Update app.py

app.py

@@ -20,7 +20,8 @@ from llama_index import VectorStoreIndex, SimpleDirectoryReader, ServiceContext
 from llama_index.llms import HuggingFaceLLM
 from langchain.document_loaders import PyPDFLoader
 
-documents = SimpleDirectoryReader("Dat").load_data()
+documents = [SimpleDirectoryReader("Dat").load_data(file_path=file)[0] for file in os.listdir("Dat")]
+documents = [CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=0).split_text(doc) for doc in documents]
 
 from llama_index.prompts.prompts import SimpleInputPrompt
 
@@ -67,8 +68,8 @@ query_wrapper_prompt = SimpleInputPrompt("<|USER|>{query_str}<|ASSISTANT|>")
 import torch
 
 llm = HuggingFaceLLM(
-    context_window=4096,
-    max_new_tokens=256,
+    context_window=2048,
+    max_new_tokens=128,
     generate_kwargs={"temperature": 0.5, "do_sample": False},
     system_prompt=system_prompt,
     query_wrapper_prompt=query_wrapper_prompt,
@@ -87,7 +88,7 @@ embed_model = LangchainEmbedding(
 )
 
 service_context = ServiceContext.from_defaults(
-    chunk_size=1024,
+    chunk_size=512,
     llm=llm,
     embed_model=embed_model
 )
@@ -95,9 +96,6 @@ service_context = ServiceContext.from_defaults(
 index = VectorStoreIndex.from_documents(documents, service_context=service_context)
 
 query_engine = index.as_query_engine()
-response = query_engine.query("What is cyclothymic disorder?")
-
-print(response)
 
 import gradio as gr