Update app.py

app.py

@@ -1,8 +1,65 @@
-message = "hi hello world"
+import logging
+import sys
+
+logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
+
+from llama_index import VectorStoreIndex, SimpleDirectoryReader, ServiceContext
+from llama_index.llms import HuggingFaceLLM
+
+documents = SimpleDirectoryReader("/content/drive/MyDrive/data").load_data()
+
+from llama_index.prompts.prompts import SimpleInputPrompt
+
+
+system_prompt = "You are a Q&A assistant. Your goal is to answer questions as accurately as possible based on the instructions and context provided."
+
+
+
+# This will wrap the default prompts that are internal to llama-index
+query_wrapper_prompt = SimpleInputPrompt("<|USER|>{query_str}<|ASSISTANT|>")
+
+import torch
+
+llm = HuggingFaceLLM(
+    context_window=4096,
+    max_new_tokens=256,
+    generate_kwargs={"temperature": 0.0, "do_sample": False},
+    system_prompt=system_prompt,
+    query_wrapper_prompt=query_wrapper_prompt,
+    tokenizer_name="NousResearch/Llama-2-7b-hf",
+    model_name="NousResearch/Llama-2-7b-hf",
+    device_map="auto",
+    # uncomment this if using CUDA to reduce memory usage
+    model_kwargs={"torch_dtype": torch.float16 , "load_in_8bit":True}
+)
+
+from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+from llama_index import LangchainEmbedding, ServiceContext
+
+embed_model = LangchainEmbedding(
+  HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+)
+
+service_context = ServiceContext.from_defaults(
+    chunk_size=1024,
+    llm=llm,
+    embed_model=embed_model
+)
+
+index = VectorStoreIndex.from_documents(documents, service_context=service_context)
+
+#query_engine = index.as_query_engine()
+#response = query_engine.query("what is the name of this document?")
+
+#print(response)
+
 
 import gradio as gr
 def random_response(message, history):
-  return message + "heya"
+    query_engine = index.as_query_engine()
+    response = query_engine.query(message)
+    return response
 
 demo = gr.ChatInterface(random_response)
 if __name__ == "__main__":