Update app.py

app.py

@@ -1,4 +1,5 @@
 import os
+from getpass import getpass
 import streamlit as st
 from llama_index.node_parser import SemanticSplitterNodeParser
 from llama_index.embeddings import OpenAIEmbedding
@@ -10,49 +11,55 @@ from llama_index import VectorStoreIndex
 from llama_index.retrievers import VectorIndexRetriever
 from llama_index.query_engine import RetrieverQueryEngine
 
-# Streamlit interface for inputting API keys
-st.title("Annual Report Summary Chatbot")
-pinecone_api_key = os.getenv("PINECONE_API_KEY")
-openai_api_key = os.getenv("OPENAI_API_KEY")
+# Streamlit UI for API keys
+st.title("Annual Report Summary Query")
 
-if pinecone_api_key and openai_api_key:
-    # This will be the model we use both for Node parsing and for vectorization
-    embed_model = OpenAIEmbedding(api_key=openai_api_key)
+# 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")
 
-    # Define the initial pipeline
-    pipeline = IngestionPipeline(
-        transformations=[
-            SemanticSplitterNodeParser(
-                buffer_size=1,
-                breakpoint_percentile_threshold=95,
-                embed_model=embed_model,
-            ),
-            embed_model,
-        ],
-    )
+# Initialize the model and pipeline
+embed_model = OpenAIEmbedding(api_key=openai_api_key)
+pipeline = IngestionPipeline(
+    transformations=[
+        SemanticSplitterNodeParser(
+            buffer_size=1,
+            breakpoint_percentile_threshold=95,
+            embed_model=embed_model,
+        ),
+        embed_model,
+    ],
+)
 
-    # Initialize connection to Pinecone
-    pc = PineconeGRPC(api_key=pinecone_api_key)
-    index_name = "anualreport"
+# Initialize connection to Pinecone
+pc = PineconeGRPC(api_key=pinecone_api_key)
+index_name = "anualreport"
+pinecone_index = pc.Index(index_name)
+vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
+pinecone_index.describe_index_stats()
 
-    # Initialize your index
-    pinecone_index = pc.Index(index_name)
+# Set OpenAI API key environment variable if not set
+if not os.getenv('OPENAI_API_KEY'):
+    os.environ['OPENAI_API_KEY'] = openai_api_key
 
-    # Initialize VectorStore
-    vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
+# Instantiate VectorStoreIndex object
+vector_index = VectorStoreIndex.from_vector_store(vector_store=vector_store)
+retriever = VectorIndexRetriever(index=vector_index, similarity_top_k=5)
+query_engine = RetrieverQueryEngine(retriever=retriever)
 
-    pinecone_index.describe_index_stats()
+# User query input
+query = st.text_input("Enter your query:", "Summary of the Annual Report?")
 
-    # Instantiate VectorStoreIndex object from our vector_store object
-    vector_index = VectorStoreIndex.from_vector_store(vector_store=vector_store)
+# Process query and display results
+if st.button("Get Summary"):
+    llm_query = query_engine.query(query)
+    st.write("Results:")
+    st.write(llm_query.response)
 
-    # Grab 5 search results
-    retriever = VectorIndexRetriever(index=vector_index, similarity_top_k=5)
+    # Display each result
+    for idx, result in enumerate(llm_query.response):
+        st.write(f"Result {idx+1}: {result.get_content()}")
 
-    # Query vector DB
-    query_engine = RetrieverQueryEngine(retriever=retriever)
+if __name__ == "__main__":
+    st._main_run_clExplicit('--runner', '-')
 
-    user_query = st.text_input("Ask a question about the annual report:")
-    if st.button("Submit"):
-        llm_query = query_engine.query(user_query)
-        st.write(llm_query.response)