Update app.py

app.py

@@ -4,11 +4,12 @@ from dotenv import load_dotenv
 import time
 from langchain.vectorstores import Chroma
 from langchain.embeddings import HuggingFaceEmbeddings
-from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.prompts import ChatPromptTemplate, PromptTemplate
 from langchain_groq import ChatGroq
 from langchain.chains import RetrievalQA
 from langchain.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains import LLMChain
 
 # Set persistent storage path
 PERSISTENT_DIR = "vector_db"
@@ -124,7 +125,7 @@ print(f"Loading and processing PDFs & vector database took {end_time - start_tim
 start_time = time.time()
 retriever = vector_db.as_retriever()
 
-prompt_template = """Use the following pieces of context to answer the question at the end.
+prompt_template = """Use the following pieces of context to answer the question at the end. If the context doesn't provide enough information to answer the question, use your existing knowledge as an Agro-Homeopathy expert to provide the best possible answer.
 
 {context}
 
@@ -143,7 +144,16 @@ qa = RetrievalQA.from_chain_type(
         )
     }
 )
-#qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever)
+
+# Create a separate LLMChain for fallback
+fallback_template = """You are an expert Agro-Homeopathy doctor. Answer the following question to the best of your ability:
+
+Question: {question}
+
+Answer:"""
+
+fallback_prompt = PromptTemplate(template=fallback_template, input_variables=["question"])
+fallback_chain = LLMChain(llm=llm, prompt=fallback_prompt)
 
 chat_container = st.container()
 
@@ -158,10 +168,12 @@ start_time = time.time()
 if submit_button and query:
     with st.spinner("Generating response..."):
         result = qa({"query": query})  
-    if result['result'].strip() == "":
-        response = "I apologize, but I don't have enough information in the provided PDFs to answer your question."
-    else:
-        response = result['result']
+        if result['result'].strip() == "":
+            # If no result from PDF, use fallback chain
+            fallback_result = fallback_chain.run(query)
+            response = fallback_result
+        else:
+            response = result['result']
 
     col1, col2 = st.columns([1, 10])
     with col1:
@@ -179,4 +191,4 @@ if submit_button and query:
     st.session_state["query"] = ""
 
 end_time = time.time()
-print(f"Actual query took {end_time - start_time:.4f} seconds")
+print(f"Actual query took {end_time - start_time:.4f} seconds")