Create app.py

app.py

@@ -0,0 +1,58 @@
+
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, ServiceContext
+from llama_index.llms.huggingface import HuggingFaceLLM
+import torch
+
+documents = SimpleDirectoryReader("/content/Data").load_data()
+from llama_index.core.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."
+
+
+query_wrapper_prompt = SimpleInputPrompt("<|USER|>{query_str}<|ASSISTANT|>")
+
+
+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="microsoft/phi-2",
+    model_name="microsoft/phi-2",
+    device_map="cuda",
+    # uncomment this if using CUDA to reduce memory usage
+    model_kwargs={"torch_dtype": torch.bfloat16}
+)
+
+
+!pip install llama-index-embeddings-huggingface
+
+
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+
+# loads BAAI/bge-small-en
+# embed_model = HuggingFaceEmbedding()
+
+# loads BAAI/bge-small-en-v1.5
+embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
+
+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()
+
+def predict(input, history):
+  response = query_engine.query(input)
+  return str(response)
+
+
+
+import gradio as gr
+
+gr.ChatInterface(predict).launch(share=True)