Update app.py

app.py

@@ -1,14 +1,13 @@
-# incident_bot.py
+# app.py
 import gradio as gr
-from langchain.embeddings import HuggingFaceEmbeddings
+from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.vectorstores import FAISS
 from langchain.llms import HuggingFacePipeline
 from langchain.chains import RetrievalQA
-from langchain.document_loaders import TextLoader
 from langchain.text_splitter import CharacterTextSplitter
 from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 
-# 🔹 Load alerts/logs dataset inline
+# 🔹 Sample logs (inline dataset)
 sample_logs = """
 [ERROR] Disk usage exceeded 90% on node-3
 [WARNING] High memory usage detected on node-2
@@ -25,10 +24,10 @@ docs = text_splitter.create_documents([sample_logs])
 embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
 db = FAISS.from_documents(docs, embeddings)
 
-# 🔹 Load Mistral 7B Instruct (CPU-friendly)
-model_id = "mistralai/Mistral-7B-Instruct-v0.1"
+# 🔹 Load TinyLlama (fast + CPU-friendly)
+model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
+model = AutoModelForCausalLM.from_pretrained(model_id)
 llm_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=256)
 llm = HuggingFacePipeline(pipeline=llm_pipeline)
 
@@ -37,7 +36,6 @@ qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=db.as_retriever())
 
 # 🔹 Gradio chatbot UI
 def chat(query):
-    response = qa_chain.run(query)
-    return response
+    return qa_chain.run(query)
 
 gr.ChatInterface(chat, title="Incident RCA Bot 🚨", description="Ask about logs, errors, and root causes").launch()