updated app.py with jupyternotebook code.

app.py

@@ -1,15 +1,90 @@
 import gradio as gr
+import json
+from langchain.llms import GooglePalm
 
-def greet(name, intensity):
-    return "Hello, " + name + "!" * int(intensity)
+api_key = "AIzaSyCdM_aAIsW_nPbjarOF83mbX1_z1cVX2_M"
 
-demo = gr.Interface(
-    fn=greet,
-    inputs=["text", "slider"],
-    outputs=["text"],
+llm = GooglePalm(google_api_key = api_key, temperature=0.7)
+
+from langchain.document_loaders.csv_loader import CSVLoader
+
+loader = CSVLoader(file_path='aiotsmartlabs_faq.csv', source_column = 'prompt')
+data = loader.load()
+
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+
+# instructor_embeddings = HuggingFaceEmbeddings(model_name = "Alibaba-NLP/gte-Qwen2-7B-instruct") # best model <-- but too big
+instructor_embeddings = HuggingFaceEmbeddings(model_name = "BAAI/bge-m3")
+# instructor_embeddings = HuggingFaceEmbeddings()
+
+vectordb = FAISS.from_documents(documents = data, embedding = instructor_embeddings)
+
+# e = embeddings_model.embed_query("What is your refund policy")
+
+retriever = vectordb.as_retriever()
+
+from langchain.prompts import PromptTemplate
+
+prompt_template = """Given the following context and a question, generate an answer based on the context only.
+
+In the answer try to provide as much text as possible from "response" section in the source document context without making much changes.
+If somebody asks "Who are you?" or a similar phrase, state "I am Rishi's assistant built using a Large Language Model!"
+If the answer is not found in the context, kindly state "I don't know. Please ask Rishi on Discord. Discord Invite Link: https://discord.gg/6ezpZGeCcM. Or email at rishi@aiotsmartlabs.com" Don't try to make up an answer.
+
+CONTEXT: {context}
+
+QUESTION: {question}"""
+
+PROMPT = PromptTemplate(
+    template = prompt_template, input_variables = ["context", "question"]
+)
+
+from langchain.chains import RetrievalQA
+
+chain = RetrievalQA.from_chain_type(llm = llm,
+            chain_type="stuff",
+            retriever=retriever,
+            input_key="query",
+            return_source_documents=True,
+            chain_type_kwargs = {"prompt": PROMPT})
+
+# Load your LLM model and necessary components
+# Assume `chain` is a function defined in your notebook that takes a query and returns the output as shown
+# For this example, we'll assume the model and chain function are already available
+
+def chatbot(query):
+    response = chain(query)
+    # Extract the 'result' part of the response
+    result = response.get('result', 'Sorry, I could not find an answer.')
+    return result
+
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=chatbot,  # Function to call
+    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter your question here..."),  # Input type
+    outputs="text",  # Output type
+    title="Hugging Face LLM Chatbot",
+    description="Ask any question related to the documents and get an answer from the LLM model.",
 )
 
-demo.launch()
+# Launch the interface
+iface.launch()
+
+# Save this file as app.py and push it to your Hugging Face Space repository
+
+# import gradio as gr
+
+# def greet(name, intensity):
+#     return "Hello, " + name + "!" * int(intensity)
+
+# demo = gr.Interface(
+#     fn=greet,
+#     inputs=["text", "slider"],
+#     outputs=["text"],
+# )
+
+# demo.launch()
 
 
 # import gradio as gr