query.py

def query_pinecone(query, top_k):
    # generate embeddings for the query
    xq = retriever.encode([query]).tolist()
    # search pinecone index for context passage with the answer
    xc = index.query(xq, top_k=top_k, include_metadata=True)
    return xc

def format_query(query, context):
    # extract passage_text from Pinecone search result and add the <P> tag
    context = [f"<P> {m['metadata']['passage_text']}" for m in context]
    # concatinate all context passages
    context = " ".join(context)
    # contcatinate the query and context passages
    query = f"question: {query} context: {context}"
    return query

query = "when was the first electric power system built?"
result = query_pinecone(query, top_k=1)

from pprint import pprint
# format the query in the form generator expects the input
query = format_query(query, result["matches"])
pprint(query)