Update app.py

app.py

@@ -1,16 +1,14 @@
 import streamlit as st
 from langchain.prompts import FewShotChatMessagePromptTemplate
 from langchain.prompts.example_selector import LengthBasedExampleSelector
-from langchain_huggingface import HuggingFaceEndpoint, HuggingFacePipeline
-from langchain.chains import LLMChain
-from langchain.prompts import PromptTemplate
+from langchain.llms import HuggingFaceHub
 from datasets import load_dataset
-from transformers import pipeline
 
-# Load dataset (using knkarthick/dialogsum as an example)
+# Load dataset (you can use any summarization dataset here)
 @st.cache_data
 def load_examples():
-    dataset = load_dataset("knkarthick/dialogsum", split="train[:5]")  # Take only 5 for speed
+    # Using 'knkarthick/dialogsum' as an example dataset
+    dataset = load_dataset("knkarthick/dialogsum", split="train[:5]")  # Load a subset for testing
     examples = []
     for example in dataset:
         examples.append({
@@ -19,13 +17,9 @@ def load_examples():
         })
     return examples
 
+# Load few-shot examples from the dataset
 examples = load_examples()
 
-# Load the Hugging Face model
-hf_endpoint = HuggingFaceEndpoint(
-    endpoint_url="https://api-inference.huggingface.co/models/google/pegasus-xsum"  # or any model you like
-)
-
 # Create FewShotChatMessagePromptTemplate
 example_prompt = FewShotChatMessagePromptTemplate.from_examples(
     examples=examples,
@@ -35,10 +29,13 @@ example_prompt = FewShotChatMessagePromptTemplate.from_examples(
     suffix="Now summarize this:\n{input}"
 )
 
-# Streamlit UI
-st.title("💬 Dialogue Summarizer using Few-Shot Prompt + T5 (via Langchain)")
+# Set up Hugging Face model (you can replace it with any other available model)
+llm = HuggingFaceHub(repo_id="t5-small", task="summarization")
 
-input_text = st.text_area("📝 Paste your conversation:")
+# Streamlit UI setup
+st.title("📝 Dialogue Summarizer using Few-Shot Prompt + T5")
+
+input_text = st.text_area("📝 Paste your conversation here:")
 
 if st.button("Generate Summary"):
     if input_text.strip():
@@ -49,12 +46,9 @@ if st.button("Generate Summary"):
             for msg in messages:
                 st.markdown(f"**{msg.type.upper()}**:\n```\n{msg.content}\n```")
 
-        # Set up HuggingFacePipeline with the model endpoint
-        hf_pipeline = HuggingFacePipeline(pipeline="summarization", model=hf_endpoint)
-
-        # Generate summary
-        summary = hf_pipeline(messages[0].content)
+        # Get the summary using the Hugging Face model
+        response = llm(messages[0].content)
         st.success("✅ Summary:")
-        st.write(summary[0]['summary_text'])
+        st.write(response['text'])
     else:
         st.warning("Please enter some text.")