
+        - **GitHub:** [ThisIs-Developer/Llama-2-GGML-Medical-Chatbot](https://github.com/ThisIs-Developer/Llama-2-GGML-Medical-Chatbot) 💬
+        ''')
+        add_vertical_space(1)  # Adjust the number of spaces as needed
+        st.write('Made by [@ThisIs-Developer](https://huggingface.co/ThisIs-Developer)')
+
+    st.title("Llama-2-GGML Medical Chatbot")
+    st.markdown(
+        """
+        <style>
+            .chat-container {
+                display: flex;
+                flex-direction: column;
+                height: 400px;
+                overflow-y: auto;
+                padding: 10px;
+            }
+            .user-bubble {
+                background-color: #DCF8C6;
+                align-self: flex-end;
+                border-radius: 10px;
+                padding: 8px;
+                margin: 5px;
+                max-width: 70%;
+                word-wrap: break-word;
+            }
+            .bot-bubble {
+                background-color: #E0E0E0;
+                align-self: flex-start;
+                border-radius: 10px;
+                padding: 8px;
+                margin: 5px;
+                max-width: 70%;
+                word-wrap: break-word;
+            }
+        </style>
+        """
+    , unsafe_allow_html=True)
+
+    conversation = st.session_state.get("conversation", [])
+    
+    query = st.text_input("Ask your question here:", key="user_input")
+    if st.button("Get Answer"):
+        if query:
+            conversation.append({"role": "user", "message": query})
+            # Call your QA function
+            answer = qa_bot(query)
+            conversation.append({"role": "bot", "message": answer})
+            st.session_state.conversation = conversation
+        else:
+            st.warning("Please input a question.")
+
+    chat_container = st.empty()
+    chat_bubbles = ''.join([f'<div class="{c["role"]}-bubble">{c["message"]}</div>' for c in conversation])
+    chat_container.markdown(f'<div class="chat-container">{chat_bubbles}</div>', unsafe_allow_html=True)
+
+if __name__ == "__main__":
+    main()
+

requirements.txt

@@ -0,0 +1,11 @@
+pypdf==3.15.5
+accelerate==0.22.0
+bitsandbytes==0.41.1
+chainlit==0.6.402
+ctransformers==0.2.26
+faiss-cpu==1.7.4
+huggingface-hub==0.16.4
+langchain==0.0.281
+sentence-transformers==2.2.2
+torch==2.0.1
+transformers==4.33.0

vectorstores/db_faiss/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b1dd53e3fc2abc2535c8c24111b40ede2386c32a1604eaec17f3232646e7ee
+size 10983981

vectorstores/db_faiss/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4007c732db0ecbd2a226c55a6f83f1bb9bf8d899079a2e52b971f8da3d78cea5
+size 3567746