towards transferring over work from notebook

app.py

@@ -5,7 +5,18 @@ from typing import Iterator
 import gradio as gr
 import spaces
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer, TextStreamer
+from llama_index.core.prompts.prompts import SimpleInputPrompt
+from llama_index.llms.huggingface import HuggingFaceLLM
+from llama_index.legacy.embeddings.langchain import LangchainEmbedding
+from langchain.embeddings.huggingface import HuggingFaceEmbeddings # This import should now work
+from sentence_transformers import SentenceTransformer
+
+from llama_index.core import set_global_service_context, ServiceContext
+
+from llama_index.core import VectorStoreIndex, download_loader, Document # Import Document
+from pathlib import Path
+import fitz  # PyMuPDF
 
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 512
@@ -14,9 +25,9 @@ DEFAULT_SYS_PROMPT = """\
 """
 
 DESCRIPTION = """\
-# Test Chat Information System for MEPO Summer Bridge 2024 courtesy of Dr. Dancy & THiCC Lab
+# Test Chat Information System for MEPO 2024 courtesy of Dr. Dancy & THiCC Lab
 
-Duplicated then modified from [llama-2 7B example](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat)
+Duplicated, then modified from [llama-2 7B example](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat)
 """
 
 LICENSE = """
@@ -38,7 +49,7 @@ if torch.cuda.is_available():
     tokenizer.use_default_system_prompt = False
 
 
-@spaces.GPU(duration=120)
+@spaces.GPU(duration=240)
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],

requirements.txt

@@ -5,4 +5,10 @@ scipy==1.13.0
 sentencepiece==0.2.0
 spaces==0.28.3
 torch==2.0.0
-transformers==4.41.0
+transformers==4.41.0 
+#einops
+sentence-transformers
+PyPDF2
+PyMuPDF
+langchain
+langchain-community