Changed to Qwen.

app.py

@@ -3,7 +3,7 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
-import openai  # Import OpenAI library
+from huggingface_hub import InferenceClient  # Import Hugging Face InferenceClient
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -14,10 +14,11 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
-        # Initialize OpenAI client - you'll need to set OPENAI_API_KEY in environment variables
-        self.openai_client = openai.OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
-        if not os.getenv("OPENAI_API_KEY"):
-            print("Warning: OPENAI_API_KEY not found in environment variables.")
+        self.hf_client = InferenceClient(
+            model="Qwen/Qwen1.5-7B-Chat",  # Using Qwen model as default
+            token=os.getenv("HF_TOKEN")  # Optional: Set HF_TOKEN if you have one
+        )
+        print("Using Hugging Face model: Qwen/Qwen1.5-7B-Chat")
     
     def break_down_question(self, question: str) -> list:
         """
@@ -40,21 +41,22 @@ class BasicAgent:
             Question: {question}
             """
             
-            # Call the OpenAI API to get the breakdown
-            response = self.openai_client.chat.completions.create(
-                model="gpt-3.5-turbo",
-                messages=[
-                    {"role": "system", "content": "You are a helpful assistant that breaks down questions into key search terms."},
-                    {"role": "user", "content": prompt}
-                ],
+            # Call the Hugging Face model to get the breakdown
+            response = self.hf_client.text_generation(
+                prompt=prompt,
+                max_new_tokens=150,
                 temperature=0.3,
-                max_tokens=150
+                repetition_penalty=1.1,
+                do_sample=True
             )
             
             # Extract the search terms from the response
-            search_terms = response.choices[0].message.content.strip().split('\n')
+            search_terms = response.strip().split('\n')
             search_terms = [term.strip() for term in search_terms if term.strip()]
             
+            # Limit to 3 search terms maximum
+            search_terms = search_terms[:3]
+            
             print(f"Question broken down into {len(search_terms)} search terms: {search_terms}")
             return search_terms
             
@@ -149,7 +151,7 @@ class BasicAgent:
             # Join the results with clear separation
             combined_results = "\n\n--- Next Search Result ---\n\n".join(all_results)
             
-            # Use LLM to synthesize a coherent answer from the search results
+            # Use Hugging Face model to synthesize a coherent answer from the search results
             try:
                 synthesis_prompt = f"""
                 Based on the following search results, please provide a comprehensive answer to this question:
@@ -162,17 +164,16 @@ class BasicAgent:
                 Answer:
                 """
                 
-                response = self.openai_client.chat.completions.create(
-                    model="gpt-3.5-turbo",
-                    messages=[
-                        {"role": "system", "content": "You are a helpful assistant that synthesizes information to answer questions accurately."},
-                        {"role": "user", "content": synthesis_prompt}
-                    ],
+                # Call the Hugging Face model to synthesize an answer
+                response = self.hf_client.text_generation(
+                    prompt=synthesis_prompt,
+                    max_new_tokens=500,
                     temperature=0.5,
-                    max_tokens=500
+                    repetition_penalty=1.05,
+                    do_sample=True
                 )
                 
-                answer = response.choices[0].message.content.strip()
+                answer = response.strip()
                 print("Agent returning synthesized answer from search results.")
                 return answer
             

requirements.txt

@@ -1,3 +1,3 @@
 gradio
 requests
-openai
+huggingface_hub