Update app.py

app.py

@@ -6,7 +6,6 @@ from langchain_community.vectorstores import FAISS
 #from langchain_community.vectorstores import Chroma
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings
 #from langchain_community.embeddings import OllamaEmbeddings
-import ollama
 
 # Function to load, split, and retrieve documents from a URL
 def load_and_retrieve_docs(url):
@@ -48,8 +47,12 @@ def rag_chain(url, question):
     retrieved_docs = retriever.invoke(question)
     formatted_context = format_docs(retrieved_docs)
     formatted_prompt = f"Question: {question}\n\nContext: {formatted_context}"
-    response = ollama.chat(model='llama3', messages=[{'role': 'user', 'content': formatted_prompt}])
-    return response['message']['content']
+    
+    # Using HuggingFace transformers for generating response
+    chat_pipeline = pipeline('text-generation', model='Llama3-8b-8192')  # Use the appropriate model here
+    response = chat_pipeline(formatted_prompt, max_length=512, num_return_sequences=1)
+    
+    return response[0]['generated_text']
 
 # Gradio interface
 iface = gr.Interface(