Update app.py

app.py

@@ -3,7 +3,8 @@ from pathlib import Path
 import streamlit as st
 from transformers import pipeline
 from dotenv import load_dotenv
-from langchain import PromptTemplate, LLNChain, OpenAI
+from langchain import PromptTemplate, HuggingFaceHub, LLMChain
+
 if Path(".env").is_file():
     load_dotenv(".env")
 st.set_page_config(layout="wide")
@@ -12,29 +13,29 @@ HF_TOKEN = os.getenv("HF_TOKEN")
 def img2Text(url):
     image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
     text = image_to_text(url)
-    st.header("Caption :")
+    st.subheader("Caption :")
     st.subheader(text)
     print(text)
     return text
-img2Text(test-photo.png)
+img2Text("photo.png")
 
 #llm
 def generate_story(scenario):
     template = """
     You are a story teller;
-    You can generate a short story based on a simple narrative, the story should be no mmomre than 20 words;
+    You can generate a short story based on a simple narrative, the story should be no momre than 20 words;
 
     CONTEXT: {scenario}
     STORY:
     """
 
     prompt = PromptTemplate(template=template,input_variables=["scenario"])
-
-    story_llm = LLMChain(llm=OpenAI(
-        model_name="gpt-3.5-turbo", temperature=1), prompt=prompt, verbose=True)
-
-    story = story_llm.predict(scenario=scenario)
-    st.header("Story :")
+    llm_chain = LLMChain(prompt=prompt, 
+                     llm=HuggingFaceHub(repo_id="google/flan-t5-xl", 
+                                        model_kwargs={"temperature":0, 
+                                                      "max_length":64}))
+    story =llm_chain.run(scenario)
+    st.subheader("Story :")
     st.subheader(story)
     print(story)
     return story