Update app.py

app.py

@@ -7,29 +7,28 @@ from langchain_community.llms import CTransformers
 from langchain.chains import RetrievalQA
 from huggingface_hub import snapshot_download
 
-# Download the FAISS database files
+# Download the FAISS database files from Hugging Face
 local_dir = snapshot_download(
-    repo_id="GovindRaj/upload-pdf",
-    repo_type="space",
-    local_dir="./vectorstore"
+    repo_id="GovindRaj/faiss-vectorstore",  # Your Hugging Face repo
+    repo_type="space",  # Dataset or space, as needed
+    local_dir="./vectorstore"  # Local path to store downloaded data
 )
 
-# Update the path to local directory
+# Path to the local FAISS database after download
 DB_FAISS_PATH = './vectorstore/db_faiss'
 
+# Define your custom prompt template for the LLM
 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'])
+    prompt = PromptTemplate(template=custom_prompt_template, input_variables=['context', 'question'])
     return prompt
 
+# Function to create a retrieval-based QA chain
 def retrieval_qa_chain(llm, prompt, db):
     qa_chain = RetrievalQA.from_chain_type(
         llm=llm,
@@ -40,6 +39,7 @@ def retrieval_qa_chain(llm, prompt, db):
     )
     return qa_chain
 
+# Load the LLM model (e.g., LLaMA model from a local path)
 def load_llm():
     model_path = "./llama-2-7b-chat.ggmlv3.q4_0.bin"
     llm = CTransformers(
@@ -50,6 +50,7 @@ def load_llm():
     )
     return llm
 
+# Main chatbot logic
 def qa_bot():
     embeddings = HuggingFaceEmbeddings(
         model_name="sentence-transformers/all-MiniLM-L6-v2",
@@ -61,6 +62,7 @@ def qa_bot():
     qa = retrieval_qa_chain(llm, qa_prompt, db)
     return qa
 
+# Streamlit main app
 def main():
     st.title("Medical Chatbot")
     
@@ -89,4 +91,4 @@ def main():
                 st.session_state.messages.append({"role": "assistant", "content": response["result"]})
 
 if __name__ == '__main__':
-    main()
+    main()