Update app.py

app.py

@@ -1,16 +1,24 @@
-from langchain import PromptTemplate
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.llms import CTransformers
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_community.llms import CTransformers
 from langchain.chains import RetrievalQA
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
 from huggingface_hub import hf_hub_download
-
-
+import os
 
 DB_FAISS_PATH = "vectorstores/db_faiss"
 
+def load_llm():
+    model_name = 'TheBloke/Llama-2-7B-Chat-GGML'  # Replace with the actual model repository name
+    model_path = hf_hub_download(repo_id=model_name, filename='pytorch_model.bin', cache_dir='./models')
+    llm = CTransformers(
+        model=model_path,
+        model_type="llama",
+        max_new_tokens=512,
+        temperature=0.5
+    )
+    return llm
+
 custom_prompt_template = """Use the following pieces of information to answer the user's question.
 If you don't know the answer, just say that you don't know, don't try to make up an answer.
 
@@ -25,15 +33,6 @@ def set_custom_prompt():
     prompt = PromptTemplate(template=custom_prompt_template, input_variables=['context', 'question'])
     return prompt
 
-def load_llm():
-    llm = CTransformers(
-        model=model,
-        model_type="llama",
-        max_new_tokens=512,
-        temperature=0.5
-    )
-    return llm
-
 def retrieval_QA_chain(llm, prompt, db):
     qachain = RetrievalQA.from_chain_type(
         llm=llm,
@@ -66,14 +65,14 @@ def chatbot_response(query):
     except Exception as e:
         return f"An error occurred: {str(e)}"
 
-# Create a Gradio interface with updated API
 iface = gr.Interface(
     fn=chatbot_response,
     inputs=gr.Textbox(lines=2, placeholder="Enter your question..."),
     outputs="text",
     title="Medical Chatbot",
-    description="Ask a medical question and get answers based on the provided context."
+    description="Ask a medical question and get answers based on the provided context.",
+    live=True
 )
 
-# Launch the Gradio app
 iface.launch()
+