Update app.py

app.py

@@ -8,27 +8,18 @@ from transformers import pipeline
 from langchain.llms import HuggingFacePipeline
  
 
-# Instantiate chromadb instance. Data is stored on disk (a folder named 'my_vectordb' will be created in the same folder as this file).
-chroma_client = chromadb.PersistentClient(path="vector_db")
 
-# Select the embedding model to use.
-# List of model names can be found here https://www.sbert.net/docs/pretrained_models.html
+chroma_client = chromadb.PersistentClient(path="data_db")
+
+
 sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="all-mpnet-base-v2")
 
-# Use this to delete the database
-# chroma_client.delete_collection(name="my_collection")
 
-# Create the collection, aka vector database. Or, if database already exist, then use it. Specify the model that we want to use to do the embedding.
 collection = chroma_client.get_or_create_collection(name="my_collection", embedding_function=sentence_transformer_ef)
 
-# Add the data to the collection
-# collection.add(
-#     documents=documents,
-#     metadatas=metadatas,
-#     ids=ids
-# )
 
-# Streamlit app layout
+
+
 st.title("ChromaDB and HuggingFace Pipeline Integration")
 
 query = st.text_input("Enter your query:", value="director")