Upload 2 files

app.py

@@ -23,14 +23,22 @@ import torch
 from langchain_community.llms.ollama import Ollama
 from langchain.prompts import ChatPromptTemplate
 from langchain_community.vectorstores import FAISS
+
+#from langchain import PromtTemplate, HuggingFaceHub, LLMChain
 # from langchain.vectorstores import faiss
 # from langchain.vectorstores import FAISS
 
 import time
 from time import sleep
 from stqdm import stqdm
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
 
+os.environ['HUGGINGFACEHUB_API_TOKEN'] = os.getenv("HUGGINGFACEHUB_API_TOKEN")
 
+print(os.environ)
 
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
@@ -272,8 +280,13 @@ def chat_actions():
     prompt_template = ChatPromptTemplate.from_template(PROMPT_TEMPLATE)
     prompt = prompt_template.format(context=context_text, question=query)
 
-    model = Ollama(model="llama3")
-    response_text = model.invoke(prompt)
+    try:
+        model = Ollama(model="llama3")
+        response_text = model.invoke(prompt)
+        st.write(response_text)
+    except Exception as e:
+        st.error(f"Error invoke: {e}")
+
 
     formatted_response = f"Response: {response_text}\nSources: {sources}"
     print(formatted_response)

requirements.txt

@@ -16,4 +16,5 @@ langchain_community
 langchain
 # faiss-gpu
 faiss-cpu==1.7.2
-stqdm
+stqdm
+python-dotenv