Update app.py

app.py

@@ -1,25 +1,18 @@
 import os
 from getpass import getpass
-import streamlit as st
+import gradio as gr
+
+pinecone_api_key = os.getenv("PINECONE_API_KEY") or getpass("Enter your Pinecone API Key: ")
+openai_api_key = os.getenv("OPENAI_API_KEY") or getpass("Enter your OpenAI API Key: ")
+
 from llama_index.node_parser import SemanticSplitterNodeParser
 from llama_index.embeddings import OpenAIEmbedding
 from llama_index.ingestion import IngestionPipeline
-from pinecone.grpc import PineconeGRPC
-from pinecone import ServerlessSpec
-from llama_index.vector_stores import PineconeVectorStore
-from llama_index import VectorStoreIndex
-from llama_index.retrievers import VectorIndexRetriever
-from llama_index.query_engine import RetrieverQueryEngine
-
-# Streamlit UI for API keys
-st.title("Annual Report Summary Query")
 
-# Retrieve API keys
-pinecone_api_key = st.text_input("Enter your Pinecone API Key:", type="password")
-openai_api_key = st.text_input("Enter your OpenAI API Key:", type="password")
-
-# Initialize the model and pipeline
+# This will be the model we use both for Node parsing and for vectorization
 embed_model = OpenAIEmbedding(api_key=openai_api_key)
+
+# Define the initial pipeline
 pipeline = IngestionPipeline(
     transformations=[
         SemanticSplitterNodeParser(
@@ -31,35 +24,52 @@ pipeline = IngestionPipeline(
     ],
 )
 
+from pinecone.grpc import PineconeGRPC
+from pinecone import ServerlessSpec
+
+from llama_index.vector_stores import PineconeVectorStore
+
 # Initialize connection to Pinecone
 pc = PineconeGRPC(api_key=pinecone_api_key)
 index_name = "anualreport"
+
+# Initialize your index
 pinecone_index = pc.Index(index_name)
+
+# Initialize VectorStore
 vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
+
 pinecone_index.describe_index_stats()
 
-# Set OpenAI API key environment variable if not set
+from llama_index import VectorStoreIndex
+from llama_index.retrievers import VectorIndexRetriever
+
+# Set the OpenAI API key if not already set
 if not os.getenv('OPENAI_API_KEY'):
     os.environ['OPENAI_API_KEY'] = openai_api_key
 
-# Instantiate VectorStoreIndex object
+# Instantiate VectorStoreIndex object from our vector_store object
 vector_index = VectorStoreIndex.from_vector_store(vector_store=vector_store)
+
+# Grab 5 search results
 retriever = VectorIndexRetriever(index=vector_index, similarity_top_k=5)
-query_engine = RetrieverQueryEngine(retriever=retriever)
 
-# User query input
-query = st.text_input("Enter your query:", "Summary of the Annual Report?")
+from llama_index.query_engine import RetrieverQueryEngine
 
-# Process query and display results
-if st.button("Get Summary"):
-    llm_query = query_engine.query(query)
-    st.write("Results:")
-    st.write(llm_query.response)
+# Pass in your retriever from above, which is configured to return the top 5 results
+query_engine = RetrieverQueryEngine(retriever=retriever)
 
-    # Display each result
-    for idx, result in enumerate(llm_query.response):
-        st.write(f"Result {idx+1}: {result.get_content()}")
+def query_anual_report(query):
+    response = query_engine.query(query)
+    return response.response
 
-if __name__ == "__main__":
-    st._main_run_clExplicit('--runner', '-')
+# Define Gradio Interface
+iface = gr.Interface(
+    fn=query_anual_report,
+    inputs=gr.inputs.Textbox(lines=2, placeholder="Ask something..."),
+    outputs="text",
+    title="Annual Report Query",
+    description="Ask questions about the annual report."
+)
 
+iface.launch()