Create app.py

app.py

@@ -0,0 +1,74 @@
+import gradio as gr
+
+
+from llama_index import (
+    ServiceContext,
+    SimpleDirectoryReader,
+    StorageContext,
+    VectorStoreIndex,
+    set_global_service_context,
+)
+from llama_index.llms import Gemini
+from llama_index.embeddings import GeminiEmbedding
+
+model_name = "models/embedding-001"
+
+
+llm = Gemini()
+embed_model = GeminiEmbedding(
+    model_name=model_name, api_key=GOOGLE_API_KEY, title="this is a document"
+)
+# Reads pdfs at "./" path
+documents = (
+    SimpleDirectoryReader(
+        input_dir = './',
+        required_exts = [".pdf"])
+        .load_data()
+)
+
+# ServiceContext is a bundle of commonly used 
+# resources used during the indexing and 
+# querying stage 
+service_context = (
+    ServiceContext
+    .from_defaults(
+        llm=llm, 
+        embed_model=embed_model, 
+        chunk_size=545
+    )
+)
+set_global_service_context(service_context)
+print("node passer11")
+# Node represents a “chunk” of a source Document
+nodes = (
+    service_context
+    .node_parser
+    .get_nodes_from_documents(documents)
+)
+print("node passer")
+# offers core abstractions around storage of Nodes, 
+# indices, and vectors
+storage_context = StorageContext.from_defaults()
+storage_context.docstore.add_documents(nodes)
+print("node passer")
+# Create the vectorstore index
+index = (
+    VectorStoreIndex
+    .from_documents(
+        documents, 
+        storage_context=storage_context, 
+        llm=llm
+        )
+)
+print("node passer")
+query_engine = index.as_query_engine()
+
+# Query the index
+
+
+def greet(name):
+    response = query_engine.query(name)
+    return response
+
+iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+iface.launch()