Update app.py

app.py

@@ -3,10 +3,10 @@ import requests
 
 # Replace with your actual LangSmith API key
 LANGSMITH_API_KEY = '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'
-LANGSMITH_ENDPOINT = 'https://smith.langchain.com/o/b7d2cb3f-e589-52bb-9b8a-2e8483e4ee8d/settings'
+LANGSMITH_ENDPOINT = 'https://smith.langchain.com/o/b7d2cb3f-e589-52bb-9b8a-2e8483e4ee8d/tailor'  # Make sure this is the correct endpoint
 
-# Initialize the Hugging Face conversational pipeline
-conversational_pipeline = pipeline('conversational', model='facebook/blenderbot-3B')
+# Initialize the Hugging Face text generation pipeline with BlenderBot
+conversational_pipeline = pipeline('text-generation', model='facebook/blenderbot-3B')
 
 def tailor_with_langsmith(model_data):
     headers = {
@@ -22,11 +22,11 @@ def tailor_with_langsmith(model_data):
 
 def create_custom_conversation(prompt):
     # Step 1: Get response from Hugging Face model
-    hf_response = conversational_pipeline(prompt)
+    hf_response = conversational_pipeline(prompt, max_length=50)  # Adjust max_length as needed
     hf_reply = hf_response[0]['generated_text']
 
     # Step 2: Tailor the response using LangSmith
-    tailored_response = tailor_with_langsmith(hf_reply)
+    tailored_response = tailor_with_langsmith({'model_data': hf_reply})
     tailored_reply = tailored_response.get('tailored_reply', '')
 
     return tailored_reply