Update app.py

app.py

@@ -2,11 +2,10 @@ from transformers import T5Tokenizer, T5ForConditionalGeneration
 from langchain.llms import HuggingFacePipeline
 from langchain.prompts import PromptTemplate
 from langchain.chains import RetrievalQA
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.vectorstores import Chroma
-from langchain_community.document_loaders import TextLoader
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.document_loaders import TextLoader
 from langchain.text_splitter import CharacterTextSplitter
-from langchain_community.document_loaders import WikipediaLoader
 from transformers import pipeline
 
 # Load T5-small model and tokenizer
@@ -26,19 +25,16 @@ text_generation_pipeline = pipeline(
 # Create a LangChain LLM from the pipeline
 llm = HuggingFacePipeline(pipeline=text_generation_pipeline)
 
-# Load and process documents
-#loader = TextLoader("https://en.wikipedia.org/wiki/Artificial_neuron")
-
-
-# Load content from Wikipedia
-loader = WikipediaLoader(query="Artificial neuron", load_max_docs=1)
+# Load and process documents from a local file
+loader = TextLoader("NeuralNetworkWikipedia.txt")
 documents = loader.load()
-
 text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
 texts = text_splitter.split_documents(documents)
 
-# Create embeddings and vector store
-embeddings = HuggingFaceEmbeddings()
+# Create embeddings using a smaller model
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+
+# Create vector store
 db = Chroma.from_documents(texts, embeddings)
 
 # Create a retriever