Update app.py

app.py

@@ -1,50 +1,147 @@
 
-import pandas as pd
+# import pandas as pd
 
 
-df = pd.read_json("./tourisme_chatbot.json")
+# df = pd.read_json("./tourisme_chatbot.json")
 
-context_data = []
-for i in range(len(df)):
-  context = ""
-  for j in range(4):
-    context += df.columns[j]
-    context += ": "
-    context += df.iloc[i][j]
-    context += " "
-  context_data.append(context)
+# context_data = []
+# for i in range(len(df)):
+#   context = ""
+#   for j in range(4):
+#     context += df.columns[j]
+#     context += ": "
+#     context += df.iloc[i][j]
+#     context += " "
+#   context_data.append(context)
 
 
-import os
+# import os
 
-# Get the secret key from the environment
-groq_key = os.environ.get('groq_api_key')
+# # Get the secret key from the environment
+# groq_key = os.environ.get('groq_api_key')
 
-## LLM used for RAG
-from langchain_groq import ChatGroq
+# ## LLM used for RAG
+# from langchain_groq import ChatGroq
 
-llm = ChatGroq(model="llama-3.1-70b-versatile",api_key=groq_key)
+# llm = ChatGroq(model="llama-3.1-70b-versatile",api_key=groq_key)
 
-## Embedding model!
-from langchain_huggingface import HuggingFaceEmbeddings
-embed_model = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")
+# ## Embedding model!
+# from langchain_huggingface import HuggingFaceEmbeddings
+# embed_model = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")
 
-# create vector store!
-from langchain_chroma import Chroma
+# # create vector store!
+# from langchain_chroma import Chroma
 
-vectorstore = Chroma(
-    collection_name="tourism_dataset_store",
-    embedding_function=embed_model,
-    persist_directory="./",
-)
+# vectorstore = Chroma(
+#     collection_name="tourism_dataset_store",
+#     embedding_function=embed_model,
+#     persist_directory="./",
+# )
+
+# # add data to vector nstore
+# vectorstore.add_texts(context_data)
+
+# retriever = vectorstore.as_retriever()
+
+# from langchain_core.prompts import PromptTemplate
+
+# template = ("""You are a Moroccan tourism expert.
+#     Use the provided context to answer the question.
+#     If you don't know the answer, say so. Explain your answer in detail.
+#     Do not discuss the context in your response; just provide the answer directly.
+#     Context: {context}
+#     Question: {question}
+#     Answer:""")
+
+# rag_prompt = PromptTemplate.from_template(template)
+
+# from langchain_core.output_parsers import StrOutputParser
+# from langchain_core.runnables import RunnablePassthrough
+
+# rag_chain = (
+#     {"context": retriever, "question": RunnablePassthrough()}
+#     | rag_prompt
+#     | llm
+#     | StrOutputParser()
+# )
+
+# import gradio as gr
+
+# def rag_memory_stream(text):
+#     partial_text = ""
+#     for new_text in rag_chain.stream(text):
+#         partial_text += new_text
+#         yield partial_text
+
+# examples = ['Tourist attraction sites in Morocco', 'What are some fun activities to do in Morocco?']
+
+
+
+
+# title = "Real-time AI App with Groq API and LangChain to Answer Morroco Tourism questions"
+# demo = gr.Interface(
+#     title=title,
+#     fn=rag_memory_stream,
+#     inputs="text",
+#     outputs="text",
+#     examples=examples,
+#     allow_flagging="never",
+# )
 
-# add data to vector nstore
-vectorstore.add_texts(context_data)
 
-retriever = vectorstore.as_retriever()
+# if __name__ == "__main__":
+#     demo.launch()
 
+import os
+import pandas as pd
+import gradio as gr
+
+# Read JSON file
+df = pd.read_json("./tourisme_chatbot.json")
+
+context_data = []
+for i in range(len(df)):
+    context = ""
+    for j in range(4):
+        context += df.columns[j]
+        context += ": "
+        context += df.iloc[i, j]  # Using iloc to avoid the deprecation warning
+        context += " "
+    context_data.append(context)
+
+# Lazy initialization function
+llm = None
+embed_model = None
+vectorstore = None
+groq_key = os.environ.get('groq_api_key')
+
+def initialize_model():
+    global llm, embed_model, vectorstore
+    
+    # Only initialize the models and vector store when needed
+    if llm is None:
+        from langchain_groq import ChatGroq
+        llm = ChatGroq(model="llama-3.1-70b-versatile", api_key=groq_key)
+
+    if embed_model is None:
+        from langchain_huggingface import HuggingFaceEmbeddings
+        embed_model = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")
+
+    if vectorstore is None:
+        from langchain_chroma import Chroma
+        vectorstore = Chroma(
+            collection_name="tourism_dataset_store",
+            embedding_function=embed_model,
+            persist_directory="./",
+        )
+        vectorstore.add_texts(context_data)  # Adding the context data to the vector store
+
+# RAG Chain setup
 from langchain_core.prompts import PromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
 
+# Define prompt template
 template = ("""You are a Moroccan tourism expert.
     Use the provided context to answer the question.
     If you don't know the answer, say so. Explain your answer in detail.
@@ -55,30 +152,26 @@ template = ("""You are a Moroccan tourism expert.
 
 rag_prompt = PromptTemplate.from_template(template)
 
-from langchain_core.output_parsers import StrOutputParser
-from langchain_core.runnables import RunnablePassthrough
-
+# Create RAG chain
 rag_chain = (
-    {"context": retriever, "question": RunnablePassthrough()}
+    {"context": vectorstore.as_retriever(), "question": RunnablePassthrough()}
     | rag_prompt
     | llm
     | StrOutputParser()
 )
 
-import gradio as gr
-
+# Function for real-time stream of results
 def rag_memory_stream(text):
+    initialize_model()  # Initialize models and vector store if not done yet
     partial_text = ""
     for new_text in rag_chain.stream(text):
         partial_text += new_text
         yield partial_text
 
-examples = ['Tourist attraction sites in Morocco', 'What are some fun activities to do in Morocco?']
-
-
+# Gradio Interface setup
+examples = ['Tourist attraction sites in Morocco', 'What are some fun activities to do in Morocco?', 'What can I do in Marrakech 40000 Morocco?']
 
-
-title = "Real-time AI App with Groq API and LangChain to Answer Morroco Tourism questions"
+title = "Real-time AI App with Groq API and LangChain to Answer Morocco Tourism Questions"
 demo = gr.Interface(
     title=title,
     fn=rag_memory_stream,
@@ -88,6 +181,5 @@ demo = gr.Interface(
     allow_flagging="never",
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()