app.py

import os
from getpass import getpass
import gradio as gr
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.node_parser import SemanticSplitterNodeParser
from llama_index.embeddings import OpenAIEmbedding
from llama_index.ingestion import IngestionPipeline
from llama_index.query_engine import RetrieverQueryEngine



pinecone_api_key = os.getenv("PINECONE_API_KEY") 
openai_api_key = os.getenv("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)

# Define the initial pipeline
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 = os.getenv("INDEX_NAME")

# Initialize your index
pinecone_index = pc.Index(index_name)

# Initialize VectorStore
vector_store = PineconeVectorStore(pinecone_index=pinecone_index)

pinecone_index.describe_index_stats()


# Due to how LlamaIndex works here, if your Open AI API key was
# not set to an environment variable before, you have to set it at this point
if not os.getenv('OPENAI_API_KEY'):
    os.environ['OPENAI_API_KEY'] = openai_api_key

# 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)


# Pass in your retriever from above, which is configured to return the top 5 results
query_engine = RetrieverQueryEngine(retriever=retriever)

# Define the function to handle user input and return the query response
def query_annual_report(summary_request):
    llm_query = query_engine.query(summary_request)
    return llm_query.response

# Create the Gradio interface
iface = gr.Interface(
    fn=query_annual_report,
    inputs="text",
    outputs="text",
    title="Annual Report Summary Query",
    description="Enter your query to get the summary of the annual report."
)

# Launch the Gradio app
iface.launch()