Update app.py

app.py

@@ -7,11 +7,11 @@ from transformers import AutoModel, AutoTokenizer, BitsAndBytesConfig
 from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, EulerDiscreteScheduler
 from parler_tts import ParlerTTSForConditionalGeneration
 import soundfile as sf
-from langchain.embeddings import OpenAIEmbeddings
-from langchain.vectorstores import Chroma 
+from langchain_community.embeddings import OpenAIEmbeddings  
+from langchain_community.vectorstores import Chroma 
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.chains import RetrievalQA
-from langchain.llms import OpenAI 
+from langchain_community.llms import OpenAI 
 from PIL import Image
 from decord import VideoReader, cpu
 import requests
@@ -19,7 +19,7 @@ import requests
 client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
 MODEL = 'llama3-groq-70b-8192-tool-use-preview'
 
-# Configure transformers to load the model with 4-bit quantization
+# Configure BitsAndBytes for 4-bit quantization
 bnb_config = BitsAndBytesConfig(
     load_in_4bit=True,
     bnb_4bit_use_double_quant=True,
@@ -27,9 +27,9 @@ bnb_config = BitsAndBytesConfig(
     bnb_4bit_compute_dtype=torch.bfloat16
 )
 
-# Load models for text, speech, and image processing
+# Load MiniCPM-V-2_6 with 4-bit quantization
 text_model = AutoModel.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True,
-    quantization_config=bnb_config, device_map="auto") 
+                                      quantization_config=bnb_config, device_map="auto")
 tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True)
 
 tts_model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler-tts-large-v1").to('cuda')